diff --git a/README.md b/README.md index 45b5771..c2424fd 100644 --- a/README.md +++ b/README.md @@ -100,7 +100,7 @@ If you are comfortable with your skills, you can run the other 4 versions. You c #### **TensorRT Setup help** In our testing, the screenshot engine was the bottleneck. Tensorrt is only available via download from NVIDIA's site. -You will need to make an account. Just go to this link and get `TensorRT 8.4 GA`. https://developer.nvidia.com/tensorrt You will need to install it via the .whl file they give you. You may also need https://developer.nvidia.com/cudnn. +You will need to make an account. Just go to this link and get `TensorRT 8.5 GA Update 2`. https://developer.nvidia.com/tensorrt You will need to install it via the .whl file they give you. You may also need https://developer.nvidia.com/cudnn. Sometimes you will need to remake the .engine model. To do this you need to visit the [YoloV5's Github repo](https://github.com/ultralytics/yolov5) and download it. Then execute the `export.py` script in the repo with the command below. This can take up to 20 minutes and have no visual feedback. It's not frozen, just looks like it. @@ -110,12 +110,14 @@ NOTE, you will need to use the provided or download a new version of the yolov5 ### REQUIREMENTS - Nvidia RTX 2050 or higher -- Nvidia CUDA Toolkit 11.3 (https://developer.nvidia.com/cuda-11.3.0-download-archive) +- One of the following + - Nvidia CUDA Toolkit 11.6 (Most compatibility) (https://developer.nvidia.com/cuda-11-6-0-download-archive) + - Nvidia CUDA Toolkit 11.7 (No onnx support currently, faster) (https://developer.nvidia.com/cuda-11-7-0-download-archive) ### Pre-setup 1. Unzip the file and place the folder somewhere easy to access -2. Make sure you have a pet Python (aka install python) - https://www.python.org/ +2. Make sure you have a pet Python (aka install python, use 3.10) - https://www.python.org/ ***IF YOU GET THE FOLLOWING ERROR `python is not recognized as an internal or external command, operable program, or batch file` Watch This: https://youtu.be/E2HvWhhAW0g*** @@ -123,7 +125,8 @@ NOTE, you will need to use the provided or download a new version of the yolov5 3. (Windows Users) Open up either `PowerShell` or `Command Prompt`. This can be done by pressing the Windows Key and searching for one of those applications. -4. To install `PyTorch` go to this website, https://pytorch.org/get-started/locally/, and Select the stable build, your OS, Pip, Python and CUDA 11.3. Then select the text that is generated and run that command. +4. To install `PyTorch` go to this website, https://pytorch.org/get-started/locally/, and Select the stable build, your OS, Pip, Python and CUDA 11.6. Then select the text that is generated and run that command. + 6. Copy and paste the commands below into your terminal. This will install the Open Source packages needed to run the program. You will need to `cd` into the downloaded directory first. Follow step 2 in the Run section below if you need help. ``` diff --git a/export.py b/export.py new file mode 100644 index 0000000..531fa91 --- /dev/null +++ b/export.py @@ -0,0 +1,672 @@ +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license +""" +Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit + +Format | `export.py --include` | Model +--- | --- | --- +PyTorch | - | yolov5s.pt +TorchScript | `torchscript` | yolov5s.torchscript +ONNX | `onnx` | yolov5s.onnx +OpenVINO | `openvino` | yolov5s_openvino_model/ +TensorRT | `engine` | yolov5s.engine +CoreML | `coreml` | yolov5s.mlmodel +TensorFlow SavedModel | `saved_model` | yolov5s_saved_model/ +TensorFlow GraphDef | `pb` | yolov5s.pb +TensorFlow Lite | `tflite` | yolov5s.tflite +TensorFlow Edge TPU | `edgetpu` | yolov5s_edgetpu.tflite +TensorFlow.js | `tfjs` | yolov5s_web_model/ +PaddlePaddle | `paddle` | yolov5s_paddle_model/ + +Requirements: + $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu # CPU + $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow # GPU + +Usage: + $ python export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ... + +Inference: + $ python detect.py --weights yolov5s.pt # PyTorch + yolov5s.torchscript # TorchScript + yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn + yolov5s_openvino_model # OpenVINO + yolov5s.engine # TensorRT + yolov5s.mlmodel # CoreML (macOS-only) + yolov5s_saved_model # TensorFlow SavedModel + yolov5s.pb # TensorFlow GraphDef + yolov5s.tflite # TensorFlow Lite + yolov5s_edgetpu.tflite # TensorFlow Edge TPU + yolov5s_paddle_model # PaddlePaddle + +TensorFlow.js: + $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example + $ npm install + $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model + $ npm start +""" + +import argparse +import contextlib +import json +import os +import platform +import re +import subprocess +import sys +import time +import warnings +from pathlib import Path + +import pandas as pd +import torch +from torch.utils.mobile_optimizer import optimize_for_mobile + +FILE = Path(__file__).resolve() +ROOT = FILE.parents[0] # YOLOv5 root directory +if str(ROOT) not in sys.path: + sys.path.append(str(ROOT)) # add ROOT to PATH +if platform.system() != 'Windows': + ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative + +from models.experimental import attempt_load +from models.yolo import ClassificationModel, Detect, DetectionModel, SegmentationModel +from utils.dataloaders import LoadImages +from utils.general import (LOGGER, Profile, check_dataset, check_img_size, check_requirements, check_version, + check_yaml, colorstr, file_size, get_default_args, print_args, url2file, yaml_save) +from utils.torch_utils import select_device, smart_inference_mode + +MACOS = platform.system() == 'Darwin' # macOS environment + + +def export_formats(): + # YOLOv5 export formats + x = [ + ['PyTorch', '-', '.pt', True, True], + ['TorchScript', 'torchscript', '.torchscript', True, True], + ['ONNX', 'onnx', '.onnx', True, True], + ['OpenVINO', 'openvino', '_openvino_model', True, False], + ['TensorRT', 'engine', '.engine', False, True], + ['CoreML', 'coreml', '.mlmodel', True, False], + ['TensorFlow SavedModel', 'saved_model', '_saved_model', True, True], + ['TensorFlow GraphDef', 'pb', '.pb', True, True], + ['TensorFlow Lite', 'tflite', '.tflite', True, False], + ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False, False], + ['TensorFlow.js', 'tfjs', '_web_model', False, False], + ['PaddlePaddle', 'paddle', '_paddle_model', True, True],] + return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'CPU', 'GPU']) + + +def try_export(inner_func): + # YOLOv5 export decorator, i..e @try_export + inner_args = get_default_args(inner_func) + + def outer_func(*args, **kwargs): + prefix = inner_args['prefix'] + try: + with Profile() as dt: + f, model = inner_func(*args, **kwargs) + LOGGER.info(f'{prefix} export success ✅ {dt.t:.1f}s, saved as {f} ({file_size(f):.1f} MB)') + return f, model + except Exception as e: + LOGGER.info(f'{prefix} export failure ❌ {dt.t:.1f}s: {e}') + return None, None + + return outer_func + + +@try_export +def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')): + # YOLOv5 TorchScript model export + LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...') + f = file.with_suffix('.torchscript') + + ts = torch.jit.trace(model, im, strict=False) + d = {'shape': im.shape, 'stride': int(max(model.stride)), 'names': model.names} + extra_files = {'config.txt': json.dumps(d)} # torch._C.ExtraFilesMap() + if optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html + optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files) + else: + ts.save(str(f), _extra_files=extra_files) + return f, None + + +@try_export +def export_onnx(model, im, file, opset, dynamic, simplify, prefix=colorstr('ONNX:')): + # YOLOv5 ONNX export + check_requirements('onnx>=1.12.0') + import onnx + + LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...') + f = file.with_suffix('.onnx') + + output_names = ['output0', 'output1'] if isinstance(model, SegmentationModel) else ['output0'] + if dynamic: + dynamic = {'images': {0: 'batch', 2: 'height', 3: 'width'}} # shape(1,3,640,640) + if isinstance(model, SegmentationModel): + dynamic['output0'] = {0: 'batch', 1: 'anchors'} # shape(1,25200,85) + dynamic['output1'] = {0: 'batch', 2: 'mask_height', 3: 'mask_width'} # shape(1,32,160,160) + elif isinstance(model, DetectionModel): + dynamic['output0'] = {0: 'batch', 1: 'anchors'} # shape(1,25200,85) + + torch.onnx.export( + model.cpu() if dynamic else model, # --dynamic only compatible with cpu + im.cpu() if dynamic else im, + f, + verbose=False, + opset_version=opset, + do_constant_folding=True, # WARNING: DNN inference with torch>=1.12 may require do_constant_folding=False + input_names=['images'], + output_names=output_names, + dynamic_axes=dynamic or None) + + # Checks + model_onnx = onnx.load(f) # load onnx model + onnx.checker.check_model(model_onnx) # check onnx model + + # Metadata + d = {'stride': int(max(model.stride)), 'names': model.names} + for k, v in d.items(): + meta = model_onnx.metadata_props.add() + meta.key, meta.value = k, str(v) + onnx.save(model_onnx, f) + + # Simplify + if simplify: + try: + cuda = torch.cuda.is_available() + check_requirements(('onnxruntime-gpu' if cuda else 'onnxruntime', 'onnx-simplifier>=0.4.1')) + import onnxsim + + LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') + model_onnx, check = onnxsim.simplify(model_onnx) + assert check, 'assert check failed' + onnx.save(model_onnx, f) + except Exception as e: + LOGGER.info(f'{prefix} simplifier failure: {e}') + return f, model_onnx + + +@try_export +def export_openvino(file, metadata, half, prefix=colorstr('OpenVINO:')): + # YOLOv5 OpenVINO export + check_requirements('openvino-dev') # requires openvino-dev: https://pypi.org/project/openvino-dev/ + import openvino.inference_engine as ie + + LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...') + f = str(file).replace('.pt', f'_openvino_model{os.sep}') + + args = [ + 'mo', + '--input_model', + str(file.with_suffix('.onnx')), + '--output_dir', + f, + '--data_type', + ('FP16' if half else 'FP32'),] + subprocess.run(args, check=True, env=os.environ) # export + yaml_save(Path(f) / file.with_suffix('.yaml').name, metadata) # add metadata.yaml + return f, None + + +@try_export +def export_paddle(model, im, file, metadata, prefix=colorstr('PaddlePaddle:')): + # YOLOv5 Paddle export + check_requirements(('paddlepaddle', 'x2paddle')) + import x2paddle + from x2paddle.convert import pytorch2paddle + + LOGGER.info(f'\n{prefix} starting export with X2Paddle {x2paddle.__version__}...') + f = str(file).replace('.pt', f'_paddle_model{os.sep}') + + pytorch2paddle(module=model, save_dir=f, jit_type='trace', input_examples=[im]) # export + yaml_save(Path(f) / file.with_suffix('.yaml').name, metadata) # add metadata.yaml + return f, None + + +@try_export +def export_coreml(model, im, file, int8, half, prefix=colorstr('CoreML:')): + # YOLOv5 CoreML export + check_requirements('coremltools') + import coremltools as ct + + LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...') + f = file.with_suffix('.mlmodel') + + ts = torch.jit.trace(model, im, strict=False) # TorchScript model + ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])]) + bits, mode = (8, 'kmeans_lut') if int8 else (16, 'linear') if half else (32, None) + if bits < 32: + if MACOS: # quantization only supported on macOS + with warnings.catch_warnings(): + warnings.filterwarnings('ignore', category=DeprecationWarning) # suppress numpy==1.20 float warning + ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode) + else: + print(f'{prefix} quantization only supported on macOS, skipping...') + ct_model.save(f) + return f, ct_model + + +@try_export +def export_engine(model, im, file, half, dynamic, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')): + # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt + assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`' + try: + import tensorrt as trt + except Exception: + if platform.system() == 'Linux': + check_requirements('nvidia-tensorrt', cmds='-U --index-url https://pypi.ngc.nvidia.com') + import tensorrt as trt + + if trt.__version__[0] == '7': # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012 + grid = model.model[-1].anchor_grid + model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid] + export_onnx(model, im, file, 12, dynamic, simplify) # opset 12 + model.model[-1].anchor_grid = grid + else: # TensorRT >= 8 + check_version(trt.__version__, '8.0.0', hard=True) # require tensorrt>=8.0.0 + export_onnx(model, im, file, 12, dynamic, simplify) # opset 12 + onnx = file.with_suffix('.onnx') + + LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...') + assert onnx.exists(), f'failed to export ONNX file: {onnx}' + f = file.with_suffix('.engine') # TensorRT engine file + logger = trt.Logger(trt.Logger.INFO) + if verbose: + logger.min_severity = trt.Logger.Severity.VERBOSE + + builder = trt.Builder(logger) + config = builder.create_builder_config() + config.max_workspace_size = workspace * 1 << 30 + # config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30) # fix TRT 8.4 deprecation notice + + flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)) + network = builder.create_network(flag) + parser = trt.OnnxParser(network, logger) + if not parser.parse_from_file(str(onnx)): + raise RuntimeError(f'failed to load ONNX file: {onnx}') + + inputs = [network.get_input(i) for i in range(network.num_inputs)] + outputs = [network.get_output(i) for i in range(network.num_outputs)] + for inp in inputs: + LOGGER.info(f'{prefix} input "{inp.name}" with shape{inp.shape} {inp.dtype}') + for out in outputs: + LOGGER.info(f'{prefix} output "{out.name}" with shape{out.shape} {out.dtype}') + + if dynamic: + if im.shape[0] <= 1: + LOGGER.warning(f'{prefix} WARNING ⚠️ --dynamic model requires maximum --batch-size argument') + profile = builder.create_optimization_profile() + for inp in inputs: + profile.set_shape(inp.name, (1, *im.shape[1:]), (max(1, im.shape[0] // 2), *im.shape[1:]), im.shape) + config.add_optimization_profile(profile) + + LOGGER.info(f'{prefix} building FP{16 if builder.platform_has_fast_fp16 and half else 32} engine as {f}') + if builder.platform_has_fast_fp16 and half: + config.set_flag(trt.BuilderFlag.FP16) + with builder.build_engine(network, config) as engine, open(f, 'wb') as t: + t.write(engine.serialize()) + return f, None + + +@try_export +def export_saved_model(model, + im, + file, + dynamic, + tf_nms=False, + agnostic_nms=False, + topk_per_class=100, + topk_all=100, + iou_thres=0.45, + conf_thres=0.25, + keras=False, + prefix=colorstr('TensorFlow SavedModel:')): + # YOLOv5 TensorFlow SavedModel export + try: + import tensorflow as tf + except Exception: + check_requirements(f"tensorflow{'' if torch.cuda.is_available() else '-macos' if MACOS else '-cpu'}") + import tensorflow as tf + from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 + + from models.tf import TFModel + + LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') + f = str(file).replace('.pt', '_saved_model') + batch_size, ch, *imgsz = list(im.shape) # BCHW + + tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz) + im = tf.zeros((batch_size, *imgsz, ch)) # BHWC order for TensorFlow + _ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres) + inputs = tf.keras.Input(shape=(*imgsz, ch), batch_size=None if dynamic else batch_size) + outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres) + keras_model = tf.keras.Model(inputs=inputs, outputs=outputs) + keras_model.trainable = False + keras_model.summary() + if keras: + keras_model.save(f, save_format='tf') + else: + spec = tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype) + m = tf.function(lambda x: keras_model(x)) # full model + m = m.get_concrete_function(spec) + frozen_func = convert_variables_to_constants_v2(m) + tfm = tf.Module() + tfm.__call__ = tf.function(lambda x: frozen_func(x)[:4] if tf_nms else frozen_func(x), [spec]) + tfm.__call__(im) + tf.saved_model.save(tfm, + f, + options=tf.saved_model.SaveOptions(experimental_custom_gradients=False) if check_version( + tf.__version__, '2.6') else tf.saved_model.SaveOptions()) + return f, keras_model + + +@try_export +def export_pb(keras_model, file, prefix=colorstr('TensorFlow GraphDef:')): + # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow + import tensorflow as tf + from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 + + LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') + f = file.with_suffix('.pb') + + m = tf.function(lambda x: keras_model(x)) # full model + m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)) + frozen_func = convert_variables_to_constants_v2(m) + frozen_func.graph.as_graph_def() + tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False) + return f, None + + +@try_export +def export_tflite(keras_model, im, file, int8, data, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:')): + # YOLOv5 TensorFlow Lite export + import tensorflow as tf + + LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') + batch_size, ch, *imgsz = list(im.shape) # BCHW + f = str(file).replace('.pt', '-fp16.tflite') + + converter = tf.lite.TFLiteConverter.from_keras_model(keras_model) + converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS] + converter.target_spec.supported_types = [tf.float16] + converter.optimizations = [tf.lite.Optimize.DEFAULT] + if int8: + from models.tf import representative_dataset_gen + dataset = LoadImages(check_dataset(check_yaml(data))['train'], img_size=imgsz, auto=False) + converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib=100) + converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] + converter.target_spec.supported_types = [] + converter.inference_input_type = tf.uint8 # or tf.int8 + converter.inference_output_type = tf.uint8 # or tf.int8 + converter.experimental_new_quantizer = True + f = str(file).replace('.pt', '-int8.tflite') + if nms or agnostic_nms: + converter.target_spec.supported_ops.append(tf.lite.OpsSet.SELECT_TF_OPS) + + tflite_model = converter.convert() + open(f, 'wb').write(tflite_model) + return f, None + + +@try_export +def export_edgetpu(file, prefix=colorstr('Edge TPU:')): + # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/ + cmd = 'edgetpu_compiler --version' + help_url = 'https://coral.ai/docs/edgetpu/compiler/' + assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}' + if subprocess.run(f'{cmd} > /dev/null 2>&1', shell=True).returncode != 0: + LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}') + sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0 # sudo installed on system + for c in ( + 'curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -', + 'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list', + 'sudo apt-get update', 'sudo apt-get install edgetpu-compiler'): + subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True) + ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1] + + LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...') + f = str(file).replace('.pt', '-int8_edgetpu.tflite') # Edge TPU model + f_tfl = str(file).replace('.pt', '-int8.tflite') # TFLite model + + subprocess.run([ + 'edgetpu_compiler', + '-s', + '-d', + '-k', + '10', + '--out_dir', + str(file.parent), + f_tfl,], check=True) + return f, None + + +@try_export +def export_tfjs(file, int8, prefix=colorstr('TensorFlow.js:')): + # YOLOv5 TensorFlow.js export + check_requirements('tensorflowjs') + import tensorflowjs as tfjs + + LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...') + f = str(file).replace('.pt', '_web_model') # js dir + f_pb = file.with_suffix('.pb') # *.pb path + f_json = f'{f}/model.json' # *.json path + + args = [ + 'tensorflowjs_converter', + '--input_format=tf_frozen_model', + '--quantize_uint8' if int8 else '', + '--output_node_names=Identity,Identity_1,Identity_2,Identity_3', + str(f_pb), + str(f),] + subprocess.run([arg for arg in args if arg], check=True) + + json = Path(f_json).read_text() + with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order + subst = re.sub( + r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, ' + r'"Identity.?.?": {"name": "Identity.?.?"}, ' + r'"Identity.?.?": {"name": "Identity.?.?"}, ' + r'"Identity.?.?": {"name": "Identity.?.?"}}}', r'{"outputs": {"Identity": {"name": "Identity"}, ' + r'"Identity_1": {"name": "Identity_1"}, ' + r'"Identity_2": {"name": "Identity_2"}, ' + r'"Identity_3": {"name": "Identity_3"}}}', json) + j.write(subst) + return f, None + + +def add_tflite_metadata(file, metadata, num_outputs): + # Add metadata to *.tflite models per https://www.tensorflow.org/lite/models/convert/metadata + with contextlib.suppress(ImportError): + # check_requirements('tflite_support') + from tflite_support import flatbuffers + from tflite_support import metadata as _metadata + from tflite_support import metadata_schema_py_generated as _metadata_fb + + tmp_file = Path('/tmp/meta.txt') + with open(tmp_file, 'w') as meta_f: + meta_f.write(str(metadata)) + + model_meta = _metadata_fb.ModelMetadataT() + label_file = _metadata_fb.AssociatedFileT() + label_file.name = tmp_file.name + model_meta.associatedFiles = [label_file] + + subgraph = _metadata_fb.SubGraphMetadataT() + subgraph.inputTensorMetadata = [_metadata_fb.TensorMetadataT()] + subgraph.outputTensorMetadata = [_metadata_fb.TensorMetadataT()] * num_outputs + model_meta.subgraphMetadata = [subgraph] + + b = flatbuffers.Builder(0) + b.Finish(model_meta.Pack(b), _metadata.MetadataPopulator.METADATA_FILE_IDENTIFIER) + metadata_buf = b.Output() + + populator = _metadata.MetadataPopulator.with_model_file(file) + populator.load_metadata_buffer(metadata_buf) + populator.load_associated_files([str(tmp_file)]) + populator.populate() + tmp_file.unlink() + + +@smart_inference_mode() +def run( + data=ROOT / 'data/coco128.yaml', # 'dataset.yaml path' + weights=ROOT / 'yolov5s.pt', # weights path + imgsz=(640, 640), # image (height, width) + batch_size=1, # batch size + device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu + include=('torchscript', 'onnx'), # include formats + half=False, # FP16 half-precision export + inplace=False, # set YOLOv5 Detect() inplace=True + keras=False, # use Keras + optimize=False, # TorchScript: optimize for mobile + int8=False, # CoreML/TF INT8 quantization + dynamic=False, # ONNX/TF/TensorRT: dynamic axes + simplify=False, # ONNX: simplify model + opset=12, # ONNX: opset version + verbose=False, # TensorRT: verbose log + workspace=4, # TensorRT: workspace size (GB) + nms=False, # TF: add NMS to model + agnostic_nms=False, # TF: add agnostic NMS to model + topk_per_class=100, # TF.js NMS: topk per class to keep + topk_all=100, # TF.js NMS: topk for all classes to keep + iou_thres=0.45, # TF.js NMS: IoU threshold + conf_thres=0.25, # TF.js NMS: confidence threshold +): + t = time.time() + include = [x.lower() for x in include] # to lowercase + fmts = tuple(export_formats()['Argument'][1:]) # --include arguments + flags = [x in include for x in fmts] + assert sum(flags) == len(include), f'ERROR: Invalid --include {include}, valid --include arguments are {fmts}' + jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle = flags # export booleans + file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights) # PyTorch weights + + # Load PyTorch model + device = select_device(device) + if half: + assert device.type != 'cpu' or coreml, '--half only compatible with GPU export, i.e. use --device 0' + assert not dynamic, '--half not compatible with --dynamic, i.e. use either --half or --dynamic but not both' + model = attempt_load(weights, device=device, inplace=True, fuse=True) # load FP32 model + + # Checks + imgsz *= 2 if len(imgsz) == 1 else 1 # expand + if optimize: + assert device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu' + + # Input + gs = int(max(model.stride)) # grid size (max stride) + imgsz = [check_img_size(x, gs) for x in imgsz] # verify img_size are gs-multiples + im = torch.zeros(batch_size, 3, *imgsz).to(device) # image size(1,3,320,192) BCHW iDetection + + # Update model + model.eval() + for k, m in model.named_modules(): + if isinstance(m, Detect): + m.inplace = inplace + m.dynamic = dynamic + m.export = True + + for _ in range(2): + y = model(im) # dry runs + if half and not coreml: + im, model = im.half(), model.half() # to FP16 + shape = tuple((y[0] if isinstance(y, tuple) else y).shape) # model output shape + metadata = {'stride': int(max(model.stride)), 'names': model.names} # model metadata + LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)") + + # Exports + f = [''] * len(fmts) # exported filenames + warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning) # suppress TracerWarning + if jit: # TorchScript + f[0], _ = export_torchscript(model, im, file, optimize) + if engine: # TensorRT required before ONNX + f[1], _ = export_engine(model, im, file, half, dynamic, simplify, workspace, verbose) + if onnx or xml: # OpenVINO requires ONNX + f[2], _ = export_onnx(model, im, file, opset, dynamic, simplify) + if xml: # OpenVINO + f[3], _ = export_openvino(file, metadata, half) + if coreml: # CoreML + f[4], _ = export_coreml(model, im, file, int8, half) + if any((saved_model, pb, tflite, edgetpu, tfjs)): # TensorFlow formats + assert not tflite or not tfjs, 'TFLite and TF.js models must be exported separately, please pass only one type.' + assert not isinstance(model, ClassificationModel), 'ClassificationModel export to TF formats not yet supported.' + f[5], s_model = export_saved_model(model.cpu(), + im, + file, + dynamic, + tf_nms=nms or agnostic_nms or tfjs, + agnostic_nms=agnostic_nms or tfjs, + topk_per_class=topk_per_class, + topk_all=topk_all, + iou_thres=iou_thres, + conf_thres=conf_thres, + keras=keras) + if pb or tfjs: # pb prerequisite to tfjs + f[6], _ = export_pb(s_model, file) + if tflite or edgetpu: + f[7], _ = export_tflite(s_model, im, file, int8 or edgetpu, data=data, nms=nms, agnostic_nms=agnostic_nms) + if edgetpu: + f[8], _ = export_edgetpu(file) + add_tflite_metadata(f[8] or f[7], metadata, num_outputs=len(s_model.outputs)) + if tfjs: + f[9], _ = export_tfjs(file, int8) + if paddle: # PaddlePaddle + f[10], _ = export_paddle(model, im, file, metadata) + + # Finish + f = [str(x) for x in f if x] # filter out '' and None + if any(f): + cls, det, seg = (isinstance(model, x) for x in (ClassificationModel, DetectionModel, SegmentationModel)) # type + det &= not seg # segmentation models inherit from SegmentationModel(DetectionModel) + dir = Path('segment' if seg else 'classify' if cls else '') + h = '--half' if half else '' # --half FP16 inference arg + s = '# WARNING ⚠️ ClassificationModel not yet supported for PyTorch Hub AutoShape inference' if cls else \ + '# WARNING ⚠️ SegmentationModel not yet supported for PyTorch Hub AutoShape inference' if seg else '' + LOGGER.info(f'\nExport complete ({time.time() - t:.1f}s)' + f"\nResults saved to {colorstr('bold', file.parent.resolve())}" + f"\nDetect: python {dir / ('detect.py' if det else 'predict.py')} --weights {f[-1]} {h}" + f"\nValidate: python {dir / 'val.py'} --weights {f[-1]} {h}" + f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}') {s}" + f'\nVisualize: https://netron.app') + return f # return list of exported files/dirs + + +def parse_opt(known=False): + parser = argparse.ArgumentParser() + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') + parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)') + parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)') + parser.add_argument('--batch-size', type=int, default=1, help='batch size') + parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--half', action='store_true', help='FP16 half-precision export') + parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True') + parser.add_argument('--keras', action='store_true', help='TF: use Keras') + parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile') + parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization') + parser.add_argument('--dynamic', action='store_true', help='ONNX/TF/TensorRT: dynamic axes') + parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model') + parser.add_argument('--opset', type=int, default=17, help='ONNX: opset version') + parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log') + parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)') + parser.add_argument('--nms', action='store_true', help='TF: add NMS to model') + parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model') + parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep') + parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep') + parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold') + parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold') + parser.add_argument( + '--include', + nargs='+', + default=['torchscript'], + help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle') + opt = parser.parse_known_args()[0] if known else parser.parse_args() + print_args(vars(opt)) + return opt + + +def main(opt): + for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]): + run(**vars(opt)) + + +if __name__ == '__main__': + opt = parse_opt() + main(opt) \ No newline at end of file diff --git a/main.py b/main.py index 42d0f29..d3c4ea8 100644 --- a/main.py +++ b/main.py @@ -25,7 +25,7 @@ def main(): aaRightShift = 0 # Autoaim mouse movement amplifier - aaMovementAmp = 1.0 + aaMovementAmp = .8 # Person Class Confidence confidence = 0.5 diff --git a/main_tensorrt_gpu.py b/main_tensorrt_gpu.py index e05e38e..d6e8b71 100644 --- a/main_tensorrt_gpu.py +++ b/main_tensorrt_gpu.py @@ -94,7 +94,7 @@ def main(): sTime = time.time() # Loading Yolo5 Small AI Model - model = DetectMultiBackend('yolov5s320Half.engine', device=torch.device( + model = DetectMultiBackend('yolov5s.engine', device=torch.device( 'cuda'), dnn=False, data='', fp16=True) stride, names, pt = model.stride, model.names, model.pt diff --git a/models/common.py b/models/common.py index 10bbd8a..aa8ae67 100644 --- a/models/common.py +++ b/models/common.py @@ -21,14 +21,13 @@ import pandas as pd import requests import torch import torch.nn as nn -from IPython.display import display from PIL import Image from torch.cuda import amp from utils import TryExcept from utils.dataloaders import exif_transpose, letterbox from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr, - increment_path, is_notebook, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy, + increment_path, is_jupyter, make_divisible, non_max_suppression, scale_boxes, xywh2xyxy, xyxy2xywh, yaml_load) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import copy_attr, smart_inference_mode @@ -37,8 +36,7 @@ from utils.torch_utils import copy_attr, smart_inference_mode def autopad(k, p=None, d=1): # kernel, padding, dilation # Pad to 'same' shape outputs if d > 1: - k = d * (k - 1) + 1 if isinstance(k, - int) else [d * (x - 1) + 1 for x in k] # actual kernel-size + k = d * (k - 1) + 1 if isinstance(k, int) else [d * (x - 1) + 1 for x in k] # actual kernel-size if p is None: p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad return p @@ -50,11 +48,9 @@ class Conv(nn.Module): def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True): super().__init__() - self.conv = nn.Conv2d(c1, c2, k, s, autopad( - k, p, d), groups=g, dilation=d, bias=False) + self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False) self.bn = nn.BatchNorm2d(c2) - self.act = self.default_act if act is True else act if isinstance( - act, nn.Module) else nn.Identity() + self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() def forward(self, x): return self.act(self.bn(self.conv(x))) @@ -65,15 +61,13 @@ class Conv(nn.Module): class DWConv(Conv): # Depth-wise convolution - # ch_in, ch_out, kernel, stride, dilation, activation - def __init__(self, c1, c2, k=1, s=1, d=1, act=True): + def __init__(self, c1, c2, k=1, s=1, d=1, act=True): # ch_in, ch_out, kernel, stride, dilation, activation super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), d=d, act=act) class DWConvTranspose2d(nn.ConvTranspose2d): # Depth-wise transpose convolution - # ch_in, ch_out, kernel, stride, padding, padding_out - def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): + def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2)) @@ -102,8 +96,7 @@ class TransformerBlock(nn.Module): if c1 != c2: self.conv = Conv(c1, c2) self.linear = nn.Linear(c2, c2) # learnable position embedding - self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) - for _ in range(num_layers))) + self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers))) self.c2 = c2 def forward(self, x): @@ -116,8 +109,7 @@ class TransformerBlock(nn.Module): class Bottleneck(nn.Module): # Standard bottleneck - # ch_in, ch_out, shortcut, groups, expansion - def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): + def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) @@ -130,8 +122,7 @@ class Bottleneck(nn.Module): class BottleneckCSP(nn.Module): # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks - # ch_in, ch_out, number, shortcut, groups, expansion - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) @@ -140,8 +131,7 @@ class BottleneckCSP(nn.Module): self.cv4 = Conv(2 * c_, c2, 1, 1) self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3) self.act = nn.SiLU() - self.m = nn.Sequential( - *(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) + self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) def forward(self, x): y1 = self.cv3(self.m(self.cv1(x))) @@ -165,15 +155,13 @@ class CrossConv(nn.Module): class C3(nn.Module): # CSP Bottleneck with 3 convolutions - # ch_in, ch_out, number, shortcut, groups, expansion - def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): + def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion super().__init__() c_ = int(c2 * e) # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c1, c_, 1, 1) self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2) - self.m = nn.Sequential( - *(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) + self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n))) def forward(self, x): return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1)) @@ -184,8 +172,7 @@ class C3x(C3): def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): super().__init__(c1, c2, n, shortcut, g, e) c_ = int(c2 * e) - self.m = nn.Sequential( - *(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n))) + self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n))) class C3TR(C3): @@ -219,14 +206,12 @@ class SPP(nn.Module): c_ = c1 // 2 # hidden channels self.cv1 = Conv(c1, c_, 1, 1) self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1) - self.m = nn.ModuleList( - [nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) + self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k]) def forward(self, x): x = self.cv1(x) with warnings.catch_warnings(): - # suppress torch 1.9.0 max_pool2d() warning - warnings.simplefilter('ignore') + warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1)) @@ -242,8 +227,7 @@ class SPPF(nn.Module): def forward(self, x): x = self.cv1(x) with warnings.catch_warnings(): - # suppress torch 1.9.0 max_pool2d() warning - warnings.simplefilter('ignore') + warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning y1 = self.m(x) y2 = self.m(y1) return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1)) @@ -251,8 +235,7 @@ class SPPF(nn.Module): class Focus(nn.Module): # Focus wh information into c-space - # ch_in, ch_out, kernel, stride, padding, groups - def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): + def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups super().__init__() self.conv = Conv(c1 * 4, c2, k, s, p, g, act=act) # self.contract = Contract(gain=2) @@ -264,8 +247,7 @@ class Focus(nn.Module): class GhostConv(nn.Module): # Ghost Convolution https://github.com/huawei-noah/ghostnet - # ch_in, ch_out, kernel, stride, groups - def __init__(self, c1, c2, k=1, s=1, g=1, act=True): + def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups super().__init__() c_ = c2 // 2 # hidden channels self.cv1 = Conv(c1, c_, k, s, None, g, act=act) @@ -346,34 +328,28 @@ class DetectMultiBackend(nn.Module): # TensorFlow Lite: *.tflite # TensorFlow Edge TPU: *_edgetpu.tflite # PaddlePaddle: *_paddle_model - # scoped to avoid circular import - from models.experimental import attempt_download, attempt_load + from models.experimental import attempt_download, attempt_load # scoped to avoid circular import super().__init__() w = str(weights[0] if isinstance(weights, list) else weights) - pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type( - w) + pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, triton = self._model_type(w) fp16 &= pt or jit or onnx or engine # FP16 - # BHWC formats (vs torch BCWH) - nhwc = coreml or saved_model or pb or tflite or edgetpu + nhwc = coreml or saved_model or pb or tflite or edgetpu # BHWC formats (vs torch BCWH) stride = 32 # default stride cuda = torch.cuda.is_available() and device.type != 'cpu' # use CUDA if not (pt or triton): w = attempt_download(w) # download if not local if pt: # PyTorch - model = attempt_load(weights if isinstance( - weights, list) else w, device=device, inplace=True, fuse=fuse) + model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse) stride = max(int(model.stride.max()), 32) # model stride - names = model.module.names if hasattr( - model, 'module') else model.names # get class names + names = model.module.names if hasattr(model, 'module') else model.names # get class names model.half() if fp16 else model.float() self.model = model # explicitly assign for to(), cpu(), cuda(), half() elif jit: # TorchScript LOGGER.info(f'Loading {w} for TorchScript inference...') extra_files = {'config.txt': ''} # model metadata - model = torch.jit.load( - w, _extra_files=extra_files, map_location=device) + model = torch.jit.load(w, _extra_files=extra_files, map_location=device) model.half() if fp16 else model.float() if extra_files['config.txt']: # load metadata dict d = json.loads(extra_files['config.txt'], @@ -386,11 +362,9 @@ class DetectMultiBackend(nn.Module): net = cv2.dnn.readNetFromONNX(w) elif onnx: # ONNX Runtime LOGGER.info(f'Loading {w} for ONNX Runtime inference...') - check_requirements( - ('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime')) + check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime')) import onnxruntime - providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else [ - 'CPUExecutionProvider'] + providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider'] session = onnxruntime.InferenceSession(w, providers=providers) output_names = [x.name for x in session.get_outputs()] meta = session.get_modelmeta().custom_metadata_map # metadata @@ -398,33 +372,26 @@ class DetectMultiBackend(nn.Module): stride, names = int(meta['stride']), eval(meta['names']) elif xml: # OpenVINO LOGGER.info(f'Loading {w} for OpenVINO inference...') - # requires openvino-dev: https://pypi.org/project/openvino-dev/ - check_requirements('openvino') + check_requirements('openvino') # requires openvino-dev: https://pypi.org/project/openvino-dev/ from openvino.runtime import Core, Layout, get_batch ie = Core() if not Path(w).is_file(): # if not *.xml - # get *.xml file from *_openvino_model dir - w = next(Path(w).glob('*.xml')) - network = ie.read_model( - model=w, weights=Path(w).with_suffix('.bin')) + w = next(Path(w).glob('*.xml')) # get *.xml file from *_openvino_model dir + network = ie.read_model(model=w, weights=Path(w).with_suffix('.bin')) if network.get_parameters()[0].get_layout().empty: - network.get_parameters()[0].set_layout(Layout("NCHW")) + network.get_parameters()[0].set_layout(Layout('NCHW')) batch_dim = get_batch(network) if batch_dim.is_static: batch_size = batch_dim.get_length() - # device_name="MYRIAD" for Intel NCS2 - executable_network = ie.compile_model(network, device_name="CPU") - stride, names = self._load_metadata( - Path(w).with_suffix('.yaml')) # load metadata + executable_network = ie.compile_model(network, device_name='CPU') # device_name="MYRIAD" for Intel NCS2 + stride, names = self._load_metadata(Path(w).with_suffix('.yaml')) # load metadata elif engine: # TensorRT LOGGER.info(f'Loading {w} for TensorRT inference...') import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download - # require tensorrt>=7.0.0 - check_version(trt.__version__, '7.0.0', hard=True) + check_version(trt.__version__, '7.0.0', hard=True) # require tensorrt>=7.0.0 if device.type == 'cpu': device = torch.device('cuda:0') - Binding = namedtuple( - 'Binding', ('name', 'dtype', 'shape', 'data', 'ptr')) + Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr')) logger = trt.Logger(trt.Logger.INFO) with open(w, 'rb') as f, trt.Runtime(logger) as runtime: model = runtime.deserialize_cuda_engine(f.read()) @@ -439,20 +406,16 @@ class DetectMultiBackend(nn.Module): if model.binding_is_input(i): if -1 in tuple(model.get_binding_shape(i)): # dynamic dynamic = True - context.set_binding_shape( - i, tuple(model.get_profile_shape(0, i)[2])) + context.set_binding_shape(i, tuple(model.get_profile_shape(0, i)[2])) if dtype == np.float16: fp16 = True else: # output output_names.append(name) shape = tuple(context.get_binding_shape(i)) im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device) - bindings[name] = Binding( - name, dtype, shape, im, int(im.data_ptr())) - binding_addrs = OrderedDict((n, d.ptr) - for n, d in bindings.items()) - # if dynamic, this is instead max batch size - batch_size = bindings['images'].shape[0] + bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr())) + binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items()) + batch_size = bindings['images'].shape[0] # if dynamic, this is instead max batch size elif coreml: # CoreML LOGGER.info(f'Loading {w} for CoreML inference...') import coremltools as ct @@ -461,15 +424,13 @@ class DetectMultiBackend(nn.Module): LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...') import tensorflow as tf keras = False # assume TF1 saved_model - model = tf.keras.models.load_model( - w) if keras else tf.saved_model.load(w) + model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w) elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...') import tensorflow as tf def wrap_frozen_graph(gd, inputs, outputs): - x = tf.compat.v1.wrap_function( - lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped + x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=''), []) # wrapped ge = x.graph.as_graph_element return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs)) @@ -483,8 +444,7 @@ class DetectMultiBackend(nn.Module): gd = tf.Graph().as_graph_def() # TF GraphDef with open(w, 'rb') as f: gd.ParseFromString(f.read()) - frozen_func = wrap_frozen_graph( - gd, inputs="x:0", outputs=gd_outputs(gd)) + frozen_func = wrap_frozen_graph(gd, inputs='x:0', outputs=gd_outputs(gd)) elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu from tflite_runtime.interpreter import Interpreter, load_delegate @@ -492,14 +452,12 @@ class DetectMultiBackend(nn.Module): import tensorflow as tf Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate, if edgetpu: # TF Edge TPU https://coral.ai/software/#edgetpu-runtime - LOGGER.info( - f'Loading {w} for TensorFlow Lite Edge TPU inference...') + LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...') delegate = { 'Linux': 'libedgetpu.so.1', 'Darwin': 'libedgetpu.1.dylib', 'Windows': 'edgetpu.dll'}[platform.system()] - interpreter = Interpreter(model_path=w, experimental_delegates=[ - load_delegate(delegate)]) + interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)]) else: # TFLite LOGGER.info(f'Loading {w} for TensorFlow Lite inference...') interpreter = Interpreter(model_path=w) # load TFLite model @@ -508,46 +466,39 @@ class DetectMultiBackend(nn.Module): output_details = interpreter.get_output_details() # outputs # load metadata with contextlib.suppress(zipfile.BadZipFile): - with zipfile.ZipFile(w, "r") as model: + with zipfile.ZipFile(w, 'r') as model: meta_file = model.namelist()[0] - meta = ast.literal_eval( - model.read(meta_file).decode("utf-8")) + meta = ast.literal_eval(model.read(meta_file).decode('utf-8')) stride, names = int(meta['stride']), meta['names'] elif tfjs: # TF.js - raise NotImplementedError( - 'ERROR: YOLOv5 TF.js inference is not supported') + raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported') elif paddle: # PaddlePaddle LOGGER.info(f'Loading {w} for PaddlePaddle inference...') check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle') import paddle.inference as pdi if not Path(w).is_file(): # if not *.pdmodel - # get *.pdmodel file from *_paddle_model dir - w = next(Path(w).rglob('*.pdmodel')) + w = next(Path(w).rglob('*.pdmodel')) # get *.pdmodel file from *_paddle_model dir weights = Path(w).with_suffix('.pdiparams') config = pdi.Config(str(w), str(weights)) if cuda: - config.enable_use_gpu( - memory_pool_init_size_mb=2048, device_id=0) + config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0) predictor = pdi.create_predictor(config) - input_handle = predictor.get_input_handle( - predictor.get_input_names()[0]) + input_handle = predictor.get_input_handle(predictor.get_input_names()[0]) output_names = predictor.get_output_names() elif triton: # NVIDIA Triton Inference Server LOGGER.info(f'Using {w} as Triton Inference Server...') check_requirements('tritonclient[all]') from utils.triton import TritonRemoteModel model = TritonRemoteModel(url=w) - nhwc = model.runtime.startswith("tensorflow") + nhwc = model.runtime.startswith('tensorflow') else: raise NotImplementedError(f'ERROR: {w} is not a supported format') # class names if 'names' not in locals(): - names = yaml_load(data)['names'] if data else { - i: f'class{i}' for i in range(999)} + names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)} if names[0] == 'n01440764' and len(names) == 1000: # ImageNet - # human-readable names - names = yaml_load(ROOT / 'data/ImageNet.yaml')['names'] + names = yaml_load(ROOT / 'data/ImageNet.yaml')['names'] # human-readable names self.__dict__.update(locals()) # assign all variables to self @@ -557,12 +508,10 @@ class DetectMultiBackend(nn.Module): if self.fp16 and im.dtype != torch.float16: im = im.half() # to FP16 if self.nhwc: - # torch BCHW to numpy BHWC shape(1,320,192,3) - im = im.permute(0, 2, 3, 1) + im = im.permute(0, 2, 3, 1) # torch BCHW to numpy BHWC shape(1,320,192,3) if self.pt: # PyTorch - y = self.model( - im, augment=augment, visualize=visualize) if augment or visualize else self.model(im) + y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im) elif self.jit: # TorchScript y = self.model(im) elif self.dnn: # ONNX OpenCV DNN @@ -571,22 +520,18 @@ class DetectMultiBackend(nn.Module): y = self.net.forward() elif self.onnx: # ONNX Runtime im = im.cpu().numpy() # torch to numpy - y = self.session.run(self.output_names, { - self.session.get_inputs()[0].name: im}) + y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im}) elif self.xml: # OpenVINO im = im.cpu().numpy() # FP32 y = list(self.executable_network([im]).values()) elif self.engine: # TensorRT if self.dynamic and im.shape != self.bindings['images'].shape: i = self.model.get_binding_index('images') - self.context.set_binding_shape( - i, im.shape) # reshape if dynamic - self.bindings['images'] = self.bindings['images']._replace( - shape=im.shape) + self.context.set_binding_shape(i, im.shape) # reshape if dynamic + self.bindings['images'] = self.bindings['images']._replace(shape=im.shape) for name in self.output_names: i = self.model.get_binding_index(name) - self.bindings[name].data.resize_( - tuple(self.context.get_binding_shape(i))) + self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i))) s = self.bindings['images'].shape assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}" self.binding_addrs['images'] = int(im.data_ptr()) @@ -596,37 +541,29 @@ class DetectMultiBackend(nn.Module): im = im.cpu().numpy() im = Image.fromarray((im[0] * 255).astype('uint8')) # im = im.resize((192, 320), Image.ANTIALIAS) - # coordinates are xywh normalized - y = self.model.predict({'image': im}) + y = self.model.predict({'image': im}) # coordinates are xywh normalized if 'confidence' in y: - box = xywh2xyxy(y['coordinates'] * - [[w, h, w, h]]) # xyxy pixels - conf, cls = y['confidence'].max( - 1), y['confidence'].argmax(1).astype(np.float) - y = np.concatenate( - (box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) + box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels + conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float) + y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1) else: - # reversed for segmentation models (pred, proto) - y = list(reversed(y.values())) + y = list(reversed(y.values())) # reversed for segmentation models (pred, proto) elif self.paddle: # PaddlePaddle im = im.cpu().numpy().astype(np.float32) self.input_handle.copy_from_cpu(im) self.predictor.run() - y = [self.predictor.get_output_handle( - x).copy_to_cpu() for x in self.output_names] + y = [self.predictor.get_output_handle(x).copy_to_cpu() for x in self.output_names] elif self.triton: # NVIDIA Triton Inference Server y = self.model(im) else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU) im = im.cpu().numpy() if self.saved_model: # SavedModel - y = self.model( - im, training=False) if self.keras else self.model(im) + y = self.model(im, training=False) if self.keras else self.model(im) elif self.pb: # GraphDef y = self.frozen_func(x=self.tf.constant(im)) else: # Lite or Edge TPU input = self.input_details[0] - # is TFLite quantized uint8 model - int8 = input['dtype'] == np.uint8 + int8 = input['dtype'] == np.uint8 # is TFLite quantized uint8 model if int8: scale, zero_point = input['quantization'] im = (im / scale + zero_point).astype(np.uint8) # de-scale @@ -637,8 +574,7 @@ class DetectMultiBackend(nn.Module): x = self.interpreter.get_tensor(output['index']) if int8: scale, zero_point = output['quantization'] - x = (x.astype(np.float32) - zero_point) * \ - scale # re-scale + x = (x.astype(np.float32) - zero_point) * scale # re-scale y.append(x) y = [x if isinstance(x, np.ndarray) else x.numpy() for x in y] y[0][..., :4] *= [w, h, w, h] # xywh normalized to pixels @@ -655,8 +591,7 @@ class DetectMultiBackend(nn.Module): # Warmup model by running inference once warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton if any(warmup_types) and (self.device.type != 'cpu' or self.triton): - im = torch.empty( - *imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device) # input + im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device) # input for _ in range(2 if self.jit else 1): # self.forward(im) # warmup @@ -664,16 +599,15 @@ class DetectMultiBackend(nn.Module): def _model_type(p='path/to/model.pt'): # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle] + from export import export_formats from utils.downloads import is_url - sf = ['.pt', '.torchscript', '.onnx', '_openvino_model', '.engine', '.mlmodel', '_saved_model', - '.pb', '.tflite', '_edgetpu.tflite', '_web_model', '_paddle_model'] # export suffixes + sf = list(export_formats().Suffix) # export suffixes if not is_url(p, check=False): check_suffix(p, sf) # checks url = urlparse(p) # if url may be Triton inference server types = [s in Path(p).name for s in sf] types[8] &= not types[9] # tflite &= not edgetpu - triton = not any(types) and all( - [any(s in url.scheme for s in ["http", "grpc"]), url.netloc]) + triton = not any(types) and all([any(s in url.scheme for s in ['http', 'grpc']), url.netloc]) return types + [triton] @staticmethod @@ -691,8 +625,7 @@ class AutoShape(nn.Module): iou = 0.45 # NMS IoU threshold agnostic = False # NMS class-agnostic multi_label = False # NMS multiple labels per box - # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs - classes = None + classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs max_det = 1000 # maximum number of detections per image amp = False # Automatic Mixed Precision (AMP) inference @@ -700,15 +633,12 @@ class AutoShape(nn.Module): super().__init__() if verbose: LOGGER.info('Adding AutoShape... ') - copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', - 'stride', 'abc'), exclude=()) # copy attributes - # DetectMultiBackend() instance - self.dmb = isinstance(model, DetectMultiBackend) + copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=()) # copy attributes + self.dmb = isinstance(model, DetectMultiBackend) # DetectMultiBackend() instance self.pt = not self.dmb or model.pt # PyTorch model self.model = model.eval() if self.pt: - # Detect() - m = self.model.model.model[-1] if self.dmb else self.model.model[-1] + m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect() m.inplace = False # Detect.inplace=False for safe multithread inference m.export = True # do not output loss values @@ -716,8 +646,7 @@ class AutoShape(nn.Module): # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers self = super()._apply(fn) if self.pt: - # Detect() - m = self.model.model.model[-1] if self.dmb else self.model.model[-1] + m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect() m.stride = fn(m.stride) m.grid = list(map(fn, m.grid)) if isinstance(m.anchor_grid, list): @@ -739,47 +668,35 @@ class AutoShape(nn.Module): with dt[0]: if isinstance(size, int): # expand size = (size, size) - p = next(self.model.parameters()) if self.pt else torch.empty( - 1, device=self.model.device) # param - # Automatic Mixed Precision (AMP) inference - autocast = self.amp and (p.device.type != 'cpu') + p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device) # param + autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference if isinstance(ims, torch.Tensor): # torch with amp.autocast(autocast): - # inference - return self.model(ims.to(p.device).type_as(p), augment=augment) + return self.model(ims.to(p.device).type_as(p), augment=augment) # inference # Pre-process - n, ims = (len(ims), list(ims)) if isinstance( - ims, (list, tuple)) else (1, [ims]) # number, list of images + n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims]) # number, list of images shape0, shape1, files = [], [], [] # image and inference shapes, filenames for i, im in enumerate(ims): f = f'image{i}' # filename if isinstance(im, (str, Path)): # filename or uri - im, f = Image.open(requests.get(im, stream=True).raw if str( - im).startswith('http') else im), im + im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im im = np.asarray(exif_transpose(im)) elif isinstance(im, Image.Image): # PIL Image - im, f = np.asarray(exif_transpose(im)), getattr( - im, 'filename', f) or f + im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f files.append(Path(f).with_suffix('.jpg').name) if im.shape[0] < 5: # image in CHW - # reverse dataloader .transpose(2, 0, 1) - im = im.transpose((1, 2, 0)) - im = im[..., :3] if im.ndim == 3 else cv2.cvtColor( - im, cv2.COLOR_GRAY2BGR) # enforce 3ch input + im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1) + im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR) # enforce 3ch input s = im.shape[:2] # HWC shape0.append(s) # image shape g = max(size) / max(s) # gain shape1.append([int(y * g) for y in s]) - ims[i] = im if im.data.contiguous else np.ascontiguousarray( - im) # update - shape1 = [make_divisible(x, self.stride) - for x in np.array(shape1).max(0)] # inf shape + ims[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update + shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)] # inf shape x = [letterbox(im, shape1, auto=False)[0] for im in ims] # pad - x = np.ascontiguousarray(np.array(x).transpose( - (0, 3, 1, 2))) # stack and BHWC to BCHW - x = torch.from_numpy(x).to(p.device).type_as( - p) / 255 # uint8 to fp16/32 + x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2))) # stack and BHWC to BCHW + x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32 with amp.autocast(autocast): # Inference @@ -806,8 +723,7 @@ class Detections: def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None): super().__init__() d = pred[0].device # device - gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) - for im in ims] # normalizations + gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims] # normalizations self.ims = ims # list of images as numpy arrays self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls) self.names = names # class names @@ -824,23 +740,18 @@ class Detections: def _run(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')): s, crops = '', [] for i, (im, pred) in enumerate(zip(self.ims, self.pred)): - # string - s += f'\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' + s += f'\nimage {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string if pred.shape[0]: for c in pred[:, -1].unique(): n = (pred[:, -1] == c).sum() # detections per class - # add to string - s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " + s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string s = s.rstrip(', ') if show or save or render or crop: annotator = Annotator(im, example=str(self.names)) - # xyxy, confidence, class - for *box, conf, cls in reversed(pred): + for *box, conf, cls in reversed(pred): # xyxy, confidence, class label = f'{self.names[int(cls)]} {conf:.2f}' if crop: - file = save_dir / 'crops' / \ - self.names[int(cls)] / \ - self.files[i] if save else None + file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None crops.append({ 'box': box, 'conf': conf, @@ -848,22 +759,23 @@ class Detections: 'label': label, 'im': save_one_box(box, im, file=file, save=save)}) else: # all others - annotator.box_label( - box, label if labels else '', color=colors(cls)) + annotator.box_label(box, label if labels else '', color=colors(cls)) im = annotator.im else: s += '(no detections)' - im = Image.fromarray(im.astype(np.uint8)) if isinstance( - im, np.ndarray) else im # from np + im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np if show: - display(im) if is_notebook() else im.show(self.files[i]) + if is_jupyter(): + from IPython.display import display + display(im) + else: + im.show(self.files[i]) if save: f = self.files[i] im.save(save_dir / f) # save if i == self.n - 1: - LOGGER.info( - f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}") + LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}") if render: self.ims[i] = np.asarray(im) if pprint: @@ -879,15 +791,12 @@ class Detections: self._run(show=True, labels=labels) # show results def save(self, labels=True, save_dir='runs/detect/exp', exist_ok=False): - save_dir = increment_path( - save_dir, exist_ok, mkdir=True) # increment save_dir + save_dir = increment_path(save_dir, exist_ok, mkdir=True) # increment save_dir self._run(save=True, labels=labels, save_dir=save_dir) # save results def crop(self, save=True, save_dir='runs/detect/exp', exist_ok=False): - save_dir = increment_path( - save_dir, exist_ok, mkdir=True) if save else None - # crop results - return self._run(crop=True, save=save, save_dir=save_dir) + save_dir = increment_path(save_dir, exist_ok, mkdir=True) if save else None + return self._run(crop=True, save=save, save_dir=save_dir) # crop results def render(self, labels=True): self._run(render=True, labels=labels) # render results @@ -899,16 +808,14 @@ class Detections: ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]): - a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] - for x in x.tolist()] for x in getattr(self, k)] # update + a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update setattr(new, k, [pd.DataFrame(x, columns=c) for x in a]) return new def tolist(self): # return a list of Detections objects, i.e. 'for result in results.tolist():' r = range(self.n) # iterable - x = [Detections([self.ims[i]], [self.pred[i]], [ - self.files[i]], self.times, self.names, self.s) for i in r] + x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r] # for d in x: # for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']: # setattr(d, k, getattr(d, k)[0]) # pop out of list @@ -942,13 +849,19 @@ class Proto(nn.Module): class Classify(nn.Module): # YOLOv5 classification head, i.e. x(b,c1,20,20) to x(b,c2) - # ch_in, ch_out, kernel, stride, padding, groups - def __init__(self, c1, c2, k=1, s=1, p=None, g=1): + def __init__(self, + c1, + c2, + k=1, + s=1, + p=None, + g=1, + dropout_p=0.0): # ch_in, ch_out, kernel, stride, padding, groups, dropout probability super().__init__() c_ = 1280 # efficientnet_b0 size self.conv = Conv(c1, c_, k, s, autopad(k, p), g) self.pool = nn.AdaptiveAvgPool2d(1) # to x(b,c_,1,1) - self.drop = nn.Dropout(p=0.0, inplace=True) + self.drop = nn.Dropout(p=dropout_p, inplace=True) self.linear = nn.Linear(c_, c2) # to x(b,c2) def forward(self, x): diff --git a/models/segment/yolov5m-seg.yaml b/models/segment/yolov5m-seg.yaml index f73d199..07ec25b 100644 --- a/models/segment/yolov5m-seg.yaml +++ b/models/segment/yolov5m-seg.yaml @@ -45,4 +45,4 @@ head: [-1, 3, C3, [1024, False]], # 23 (P5/32-large) [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5) - ] \ No newline at end of file + ] diff --git a/models/segment/yolov5s-seg.yaml b/models/segment/yolov5s-seg.yaml index 7cbdb36..a827814 100644 --- a/models/segment/yolov5s-seg.yaml +++ b/models/segment/yolov5s-seg.yaml @@ -45,4 +45,4 @@ head: [-1, 3, C3, [1024, False]], # 23 (P5/32-large) [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5) - ] \ No newline at end of file + ] diff --git a/models/tf.py b/models/tf.py index 3f3dc8d..8290cf2 100644 --- a/models/tf.py +++ b/models/tf.py @@ -356,7 +356,7 @@ class TFUpsample(keras.layers.Layer): # TF version of torch.nn.Upsample() def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w' super().__init__() - assert scale_factor % 2 == 0, "scale_factor must be multiple of 2" + assert scale_factor % 2 == 0, 'scale_factor must be multiple of 2' self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * scale_factor, x.shape[2] * scale_factor), mode) # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode) # with default arguments: align_corners=False, half_pixel_centers=False @@ -371,7 +371,7 @@ class TFConcat(keras.layers.Layer): # TF version of torch.concat() def __init__(self, dimension=1, w=None): super().__init__() - assert dimension == 1, "convert only NCHW to NHWC concat" + assert dimension == 1, 'convert only NCHW to NHWC concat' self.d = 3 def call(self, inputs): @@ -523,17 +523,17 @@ class AgnosticNMS(keras.layers.Layer): selected_boxes = tf.gather(boxes, selected_inds) padded_boxes = tf.pad(selected_boxes, paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]], - mode="CONSTANT", + mode='CONSTANT', constant_values=0.0) selected_scores = tf.gather(scores_inp, selected_inds) padded_scores = tf.pad(selected_scores, paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]], - mode="CONSTANT", + mode='CONSTANT', constant_values=-1.0) selected_classes = tf.gather(class_inds, selected_inds) padded_classes = tf.pad(selected_classes, paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]], - mode="CONSTANT", + mode='CONSTANT', constant_values=-1.0) valid_detections = tf.shape(selected_inds)[0] return padded_boxes, padded_scores, padded_classes, valid_detections @@ -603,6 +603,6 @@ def main(opt): run(**vars(opt)) -if __name__ == "__main__": +if __name__ == '__main__': opt = parse_opt() main(opt) diff --git a/requirements.txt b/requirements.txt index 4be4bff..030bc7d 100644 --- a/requirements.txt +++ b/requirements.txt @@ -3,7 +3,7 @@ PyDirectInput Pillow opencv-python mss -numpy +numpy==1.23 pandas pywin32 pyyaml diff --git a/utils/__init__.py b/utils/__init__.py index 3b1a2c8..33db6b0 100644 --- a/utils/__init__.py +++ b/utils/__init__.py @@ -60,17 +60,19 @@ def notebook_init(verbose=True): check_font() import psutil - from IPython import display # to display images and clear console output if is_colab(): shutil.rmtree('/content/sample_data', ignore_errors=True) # remove colab /sample_data directory # System info + display = None if verbose: gb = 1 << 30 # bytes to GiB (1024 ** 3) ram = psutil.virtual_memory().total - total, used, free = shutil.disk_usage("/") - display.clear_output() + total, used, free = shutil.disk_usage('/') + with contextlib.suppress(Exception): # clear display if ipython is installed + from IPython import display + display.clear_output() s = f'({os.cpu_count()} CPUs, {ram / gb:.1f} GB RAM, {(total - free) / gb:.1f}/{total / gb:.1f} GB disk)' else: s = '' diff --git a/utils/augmentations.py b/utils/augmentations.py index 1eae5db..7ab75f1 100644 --- a/utils/augmentations.py +++ b/utils/augmentations.py @@ -201,7 +201,7 @@ def random_perspective(im, # Transform label coordinates n = len(targets) if n: - use_segments = any(x.any() for x in segments) + use_segments = any(x.any() for x in segments) and len(segments) == n new = np.zeros((n, 4)) if use_segments: # warp segments segments = resample_segments(segments) # upsample diff --git a/utils/dataloaders.py b/utils/dataloaders.py index cbb3114..7687a2b 100644 --- a/utils/dataloaders.py +++ b/utils/dataloaders.py @@ -52,7 +52,7 @@ for orientation in ExifTags.TAGS.keys(): def get_hash(paths): # Returns a single hash value of a list of paths (files or dirs) size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes - h = hashlib.md5(str(size).encode()) # hash sizes + h = hashlib.sha256(str(size).encode()) # hash sizes h.update(''.join(paths).encode()) # hash paths return h.hexdigest() # return hash @@ -89,7 +89,7 @@ def exif_transpose(image): if method is not None: image = image.transpose(method) del exif[0x0112] - image.info["exif"] = exif.tobytes() + image.info['exif'] = exif.tobytes() return image @@ -212,11 +212,11 @@ class LoadScreenshots: # Parse monitor shape monitor = self.sct.monitors[self.screen] - self.top = monitor["top"] if top is None else (monitor["top"] + top) - self.left = monitor["left"] if left is None else (monitor["left"] + left) - self.width = width or monitor["width"] - self.height = height or monitor["height"] - self.monitor = {"left": self.left, "top": self.top, "width": self.width, "height": self.height} + self.top = monitor['top'] if top is None else (monitor['top'] + top) + self.left = monitor['left'] if left is None else (monitor['left'] + left) + self.width = width or monitor['width'] + self.height = height or monitor['height'] + self.monitor = {'left': self.left, 'top': self.top, 'width': self.width, 'height': self.height} def __iter__(self): return self @@ -224,7 +224,7 @@ class LoadScreenshots: def __next__(self): # mss screen capture: get raw pixels from the screen as np array im0 = np.array(self.sct.grab(self.monitor))[:, :, :3] # [:, :, :3] BGRA to BGR - s = f"screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: " + s = f'screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: ' if self.transforms: im = self.transforms(im0) # transforms @@ -239,7 +239,7 @@ class LoadScreenshots: class LoadImages: # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4` def __init__(self, path, img_size=640, stride=32, auto=True, transforms=None, vid_stride=1): - if isinstance(path, str) and Path(path).suffix == ".txt": # *.txt file with img/vid/dir on each line + if isinstance(path, str) and Path(path).suffix == '.txt': # *.txt file with img/vid/dir on each line path = Path(path).read_text().rsplit() files = [] for p in sorted(path) if isinstance(path, (list, tuple)) else [path]: @@ -358,7 +358,7 @@ class LoadStreams: # YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/Zgi9g1ksQHc' check_requirements(('pafy', 'youtube_dl==2020.12.2')) import pafy - s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL + s = pafy.new(s).getbest(preftype='mp4').url # YouTube URL s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam if s == 0: assert not is_colab(), '--source 0 webcam unsupported on Colab. Rerun command in a local environment.' @@ -373,7 +373,7 @@ class LoadStreams: _, self.imgs[i] = cap.read() # guarantee first frame self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True) - LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)") + LOGGER.info(f'{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)') self.threads[i].start() LOGGER.info('') # newline @@ -495,7 +495,7 @@ class LoadImagesAndLabels(Dataset): # Display cache nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total if exists and LOCAL_RANK in {-1, 0}: - d = f"Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt" + d = f'Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt' tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT) # display cache results if cache['msgs']: LOGGER.info('\n'.join(cache['msgs'])) # display warnings @@ -598,8 +598,8 @@ class LoadImagesAndLabels(Dataset): mem = psutil.virtual_memory() cache = mem_required * (1 + safety_margin) < mem.available # to cache or not to cache, that is the question if not cache: - LOGGER.info(f"{prefix}{mem_required / gb:.1f}GB RAM required, " - f"{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, " + LOGGER.info(f'{prefix}{mem_required / gb:.1f}GB RAM required, ' + f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, ' f"{'caching images ✅' if cache else 'not caching images ⚠️'}") return cache @@ -607,7 +607,7 @@ class LoadImagesAndLabels(Dataset): # Cache dataset labels, check images and read shapes x = {} # dict nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages - desc = f"{prefix}Scanning {path.parent / path.stem}..." + desc = f'{prefix}Scanning {path.parent / path.stem}...' with Pool(NUM_THREADS) as pool: pbar = tqdm(pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix))), desc=desc, @@ -622,7 +622,7 @@ class LoadImagesAndLabels(Dataset): x[im_file] = [lb, shape, segments] if msg: msgs.append(msg) - pbar.desc = f"{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt" + pbar.desc = f'{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt' pbar.close() if msgs: @@ -1063,7 +1063,7 @@ class HUBDatasetStats(): if zipped: data['path'] = data_dir except Exception as e: - raise Exception("error/HUB/dataset_stats/yaml_load") from e + raise Exception('error/HUB/dataset_stats/yaml_load') from e check_dataset(data, autodownload) # download dataset if missing self.hub_dir = Path(data['path'] + '-hub') @@ -1188,7 +1188,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder): else: # read image im = cv2.imread(f) # BGR if self.album_transforms: - sample = self.album_transforms(image=cv2.cvtColor(im, cv2.COLOR_BGR2RGB))["image"] + sample = self.album_transforms(image=cv2.cvtColor(im, cv2.COLOR_BGR2RGB))['image'] else: sample = self.torch_transforms(im) return sample, j diff --git a/utils/docker/Dockerfile b/utils/docker/Dockerfile index 98e9c29..b5d2af9 100644 --- a/utils/docker/Dockerfile +++ b/utils/docker/Dockerfile @@ -3,35 +3,44 @@ # Image is CUDA-optimized for YOLOv5 single/multi-GPU training and inference # Start FROM NVIDIA PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch -FROM nvcr.io/nvidia/pytorch:22.12-py3 -RUN rm -rf /opt/pytorch # remove 1.2GB dir +# FROM docker.io/pytorch/pytorch:latest +FROM pytorch/pytorch:latest # Downloads to user config dir ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/ # Install linux packages -RUN apt update && apt install --no-install-recommends -y zip htop screen libgl1-mesa-glx +ENV DEBIAN_FRONTEND noninteractive +RUN apt update +RUN TZ=Etc/UTC apt install -y tzdata +RUN apt install --no-install-recommends -y gcc git zip curl htop libgl1-mesa-glx libglib2.0-0 libpython3-dev gnupg +# RUN alias python=python3 -# Install pip packages (uninstall torch nightly in favor of stable) -COPY requirements.txt . -RUN python -m pip install --upgrade pip wheel -RUN pip uninstall -y Pillow torchtext torch torchvision -RUN pip install --no-cache -U pycocotools # install --upgrade -RUN pip install --no-cache -r requirements.txt albumentations comet gsutil notebook 'opencv-python<4.6.0.66' \ - Pillow>=9.1.0 ultralytics \ - --extra-index-url https://download.pytorch.org/whl/cu113 +# Security updates +# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796 +RUN apt upgrade --no-install-recommends -y openssl # Create working directory -RUN mkdir -p /usr/src/app +RUN rm -rf /usr/src/app && mkdir -p /usr/src/app WORKDIR /usr/src/app # Copy contents # COPY . /usr/src/app (issues as not a .git directory) RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app +# Install pip packages +COPY requirements.txt . +RUN python3 -m pip install --upgrade pip wheel +RUN pip install --no-cache -r requirements.txt albumentations comet gsutil notebook \ + coremltools onnx onnx-simplifier onnxruntime 'openvino-dev>=2022.3' + # tensorflow tensorflowjs \ + # Set environment variables ENV OMP_NUM_THREADS=1 +# Cleanup +ENV DEBIAN_FRONTEND teletype + # Usage Examples ------------------------------------------------------------------------------------------------------- @@ -54,7 +63,7 @@ ENV OMP_NUM_THREADS=1 # t=ultralytics/yolov5:latest tnew=ultralytics/yolov5:v6.2 && sudo docker pull $t && sudo docker tag $t $tnew && sudo docker push $tnew # Clean up -# docker system prune -a --volumes +# sudo docker system prune -a --volumes # Update Ubuntu drivers # https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/ diff --git a/utils/docker/Dockerfile-arm64 b/utils/docker/Dockerfile-arm64 index eed1410..7023c6a 100644 --- a/utils/docker/Dockerfile-arm64 +++ b/utils/docker/Dockerfile-arm64 @@ -3,7 +3,7 @@ # Image is aarch64-compatible for Apple M1 and other ARM architectures i.e. Jetson Nano and Raspberry Pi # Start FROM Ubuntu image https://hub.docker.com/_/ubuntu -FROM arm64v8/ubuntu:20.04 +FROM arm64v8/ubuntu:rolling # Downloads to user config dir ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/ @@ -18,11 +18,9 @@ RUN apt install --no-install-recommends -y python3-pip git zip curl htop gcc lib # Install pip packages COPY requirements.txt . RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -r requirements.txt ultralytics gsutil notebook \ - tensorflow-aarch64 - # tensorflowjs \ - # onnx onnx-simplifier onnxruntime \ - # coremltools openvino-dev \ +RUN pip install --no-cache -r requirements.txt albumentations gsutil notebook \ + coremltools onnx onnxruntime + # tensorflow-aarch64 tensorflowjs \ # Create working directory RUN mkdir -p /usr/src/app diff --git a/utils/docker/Dockerfile-cpu b/utils/docker/Dockerfile-cpu index 558f81f..06bad9a 100644 --- a/utils/docker/Dockerfile-cpu +++ b/utils/docker/Dockerfile-cpu @@ -3,7 +3,7 @@ # Image is CPU-optimized for ONNX, OpenVINO and PyTorch YOLOv5 deployments # Start FROM Ubuntu image https://hub.docker.com/_/ubuntu -FROM ubuntu:20.04 +FROM ubuntu:rolling # Downloads to user config dir ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/ @@ -18,9 +18,9 @@ RUN apt install --no-install-recommends -y python3-pip git zip curl htop libgl1- # Install pip packages COPY requirements.txt . RUN python3 -m pip install --upgrade pip wheel -RUN pip install --no-cache -r requirements.txt ultralytics albumentations gsutil notebook \ - coremltools onnx onnx-simplifier onnxruntime tensorflow-cpu tensorflowjs \ - # openvino-dev \ +RUN pip install --no-cache -r requirements.txt albumentations gsutil notebook \ + coremltools onnx onnx-simplifier onnxruntime 'openvino-dev>=2022.3' \ + # tensorflow tensorflowjs \ --extra-index-url https://download.pytorch.org/whl/cpu # Create working directory diff --git a/utils/downloads.py b/utils/downloads.py index 72ea873..643b529 100644 --- a/utils/downloads.py +++ b/utils/downloads.py @@ -26,8 +26,10 @@ def is_url(url, check=True): def gsutil_getsize(url=''): # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du - s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8') - return eval(s.split(' ')[0]) if len(s) else 0 # bytes + output = subprocess.check_output(['gsutil', 'du', url], shell=True, encoding='utf-8') + if output: + return int(output.split()[0]) + return 0 def url_getsize(url='https://ultralytics.com/images/bus.jpg'): @@ -36,6 +38,25 @@ def url_getsize(url='https://ultralytics.com/images/bus.jpg'): return int(response.headers.get('content-length', -1)) +def curl_download(url, filename, *, silent: bool = False) -> bool: + """ + Download a file from a url to a filename using curl. + """ + silent_option = 'sS' if silent else '' # silent + proc = subprocess.run([ + 'curl', + '-#', + f'-{silent_option}L', + url, + '--output', + filename, + '--retry', + '9', + '-C', + '-',]) + return proc.returncode == 0 + + def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes from utils.general import LOGGER @@ -50,12 +71,13 @@ def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''): if file.exists(): file.unlink() # remove partial downloads LOGGER.info(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...') - os.system(f"curl -# -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail + # curl download, retry and resume on fail + curl_download(url2 or url, file) finally: if not file.exists() or file.stat().st_size < min_bytes: # check if file.exists(): file.unlink() # remove partial downloads - LOGGER.info(f"ERROR: {assert_msg}\n{error_msg}") + LOGGER.info(f'ERROR: {assert_msg}\n{error_msg}') LOGGER.info('') @@ -98,11 +120,9 @@ def attempt_download(file, repo='ultralytics/yolov5', release='v7.0'): file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required) if name in assets: - url3 = 'https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl' # backup gdrive mirror - safe_download( - file, - url=f'https://github.com/{repo}/releases/download/{tag}/{name}', - min_bytes=1E5, - error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag} or {url3}') + safe_download(file, + url=f'https://github.com/{repo}/releases/download/{tag}/{name}', + min_bytes=1E5, + error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/{tag}') return str(file) diff --git a/utils/flask_rest_api/example_request.py b/utils/flask_rest_api/example_request.py index 773ad89..952e5dc 100644 --- a/utils/flask_rest_api/example_request.py +++ b/utils/flask_rest_api/example_request.py @@ -7,13 +7,13 @@ import pprint import requests -DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s" -IMAGE = "zidane.jpg" +DETECTION_URL = 'http://localhost:5000/v1/object-detection/yolov5s' +IMAGE = 'zidane.jpg' # Read image -with open(IMAGE, "rb") as f: +with open(IMAGE, 'rb') as f: image_data = f.read() -response = requests.post(DETECTION_URL, files={"image": image_data}).json() +response = requests.post(DETECTION_URL, files={'image': image_data}).json() pprint.pprint(response) diff --git a/utils/flask_rest_api/restapi.py b/utils/flask_rest_api/restapi.py index 8482435..9258b1a 100644 --- a/utils/flask_rest_api/restapi.py +++ b/utils/flask_rest_api/restapi.py @@ -13,36 +13,36 @@ from PIL import Image app = Flask(__name__) models = {} -DETECTION_URL = "/v1/object-detection/" +DETECTION_URL = '/v1/object-detection/' -@app.route(DETECTION_URL, methods=["POST"]) +@app.route(DETECTION_URL, methods=['POST']) def predict(model): - if request.method != "POST": + if request.method != 'POST': return - if request.files.get("image"): + if request.files.get('image'): # Method 1 # with request.files["image"] as f: # im = Image.open(io.BytesIO(f.read())) # Method 2 - im_file = request.files["image"] + im_file = request.files['image'] im_bytes = im_file.read() im = Image.open(io.BytesIO(im_bytes)) if model in models: results = models[model](im, size=640) # reduce size=320 for faster inference - return results.pandas().xyxy[0].to_json(orient="records") + return results.pandas().xyxy[0].to_json(orient='records') -if __name__ == "__main__": - parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model") - parser.add_argument("--port", default=5000, type=int, help="port number") +if __name__ == '__main__': + parser = argparse.ArgumentParser(description='Flask API exposing YOLOv5 model') + parser.add_argument('--port', default=5000, type=int, help='port number') parser.add_argument('--model', nargs='+', default=['yolov5s'], help='model(s) to run, i.e. --model yolov5n yolov5s') opt = parser.parse_args() for m in opt.model: - models[m] = torch.hub.load("ultralytics/yolov5", m, force_reload=True, skip_validation=True) + models[m] = torch.hub.load('ultralytics/yolov5', m, force_reload=True, skip_validation=True) - app.run(host="0.0.0.0", port=opt.port) # debug=True causes Restarting with stat + app.run(host='0.0.0.0', port=opt.port) # debug=True causes Restarting with stat diff --git a/utils/general.py b/utils/general.py index 0bbcb6e..7462046 100644 --- a/utils/general.py +++ b/utils/general.py @@ -14,6 +14,7 @@ import platform import random import re import signal +import subprocess import sys import time import urllib @@ -28,7 +29,6 @@ from typing import Optional from zipfile import ZipFile, is_zipfile import cv2 -import IPython import numpy as np import pandas as pd import pkg_resources as pkg @@ -37,7 +37,7 @@ import torchvision import yaml from utils import TryExcept, emojis -from utils.downloads import gsutil_getsize +from utils.downloads import curl_download, gsutil_getsize from utils.metrics import box_iou, fitness FILE = Path(__file__).resolve() @@ -76,10 +76,18 @@ def is_colab(): return 'google.colab' in sys.modules -def is_notebook(): - # Is environment a Jupyter notebook? Verified on Colab, Jupyterlab, Kaggle, Paperspace - ipython_type = str(type(IPython.get_ipython())) - return 'colab' in ipython_type or 'zmqshell' in ipython_type +def is_jupyter(): + """ + Check if the current script is running inside a Jupyter Notebook. + Verified on Colab, Jupyterlab, Kaggle, Paperspace. + + Returns: + bool: True if running inside a Jupyter Notebook, False otherwise. + """ + with contextlib.suppress(Exception): + from IPython import get_ipython + return get_ipython() is not None + return False def is_kaggle(): @@ -89,11 +97,11 @@ def is_kaggle(): def is_docker() -> bool: """Check if the process runs inside a docker container.""" - if Path("/.dockerenv").exists(): + if Path('/.dockerenv').exists(): return True try: # check if docker is in control groups - with open("/proc/self/cgroup") as file: - return any("docker" in line for line in file) + with open('/proc/self/cgroup') as file: + return any('docker' in line for line in file) except OSError: return False @@ -112,7 +120,7 @@ def is_writeable(dir, test=False): return False -LOGGING_NAME = "yolov5" +LOGGING_NAME = 'yolov5' def set_logging(name=LOGGING_NAME, verbose=True): @@ -120,21 +128,21 @@ def set_logging(name=LOGGING_NAME, verbose=True): rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings level = logging.INFO if verbose and rank in {-1, 0} else logging.ERROR logging.config.dictConfig({ - "version": 1, - "disable_existing_loggers": False, - "formatters": { + 'version': 1, + 'disable_existing_loggers': False, + 'formatters': { name: { - "format": "%(message)s"}}, - "handlers": { + 'format': '%(message)s'}}, + 'handlers': { name: { - "class": "logging.StreamHandler", - "formatter": name, - "level": level,}}, - "loggers": { + 'class': 'logging.StreamHandler', + 'formatter': name, + 'level': level,}}, + 'loggers': { name: { - "level": level, - "handlers": [name], - "propagate": False,}}}) + 'level': level, + 'handlers': [name], + 'propagate': False,}}}) set_logging(LOGGING_NAME) # run before defining LOGGER @@ -217,7 +225,7 @@ class WorkingDirectory(contextlib.ContextDecorator): def methods(instance): # Get class/instance methods - return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")] + return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith('__')] def print_args(args: Optional[dict] = None, show_file=True, show_func=False): @@ -298,7 +306,7 @@ def check_online(): def run_once(): # Check once try: - socket.create_connection(("1.1.1.1", 443), 5) # check host accessibility + socket.create_connection(('1.1.1.1', 443), 5) # check host accessibility return True except OSError: return False @@ -337,7 +345,7 @@ def check_git_status(repo='ultralytics/yolov5', branch='master'): n = int(check_output(f'git rev-list {local_branch}..{remote}/{branch} --count', shell=True)) # commits behind if n > 0: pull = 'git pull' if remote == 'origin' else f'git pull {remote} {branch}' - s += f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use `{pull}` or `git clone {url}` to update." + s += f"⚠️ YOLOv5 is out of date by {n} commit{'s' * (n > 1)}. Use '{pull}' or 'git clone {url}' to update." else: s += f'up to date with {url} ✅' LOGGER.info(s) @@ -385,7 +393,7 @@ def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), insta check_python() # check python version if isinstance(requirements, Path): # requirements.txt file file = requirements.resolve() - assert file.exists(), f"{prefix} {file} not found, check failed." + assert file.exists(), f'{prefix} {file} not found, check failed.' with file.open() as f: requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude] elif isinstance(requirements, str): @@ -428,7 +436,7 @@ def check_img_size(imgsz, s=32, floor=0): def check_imshow(warn=False): # Check if environment supports image displays try: - assert not is_notebook() + assert not is_jupyter() assert not is_docker() cv2.imshow('test', np.zeros((1, 1, 3))) cv2.waitKey(1) @@ -449,7 +457,7 @@ def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''): for f in file if isinstance(file, (list, tuple)) else [file]: s = Path(f).suffix.lower() # file suffix if len(s): - assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}" + assert s in suffix, f'{msg}{f} acceptable suffix is {suffix}' def check_yaml(file, suffix=('.yaml', '.yml')): @@ -551,12 +559,12 @@ def check_dataset(data, autodownload=True): r = None # success elif s.startswith('bash '): # bash script LOGGER.info(f'Running {s} ...') - r = os.system(s) + r = subprocess.run(s, shell=True) else: # python script r = exec(s, {'yaml': data}) # return None dt = f'({round(time.time() - t, 1)}s)' - s = f"success ✅ {dt}, saved to {colorstr('bold', DATASETS_DIR)}" if r in (0, None) else f"failure {dt} ❌" - LOGGER.info(f"Dataset download {s}") + s = f"success ✅ {dt}, saved to {colorstr('bold', DATASETS_DIR)}" if r in (0, None) else f'failure {dt} ❌' + LOGGER.info(f'Dataset download {s}') check_font('Arial.ttf' if is_ascii(data['names']) else 'Arial.Unicode.ttf', progress=True) # download fonts return data # dictionary @@ -629,10 +637,7 @@ def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1, retry LOGGER.info(f'Downloading {url} to {f}...') for i in range(retry + 1): if curl: - s = 'sS' if threads > 1 else '' # silent - r = os.system( - f'curl -# -{s}L "{url}" -o "{f}" --retry 9 -C -') # curl download with retry, continue - success = r == 0 + success = curl_download(url, f, silent=(threads > 1)) else: torch.hub.download_url_to_file(url, f, progress=threads == 1) # torch download success = f.is_file() @@ -648,9 +653,9 @@ def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1, retry if is_zipfile(f): unzip_file(f, dir) # unzip elif is_tarfile(f): - os.system(f'tar xf {f} --directory {f.parent}') # unzip + subprocess.run(['tar', 'xf', f, '--directory', f.parent], check=True) # unzip elif f.suffix == '.gz': - os.system(f'tar xfz {f} --directory {f.parent}') # unzip + subprocess.run(['tar', 'xfz', f, '--directory', f.parent], check=True) # unzip if delete: f.unlink() # remove zip @@ -675,7 +680,7 @@ def make_divisible(x, divisor): def clean_str(s): # Cleans a string by replacing special characters with underscore _ - return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s) + return re.sub(pattern='[|@#!¡·$€%&()=?¿^*;:,¨´><+]', repl='_', string=s) def one_cycle(y1=0.0, y2=1.0, steps=100): @@ -1022,7 +1027,7 @@ def print_mutation(keys, results, hyp, save_dir, bucket, prefix=colorstr('evolve if bucket: url = f'gs://{bucket}/evolve.csv' if gsutil_getsize(url) > (evolve_csv.stat().st_size if evolve_csv.exists() else 0): - os.system(f'gsutil cp {url} {save_dir}') # download evolve.csv if larger than local + subprocess.run(['gsutil', 'cp', f'{url}', f'{save_dir}']) # download evolve.csv if larger than local # Log to evolve.csv s = '' if evolve_csv.exists() else (('%20s,' * n % keys).rstrip(',') + '\n') # add header @@ -1046,7 +1051,7 @@ def print_mutation(keys, results, hyp, save_dir, bucket, prefix=colorstr('evolve for x in vals) + '\n\n') if bucket: - os.system(f'gsutil cp {evolve_csv} {evolve_yaml} gs://{bucket}') # upload + subprocess.run(['gsutil', 'cp', f'{evolve_csv}', f'{evolve_yaml}', f'gs://{bucket}']) # upload def apply_classifier(x, model, img, im0): diff --git a/utils/google_app_engine/additional_requirements.txt b/utils/google_app_engine/additional_requirements.txt index 42d7ffc..d5b7675 100644 --- a/utils/google_app_engine/additional_requirements.txt +++ b/utils/google_app_engine/additional_requirements.txt @@ -1,4 +1,5 @@ # add these requirements in your app on top of the existing ones pip==21.1 Flask==1.0.2 -gunicorn==19.9.0 +gunicorn==19.10.0 +werkzeug>=2.2.3 # not directly required, pinned by Snyk to avoid a vulnerability diff --git a/utils/loggers/__init__.py b/utils/loggers/__init__.py index 22da870..9de1f22 100644 --- a/utils/loggers/__init__.py +++ b/utils/loggers/__init__.py @@ -84,10 +84,6 @@ class Loggers(): self.csv = True # always log to csv # Messages - # if not wandb: - # prefix = colorstr('Weights & Biases: ') - # s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs in Weights & Biases" - # self.logger.info(s) if not clearml: prefix = colorstr('ClearML: ') s = f"{prefix}run 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML" @@ -105,14 +101,8 @@ class Loggers(): # W&B if wandb and 'wandb' in self.include: - wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://') - run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None self.opt.hyp = self.hyp # add hyperparameters - self.wandb = WandbLogger(self.opt, run_id) - # temp warn. because nested artifacts not supported after 0.12.10 - # if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.11'): - # s = "YOLOv5 temporarily requires wandb version 0.12.10 or below. Some features may not work as expected." - # self.logger.warning(s) + self.wandb = WandbLogger(self.opt) else: self.wandb = None @@ -131,8 +121,8 @@ class Loggers(): # Comet if comet_ml and 'comet' in self.include: - if isinstance(self.opt.resume, str) and self.opt.resume.startswith("comet://"): - run_id = self.opt.resume.split("/")[-1] + if isinstance(self.opt.resume, str) and self.opt.resume.startswith('comet://'): + run_id = self.opt.resume.split('/')[-1] self.comet_logger = CometLogger(self.opt, self.hyp, run_id=run_id) else: @@ -168,14 +158,14 @@ class Loggers(): plot_labels(labels, names, self.save_dir) paths = self.save_dir.glob('*labels*.jpg') # training labels if self.wandb: - self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]}) + self.wandb.log({'Labels': [wandb.Image(str(x), caption=x.name) for x in paths]}) # if self.clearml: # pass # ClearML saves these images automatically using hooks if self.comet_logger: self.comet_logger.on_pretrain_routine_end(paths) def on_train_batch_end(self, model, ni, imgs, targets, paths, vals): - log_dict = dict(zip(self.keys[0:3], vals)) + log_dict = dict(zip(self.keys[:3], vals)) # Callback runs on train batch end # ni: number integrated batches (since train start) if self.plots: @@ -221,10 +211,10 @@ class Loggers(): # Callback runs on val end if self.wandb or self.clearml: files = sorted(self.save_dir.glob('val*.jpg')) - if self.wandb: - self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]}) - if self.clearml: - self.clearml.log_debug_samples(files, title='Validation') + if self.wandb: + self.wandb.log({'Validation': [wandb.Image(str(f), caption=f.name) for f in files]}) + if self.clearml: + self.clearml.log_debug_samples(files, title='Validation') if self.comet_logger: self.comet_logger.on_val_end(nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix) @@ -253,7 +243,7 @@ class Loggers(): for i, name in enumerate(self.best_keys): self.wandb.wandb_run.summary[name] = best_results[i] # log best results in the summary self.wandb.log(x) - self.wandb.end_epoch(best_result=best_fitness == fi) + self.wandb.end_epoch() if self.clearml: self.clearml.current_epoch_logged_images = set() # reset epoch image limit @@ -289,7 +279,7 @@ class Loggers(): if self.wandb: self.wandb.log(dict(zip(self.keys[3:10], results))) - self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]}) + self.wandb.log({'Results': [wandb.Image(str(f), caption=f.name) for f in files]}) # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model if not self.opt.evolve: wandb.log_artifact(str(best if best.exists() else last), @@ -339,7 +329,7 @@ class GenericLogger: if wandb and 'wandb' in self.include: self.wandb = wandb.init(project=web_project_name(str(opt.project)), - name=None if opt.name == "exp" else opt.name, + name=None if opt.name == 'exp' else opt.name, config=opt) else: self.wandb = None @@ -380,12 +370,12 @@ class GenericLogger: def log_model(self, model_path, epoch=0, metadata={}): # Log model to all loggers if self.wandb: - art = wandb.Artifact(name=f"run_{wandb.run.id}_model", type="model", metadata=metadata) + art = wandb.Artifact(name=f'run_{wandb.run.id}_model', type='model', metadata=metadata) art.add_file(str(model_path)) wandb.log_artifact(art) def update_params(self, params): - # Update the paramters logged + # Update the parameters logged if self.wandb: wandb.run.config.update(params, allow_val_change=True) diff --git a/utils/loggers/clearml/README.md b/utils/loggers/clearml/README.md index 3cf4c26..ca41c04 100644 --- a/utils/loggers/clearml/README.md +++ b/utils/loggers/clearml/README.md @@ -23,7 +23,6 @@ And so much more. It's up to you how many of these tools you want to use, you ca ![ClearML scalars dashboard](https://github.com/thepycoder/clearml_screenshots/raw/main/experiment_manager_with_compare.gif) -

@@ -35,15 +34,15 @@ Either sign up for free to the [ClearML Hosted Service](https://cutt.ly/yolov5-t 1. Install the `clearml` python package: - ```bash - pip install clearml - ``` + ```bash + pip install clearml + ``` 1. Connect the ClearML SDK to the server by [creating credentials](https://app.clear.ml/settings/workspace-configuration) (go right top to Settings -> Workspace -> Create new credentials), then execute the command below and follow the instructions: - ```bash - clearml-init - ``` + ```bash + clearml-init + ``` That's it! You're done 😎 @@ -60,18 +59,20 @@ pip install clearml>=1.2.0 This will enable integration with the YOLOv5 training script. Every training run from now on, will be captured and stored by the ClearML experiment manager. If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py` script, by default the project will be called `YOLOv5` and the task `Training`. -PLEASE NOTE: ClearML uses `/` as a delimter for subprojects, so be careful when using `/` in your project name! +PLEASE NOTE: ClearML uses `/` as a delimiter for subprojects, so be careful when using `/` in your project name! ```bash python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache ``` or with custom project and task name: + ```bash python train.py --project my_project --name my_training --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache ``` This will capture: + - Source code + uncommitted changes - Installed packages - (Hyper)parameters @@ -94,7 +95,7 @@ There even more we can do with all of this information, like hyperparameter opti ## 🔗 Dataset Version Management -Versioning your data separately from your code is generally a good idea and makes it easy to aqcuire the latest version too. This repository supports supplying a dataset version ID and it will make sure to get the data if it's not there yet. Next to that, this workflow also saves the used dataset ID as part of the task parameters, so you will always know for sure which data was used in which experiment! +Versioning your data separately from your code is generally a good idea and makes it easy to acquire the latest version too. This repository supports supplying a dataset version ID, and it will make sure to get the data if it's not there yet. Next to that, this workflow also saves the used dataset ID as part of the task parameters, so you will always know for sure which data was used in which experiment! ![ClearML Dataset Interface](https://github.com/thepycoder/clearml_screenshots/raw/main/clearml_data.gif) @@ -112,6 +113,7 @@ The YOLOv5 repository supports a number of different datasets by using yaml file |_ LICENSE |_ README.txt ``` + But this can be any dataset you wish. Feel free to use your own, as long as you keep to this folder structure. Next, ⚠️**copy the corresponding yaml file to the root of the dataset folder**⚠️. This yaml files contains the information ClearML will need to properly use the dataset. You can make this yourself too, of course, just follow the structure of the example yamls. @@ -132,13 +134,15 @@ Basically we need the following keys: `path`, `train`, `test`, `val`, `nc`, `nam ### Upload Your Dataset -To get this dataset into ClearML as a versionned dataset, go to the dataset root folder and run the following command: +To get this dataset into ClearML as a versioned dataset, go to the dataset root folder and run the following command: + ```bash cd coco128 clearml-data sync --project YOLOv5 --name coco128 --folder . ``` The command `clearml-data sync` is actually a shorthand command. You could also run these commands one after the other: + ```bash # Optionally add --parent if you want to base # this version on another dataset version, so no duplicate files are uploaded! @@ -177,7 +181,7 @@ python utils/loggers/clearml/hpo.py ## 🤯 Remote Execution (advanced) -Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you have access to a very powerful GPU machine on-site or you have some budget to use cloud GPUs. +Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you have access to a very powerful GPU machine on-site, or you have some budget to use cloud GPUs. This is where the ClearML Agent comes into play. Check out what the agent can do here: - [YouTube video](https://youtu.be/MX3BrXnaULs) @@ -186,6 +190,7 @@ This is where the ClearML Agent comes into play. Check out what the agent can do In short: every experiment tracked by the experiment manager contains enough information to reproduce it on a different machine (installed packages, uncommitted changes etc.). So a ClearML agent does just that: it listens to a queue for incoming tasks and when it finds one, it recreates the environment and runs it while still reporting scalars, plots etc. to the experiment manager. You can turn any machine (a cloud VM, a local GPU machine, your own laptop ... ) into a ClearML agent by simply running: + ```bash clearml-agent daemon --queue [--docker] ``` @@ -194,11 +199,11 @@ clearml-agent daemon --queue [--docker] With our agent running, we can give it some work. Remember from the HPO section that we can clone a task and edit the hyperparameters? We can do that from the interface too! -🪄 Clone the experiment by right clicking it +🪄 Clone the experiment by right-clicking it 🎯 Edit the hyperparameters to what you wish them to be -⏳ Enqueue the task to any of the queues by right clicking it +⏳ Enqueue the task to any of the queues by right-clicking it ![Enqueue a task from the UI](https://github.com/thepycoder/clearml_screenshots/raw/main/enqueue.gif) @@ -206,7 +211,8 @@ With our agent running, we can give it some work. Remember from the HPO section Now you can clone a task like we explained above, or simply mark your current script by adding `task.execute_remotely()` and on execution it will be put into a queue, for the agent to start working on! -To run the YOLOv5 training script remotely, all you have to do is add this line to the training.py script after the clearml logger has been instatiated: +To run the YOLOv5 training script remotely, all you have to do is add this line to the training.py script after the clearml logger has been instantiated: + ```python # ... # Loggers @@ -214,16 +220,17 @@ data_dict = None if RANK in {-1, 0}: loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance if loggers.clearml: - loggers.clearml.task.execute_remotely(queue='my_queue') # <------ ADD THIS LINE + loggers.clearml.task.execute_remotely(queue="my_queue") # <------ ADD THIS LINE # Data_dict is either None is user did not choose for ClearML dataset or is filled in by ClearML data_dict = loggers.clearml.data_dict # ... ``` + When running the training script after this change, python will run the script up until that line, after which it will package the code and send it to the queue instead! ### Autoscaling workers -ClearML comes with autoscalers too! This tool will automatically spin up new remote machines in the cloud of your choice (AWS, GCP, Azure) and turn them into ClearML agents for you whenever there are experiments detected in the queue. Once the tasks are processed, the autoscaler will automatically shut down the remote machines and you stop paying! +ClearML comes with autoscalers too! This tool will automatically spin up new remote machines in the cloud of your choice (AWS, GCP, Azure) and turn them into ClearML agents for you whenever there are experiments detected in the queue. Once the tasks are processed, the autoscaler will automatically shut down the remote machines, and you stop paying! Check out the autoscalers getting started video below. diff --git a/utils/loggers/clearml/clearml_utils.py b/utils/loggers/clearml/clearml_utils.py index 3457727..2764abe 100644 --- a/utils/loggers/clearml/clearml_utils.py +++ b/utils/loggers/clearml/clearml_utils.py @@ -25,7 +25,7 @@ def construct_dataset(clearml_info_string): dataset_root_path = Path(dataset.get_local_copy()) # We'll search for the yaml file definition in the dataset - yaml_filenames = list(glob.glob(str(dataset_root_path / "*.yaml")) + glob.glob(str(dataset_root_path / "*.yml"))) + yaml_filenames = list(glob.glob(str(dataset_root_path / '*.yaml')) + glob.glob(str(dataset_root_path / '*.yml'))) if len(yaml_filenames) > 1: raise ValueError('More than one yaml file was found in the dataset root, cannot determine which one contains ' 'the dataset definition this way.') @@ -100,7 +100,7 @@ class ClearmlLogger: self.task.connect(opt, name='Args') # Make sure the code is easily remotely runnable by setting the docker image to use by the remote agent - self.task.set_base_docker("ultralytics/yolov5:latest", + self.task.set_base_docker('ultralytics/yolov5:latest', docker_arguments='--ipc=host -e="CLEARML_AGENT_SKIP_PYTHON_ENV_INSTALL=1"', docker_setup_bash_script='pip install clearml') @@ -150,7 +150,7 @@ class ClearmlLogger: class_name = class_names[int(class_nr)] confidence_percentage = round(float(conf) * 100, 2) - label = f"{class_name}: {confidence_percentage}%" + label = f'{class_name}: {confidence_percentage}%' if conf > conf_threshold: annotator.rectangle(box.cpu().numpy(), outline=color) diff --git a/utils/loggers/comet/README.md b/utils/loggers/comet/README.md index 8a361e2..47e6a45 100644 --- a/utils/loggers/comet/README.md +++ b/utils/loggers/comet/README.md @@ -23,7 +23,7 @@ pip install comet_ml There are two ways to configure Comet with YOLOv5. -You can either set your credentials through enviroment variables +You can either set your credentials through environment variables **Environment Variables** @@ -49,11 +49,12 @@ project_name= # This will default to 'yolov5' python train.py --img 640 --batch 16 --epochs 5 --data coco128.yaml --weights yolov5s.pt ``` -That's it! Comet will automatically log your hyperparameters, command line arguments, training and valiation metrics. You can visualize and analyze your runs in the Comet UI +That's it! Comet will automatically log your hyperparameters, command line arguments, training and validation metrics. You can visualize and analyze your runs in the Comet UI yolo-ui # Try out an Example! + Check out an example of a [completed run here](https://www.comet.com/examples/comet-example-yolov5/a0e29e0e9b984e4a822db2a62d0cb357?experiment-tab=chart&showOutliers=true&smoothing=0&transformY=smoothing&xAxis=step&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github) Or better yet, try it out yourself in this Colab Notebook @@ -65,6 +66,7 @@ Or better yet, try it out yourself in this Colab Notebook By default, Comet will log the following items ## Metrics + - Box Loss, Object Loss, Classification Loss for the training and validation data - mAP_0.5, mAP_0.5:0.95 metrics for the validation data. - Precision and Recall for the validation data @@ -121,7 +123,6 @@ You can control the frequency of logged predictions and the associated images by Here is an [example project using the Panel](https://www.comet.com/examples/comet-example-yolov5?shareable=YcwMiJaZSXfcEXpGOHDD12vA1&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github) - ```shell python train.py \ --img 640 \ @@ -192,6 +193,7 @@ If you would like to use a dataset from Comet Artifacts, set the `path` variable # contents of artifact.yaml file path: "comet:///:" ``` + Then pass this file to your training script in the following way ```shell @@ -221,7 +223,7 @@ python train.py \ ## Hyperparameter Search with the Comet Optimizer -YOLOv5 is also integrated with Comet's Optimizer, making is simple to visualie hyperparameter sweeps in the Comet UI. +YOLOv5 is also integrated with Comet's Optimizer, making is simple to visualize hyperparameter sweeps in the Comet UI. ### Configuring an Optimizer Sweep diff --git a/utils/loggers/comet/__init__.py b/utils/loggers/comet/__init__.py index b0318f8..d459984 100644 --- a/utils/loggers/comet/__init__.py +++ b/utils/loggers/comet/__init__.py @@ -17,7 +17,7 @@ try: # Project Configuration config = comet_ml.config.get_config() - COMET_PROJECT_NAME = config.get_string(os.getenv("COMET_PROJECT_NAME"), "comet.project_name", default="yolov5") + COMET_PROJECT_NAME = config.get_string(os.getenv('COMET_PROJECT_NAME'), 'comet.project_name', default='yolov5') except (ModuleNotFoundError, ImportError): comet_ml = None COMET_PROJECT_NAME = None @@ -31,32 +31,32 @@ from utils.dataloaders import img2label_paths from utils.general import check_dataset, scale_boxes, xywh2xyxy from utils.metrics import box_iou -COMET_PREFIX = "comet://" +COMET_PREFIX = 'comet://' -COMET_MODE = os.getenv("COMET_MODE", "online") +COMET_MODE = os.getenv('COMET_MODE', 'online') # Model Saving Settings -COMET_MODEL_NAME = os.getenv("COMET_MODEL_NAME", "yolov5") +COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'yolov5') # Dataset Artifact Settings -COMET_UPLOAD_DATASET = os.getenv("COMET_UPLOAD_DATASET", "false").lower() == "true" +COMET_UPLOAD_DATASET = os.getenv('COMET_UPLOAD_DATASET', 'false').lower() == 'true' # Evaluation Settings -COMET_LOG_CONFUSION_MATRIX = os.getenv("COMET_LOG_CONFUSION_MATRIX", "true").lower() == "true" -COMET_LOG_PREDICTIONS = os.getenv("COMET_LOG_PREDICTIONS", "true").lower() == "true" -COMET_MAX_IMAGE_UPLOADS = int(os.getenv("COMET_MAX_IMAGE_UPLOADS", 100)) +COMET_LOG_CONFUSION_MATRIX = os.getenv('COMET_LOG_CONFUSION_MATRIX', 'true').lower() == 'true' +COMET_LOG_PREDICTIONS = os.getenv('COMET_LOG_PREDICTIONS', 'true').lower() == 'true' +COMET_MAX_IMAGE_UPLOADS = int(os.getenv('COMET_MAX_IMAGE_UPLOADS', 100)) # Confusion Matrix Settings -CONF_THRES = float(os.getenv("CONF_THRES", 0.001)) -IOU_THRES = float(os.getenv("IOU_THRES", 0.6)) +CONF_THRES = float(os.getenv('CONF_THRES', 0.001)) +IOU_THRES = float(os.getenv('IOU_THRES', 0.6)) # Batch Logging Settings -COMET_LOG_BATCH_METRICS = os.getenv("COMET_LOG_BATCH_METRICS", "false").lower() == "true" -COMET_BATCH_LOGGING_INTERVAL = os.getenv("COMET_BATCH_LOGGING_INTERVAL", 1) -COMET_PREDICTION_LOGGING_INTERVAL = os.getenv("COMET_PREDICTION_LOGGING_INTERVAL", 1) -COMET_LOG_PER_CLASS_METRICS = os.getenv("COMET_LOG_PER_CLASS_METRICS", "false").lower() == "true" +COMET_LOG_BATCH_METRICS = os.getenv('COMET_LOG_BATCH_METRICS', 'false').lower() == 'true' +COMET_BATCH_LOGGING_INTERVAL = os.getenv('COMET_BATCH_LOGGING_INTERVAL', 1) +COMET_PREDICTION_LOGGING_INTERVAL = os.getenv('COMET_PREDICTION_LOGGING_INTERVAL', 1) +COMET_LOG_PER_CLASS_METRICS = os.getenv('COMET_LOG_PER_CLASS_METRICS', 'false').lower() == 'true' -RANK = int(os.getenv("RANK", -1)) +RANK = int(os.getenv('RANK', -1)) to_pil = T.ToPILImage() @@ -66,7 +66,7 @@ class CometLogger: with Comet """ - def __init__(self, opt, hyp, run_id=None, job_type="Training", **experiment_kwargs) -> None: + def __init__(self, opt, hyp, run_id=None, job_type='Training', **experiment_kwargs) -> None: self.job_type = job_type self.opt = opt self.hyp = hyp @@ -87,52 +87,52 @@ class CometLogger: # Default parameters to pass to Experiment objects self.default_experiment_kwargs = { - "log_code": False, - "log_env_gpu": True, - "log_env_cpu": True, - "project_name": COMET_PROJECT_NAME,} + 'log_code': False, + 'log_env_gpu': True, + 'log_env_cpu': True, + 'project_name': COMET_PROJECT_NAME,} self.default_experiment_kwargs.update(experiment_kwargs) self.experiment = self._get_experiment(self.comet_mode, run_id) self.data_dict = self.check_dataset(self.opt.data) - self.class_names = self.data_dict["names"] - self.num_classes = self.data_dict["nc"] + self.class_names = self.data_dict['names'] + self.num_classes = self.data_dict['nc'] self.logged_images_count = 0 self.max_images = COMET_MAX_IMAGE_UPLOADS if run_id is None: - self.experiment.log_other("Created from", "YOLOv5") + self.experiment.log_other('Created from', 'YOLOv5') if not isinstance(self.experiment, comet_ml.OfflineExperiment): - workspace, project_name, experiment_id = self.experiment.url.split("/")[-3:] + workspace, project_name, experiment_id = self.experiment.url.split('/')[-3:] self.experiment.log_other( - "Run Path", - f"{workspace}/{project_name}/{experiment_id}", + 'Run Path', + f'{workspace}/{project_name}/{experiment_id}', ) self.log_parameters(vars(opt)) self.log_parameters(self.opt.hyp) self.log_asset_data( self.opt.hyp, - name="hyperparameters.json", - metadata={"type": "hyp-config-file"}, + name='hyperparameters.json', + metadata={'type': 'hyp-config-file'}, ) self.log_asset( - f"{self.opt.save_dir}/opt.yaml", - metadata={"type": "opt-config-file"}, + f'{self.opt.save_dir}/opt.yaml', + metadata={'type': 'opt-config-file'}, ) self.comet_log_confusion_matrix = COMET_LOG_CONFUSION_MATRIX - if hasattr(self.opt, "conf_thres"): + if hasattr(self.opt, 'conf_thres'): self.conf_thres = self.opt.conf_thres else: self.conf_thres = CONF_THRES - if hasattr(self.opt, "iou_thres"): + if hasattr(self.opt, 'iou_thres'): self.iou_thres = self.opt.iou_thres else: self.iou_thres = IOU_THRES - self.log_parameters({"val_iou_threshold": self.iou_thres, "val_conf_threshold": self.conf_thres}) + self.log_parameters({'val_iou_threshold': self.iou_thres, 'val_conf_threshold': self.conf_thres}) self.comet_log_predictions = COMET_LOG_PREDICTIONS if self.opt.bbox_interval == -1: @@ -147,22 +147,22 @@ class CometLogger: self.comet_log_per_class_metrics = COMET_LOG_PER_CLASS_METRICS self.experiment.log_others({ - "comet_mode": COMET_MODE, - "comet_max_image_uploads": COMET_MAX_IMAGE_UPLOADS, - "comet_log_per_class_metrics": COMET_LOG_PER_CLASS_METRICS, - "comet_log_batch_metrics": COMET_LOG_BATCH_METRICS, - "comet_log_confusion_matrix": COMET_LOG_CONFUSION_MATRIX, - "comet_model_name": COMET_MODEL_NAME,}) + 'comet_mode': COMET_MODE, + 'comet_max_image_uploads': COMET_MAX_IMAGE_UPLOADS, + 'comet_log_per_class_metrics': COMET_LOG_PER_CLASS_METRICS, + 'comet_log_batch_metrics': COMET_LOG_BATCH_METRICS, + 'comet_log_confusion_matrix': COMET_LOG_CONFUSION_MATRIX, + 'comet_model_name': COMET_MODEL_NAME,}) # Check if running the Experiment with the Comet Optimizer - if hasattr(self.opt, "comet_optimizer_id"): - self.experiment.log_other("optimizer_id", self.opt.comet_optimizer_id) - self.experiment.log_other("optimizer_objective", self.opt.comet_optimizer_objective) - self.experiment.log_other("optimizer_metric", self.opt.comet_optimizer_metric) - self.experiment.log_other("optimizer_parameters", json.dumps(self.hyp)) + if hasattr(self.opt, 'comet_optimizer_id'): + self.experiment.log_other('optimizer_id', self.opt.comet_optimizer_id) + self.experiment.log_other('optimizer_objective', self.opt.comet_optimizer_objective) + self.experiment.log_other('optimizer_metric', self.opt.comet_optimizer_metric) + self.experiment.log_other('optimizer_parameters', json.dumps(self.hyp)) def _get_experiment(self, mode, experiment_id=None): - if mode == "offline": + if mode == 'offline': if experiment_id is not None: return comet_ml.ExistingOfflineExperiment( previous_experiment=experiment_id, @@ -182,11 +182,11 @@ class CometLogger: return comet_ml.Experiment(**self.default_experiment_kwargs) except ValueError: - logger.warning("COMET WARNING: " - "Comet credentials have not been set. " - "Comet will default to offline logging. " - "Please set your credentials to enable online logging.") - return self._get_experiment("offline", experiment_id) + logger.warning('COMET WARNING: ' + 'Comet credentials have not been set. ' + 'Comet will default to offline logging. ' + 'Please set your credentials to enable online logging.') + return self._get_experiment('offline', experiment_id) return @@ -210,12 +210,12 @@ class CometLogger: return model_metadata = { - "fitness_score": fitness_score[-1], - "epochs_trained": epoch + 1, - "save_period": opt.save_period, - "total_epochs": opt.epochs,} + 'fitness_score': fitness_score[-1], + 'epochs_trained': epoch + 1, + 'save_period': opt.save_period, + 'total_epochs': opt.epochs,} - model_files = glob.glob(f"{path}/*.pt") + model_files = glob.glob(f'{path}/*.pt') for model_path in model_files: name = Path(model_path).name @@ -232,12 +232,12 @@ class CometLogger: data_config = yaml.safe_load(f) if data_config['path'].startswith(COMET_PREFIX): - path = data_config['path'].replace(COMET_PREFIX, "") + path = data_config['path'].replace(COMET_PREFIX, '') data_dict = self.download_dataset_artifact(path) return data_dict - self.log_asset(self.opt.data, metadata={"type": "data-config-file"}) + self.log_asset(self.opt.data, metadata={'type': 'data-config-file'}) return check_dataset(data_file) @@ -253,8 +253,8 @@ class CometLogger: filtered_detections = detections[mask] filtered_labels = labelsn[mask] - image_id = path.split("/")[-1].split(".")[0] - image_name = f"{image_id}_curr_epoch_{self.experiment.curr_epoch}" + image_id = path.split('/')[-1].split('.')[0] + image_name = f'{image_id}_curr_epoch_{self.experiment.curr_epoch}' if image_name not in self.logged_image_names: native_scale_image = PIL.Image.open(path) self.log_image(native_scale_image, name=image_name) @@ -263,22 +263,22 @@ class CometLogger: metadata = [] for cls, *xyxy in filtered_labels.tolist(): metadata.append({ - "label": f"{self.class_names[int(cls)]}-gt", - "score": 100, - "box": { - "x": xyxy[0], - "y": xyxy[1], - "x2": xyxy[2], - "y2": xyxy[3]},}) + 'label': f'{self.class_names[int(cls)]}-gt', + 'score': 100, + 'box': { + 'x': xyxy[0], + 'y': xyxy[1], + 'x2': xyxy[2], + 'y2': xyxy[3]},}) for *xyxy, conf, cls in filtered_detections.tolist(): metadata.append({ - "label": f"{self.class_names[int(cls)]}", - "score": conf * 100, - "box": { - "x": xyxy[0], - "y": xyxy[1], - "x2": xyxy[2], - "y2": xyxy[3]},}) + 'label': f'{self.class_names[int(cls)]}', + 'score': conf * 100, + 'box': { + 'x': xyxy[0], + 'y': xyxy[1], + 'x2': xyxy[2], + 'y2': xyxy[3]},}) self.metadata_dict[image_name] = metadata self.logged_images_count += 1 @@ -305,35 +305,35 @@ class CometLogger: return predn, labelsn def add_assets_to_artifact(self, artifact, path, asset_path, split): - img_paths = sorted(glob.glob(f"{asset_path}/*")) + img_paths = sorted(glob.glob(f'{asset_path}/*')) label_paths = img2label_paths(img_paths) for image_file, label_file in zip(img_paths, label_paths): image_logical_path, label_logical_path = map(lambda x: os.path.relpath(x, path), [image_file, label_file]) try: - artifact.add(image_file, logical_path=image_logical_path, metadata={"split": split}) - artifact.add(label_file, logical_path=label_logical_path, metadata={"split": split}) + artifact.add(image_file, logical_path=image_logical_path, metadata={'split': split}) + artifact.add(label_file, logical_path=label_logical_path, metadata={'split': split}) except ValueError as e: logger.error('COMET ERROR: Error adding file to Artifact. Skipping file.') - logger.error(f"COMET ERROR: {e}") + logger.error(f'COMET ERROR: {e}') continue return artifact def upload_dataset_artifact(self): - dataset_name = self.data_dict.get("dataset_name", "yolov5-dataset") - path = str((ROOT / Path(self.data_dict["path"])).resolve()) + dataset_name = self.data_dict.get('dataset_name', 'yolov5-dataset') + path = str((ROOT / Path(self.data_dict['path'])).resolve()) metadata = self.data_dict.copy() - for key in ["train", "val", "test"]: + for key in ['train', 'val', 'test']: split_path = metadata.get(key) if split_path is not None: - metadata[key] = split_path.replace(path, "") + metadata[key] = split_path.replace(path, '') - artifact = comet_ml.Artifact(name=dataset_name, artifact_type="dataset", metadata=metadata) + artifact = comet_ml.Artifact(name=dataset_name, artifact_type='dataset', metadata=metadata) for key in metadata.keys(): - if key in ["train", "val", "test"]: + if key in ['train', 'val', 'test']: if isinstance(self.upload_dataset, str) and (key != self.upload_dataset): continue @@ -352,13 +352,13 @@ class CometLogger: metadata = logged_artifact.metadata data_dict = metadata.copy() - data_dict["path"] = artifact_save_dir + data_dict['path'] = artifact_save_dir - metadata_names = metadata.get("names") + metadata_names = metadata.get('names') if type(metadata_names) == dict: - data_dict["names"] = {int(k): v for k, v in metadata.get("names").items()} + data_dict['names'] = {int(k): v for k, v in metadata.get('names').items()} elif type(metadata_names) == list: - data_dict["names"] = {int(k): v for k, v in zip(range(len(metadata_names)), metadata_names)} + data_dict['names'] = {int(k): v for k, v in zip(range(len(metadata_names)), metadata_names)} else: raise "Invalid 'names' field in dataset yaml file. Please use a list or dictionary" @@ -366,13 +366,13 @@ class CometLogger: return data_dict def update_data_paths(self, data_dict): - path = data_dict.get("path", "") + path = data_dict.get('path', '') - for split in ["train", "val", "test"]: + for split in ['train', 'val', 'test']: if data_dict.get(split): split_path = data_dict.get(split) - data_dict[split] = (f"{path}/{split_path}" if isinstance(split, str) else [ - f"{path}/{x}" for x in split_path]) + data_dict[split] = (f'{path}/{split_path}' if isinstance(split, str) else [ + f'{path}/{x}' for x in split_path]) return data_dict @@ -413,11 +413,11 @@ class CometLogger: def on_train_end(self, files, save_dir, last, best, epoch, results): if self.comet_log_predictions: curr_epoch = self.experiment.curr_epoch - self.experiment.log_asset_data(self.metadata_dict, "image-metadata.json", epoch=curr_epoch) + self.experiment.log_asset_data(self.metadata_dict, 'image-metadata.json', epoch=curr_epoch) for f in files: - self.log_asset(f, metadata={"epoch": epoch}) - self.log_asset(f"{save_dir}/results.csv", metadata={"epoch": epoch}) + self.log_asset(f, metadata={'epoch': epoch}) + self.log_asset(f'{save_dir}/results.csv', metadata={'epoch': epoch}) if not self.opt.evolve: model_path = str(best if best.exists() else last) @@ -481,7 +481,7 @@ class CometLogger: if self.comet_log_confusion_matrix: epoch = self.experiment.curr_epoch class_names = list(self.class_names.values()) - class_names.append("background") + class_names.append('background') num_classes = len(class_names) self.experiment.log_confusion_matrix( @@ -491,7 +491,7 @@ class CometLogger: epoch=epoch, column_label='Actual Category', row_label='Predicted Category', - file_name=f"confusion-matrix-epoch-{epoch}.json", + file_name=f'confusion-matrix-epoch-{epoch}.json', ) def on_fit_epoch_end(self, result, epoch): diff --git a/utils/loggers/comet/comet_utils.py b/utils/loggers/comet/comet_utils.py index 3cbd451..2760076 100644 --- a/utils/loggers/comet/comet_utils.py +++ b/utils/loggers/comet/comet_utils.py @@ -11,28 +11,28 @@ import yaml logger = logging.getLogger(__name__) -COMET_PREFIX = "comet://" -COMET_MODEL_NAME = os.getenv("COMET_MODEL_NAME", "yolov5") -COMET_DEFAULT_CHECKPOINT_FILENAME = os.getenv("COMET_DEFAULT_CHECKPOINT_FILENAME", "last.pt") +COMET_PREFIX = 'comet://' +COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'yolov5') +COMET_DEFAULT_CHECKPOINT_FILENAME = os.getenv('COMET_DEFAULT_CHECKPOINT_FILENAME', 'last.pt') def download_model_checkpoint(opt, experiment): - model_dir = f"{opt.project}/{experiment.name}" + model_dir = f'{opt.project}/{experiment.name}' os.makedirs(model_dir, exist_ok=True) model_name = COMET_MODEL_NAME model_asset_list = experiment.get_model_asset_list(model_name) if len(model_asset_list) == 0: - logger.error(f"COMET ERROR: No checkpoints found for model name : {model_name}") + logger.error(f'COMET ERROR: No checkpoints found for model name : {model_name}') return model_asset_list = sorted( model_asset_list, - key=lambda x: x["step"], + key=lambda x: x['step'], reverse=True, ) - logged_checkpoint_map = {asset["fileName"]: asset["assetId"] for asset in model_asset_list} + logged_checkpoint_map = {asset['fileName']: asset['assetId'] for asset in model_asset_list} resource_url = urlparse(opt.weights) checkpoint_filename = resource_url.query @@ -44,22 +44,22 @@ def download_model_checkpoint(opt, experiment): checkpoint_filename = COMET_DEFAULT_CHECKPOINT_FILENAME if asset_id is None: - logger.error(f"COMET ERROR: Checkpoint {checkpoint_filename} not found in the given Experiment") + logger.error(f'COMET ERROR: Checkpoint {checkpoint_filename} not found in the given Experiment') return try: - logger.info(f"COMET INFO: Downloading checkpoint {checkpoint_filename}") + logger.info(f'COMET INFO: Downloading checkpoint {checkpoint_filename}') asset_filename = checkpoint_filename - model_binary = experiment.get_asset(asset_id, return_type="binary", stream=False) - model_download_path = f"{model_dir}/{asset_filename}" - with open(model_download_path, "wb") as f: + model_binary = experiment.get_asset(asset_id, return_type='binary', stream=False) + model_download_path = f'{model_dir}/{asset_filename}' + with open(model_download_path, 'wb') as f: f.write(model_binary) opt.weights = model_download_path except Exception as e: - logger.warning("COMET WARNING: Unable to download checkpoint from Comet") + logger.warning('COMET WARNING: Unable to download checkpoint from Comet') logger.exception(e) @@ -75,9 +75,9 @@ def set_opt_parameters(opt, experiment): resume_string = opt.resume for asset in asset_list: - if asset["fileName"] == "opt.yaml": - asset_id = asset["assetId"] - asset_binary = experiment.get_asset(asset_id, return_type="binary", stream=False) + if asset['fileName'] == 'opt.yaml': + asset_id = asset['assetId'] + asset_binary = experiment.get_asset(asset_id, return_type='binary', stream=False) opt_dict = yaml.safe_load(asset_binary) for key, value in opt_dict.items(): setattr(opt, key, value) @@ -85,11 +85,11 @@ def set_opt_parameters(opt, experiment): # Save hyperparameters to YAML file # Necessary to pass checks in training script - save_dir = f"{opt.project}/{experiment.name}" + save_dir = f'{opt.project}/{experiment.name}' os.makedirs(save_dir, exist_ok=True) - hyp_yaml_path = f"{save_dir}/hyp.yaml" - with open(hyp_yaml_path, "w") as f: + hyp_yaml_path = f'{save_dir}/hyp.yaml' + with open(hyp_yaml_path, 'w') as f: yaml.dump(opt.hyp, f) opt.hyp = hyp_yaml_path @@ -113,7 +113,7 @@ def check_comet_weights(opt): if opt.weights.startswith(COMET_PREFIX): api = comet_ml.API() resource = urlparse(opt.weights) - experiment_path = f"{resource.netloc}{resource.path}" + experiment_path = f'{resource.netloc}{resource.path}' experiment = api.get(experiment_path) download_model_checkpoint(opt, experiment) return True @@ -140,7 +140,7 @@ def check_comet_resume(opt): if opt.resume.startswith(COMET_PREFIX): api = comet_ml.API() resource = urlparse(opt.resume) - experiment_path = f"{resource.netloc}{resource.path}" + experiment_path = f'{resource.netloc}{resource.path}' experiment = api.get(experiment_path) set_opt_parameters(opt, experiment) download_model_checkpoint(opt, experiment) diff --git a/utils/loggers/comet/hpo.py b/utils/loggers/comet/hpo.py index 7dd5c92..fc49115 100644 --- a/utils/loggers/comet/hpo.py +++ b/utils/loggers/comet/hpo.py @@ -21,7 +21,7 @@ from utils.torch_utils import select_device # Project Configuration config = comet_ml.config.get_config() -COMET_PROJECT_NAME = config.get_string(os.getenv("COMET_PROJECT_NAME"), "comet.project_name", default="yolov5") +COMET_PROJECT_NAME = config.get_string(os.getenv('COMET_PROJECT_NAME'), 'comet.project_name', default='yolov5') def get_args(known=False): @@ -68,30 +68,30 @@ def get_args(known=False): parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use') # Comet Arguments - parser.add_argument("--comet_optimizer_config", type=str, help="Comet: Path to a Comet Optimizer Config File.") - parser.add_argument("--comet_optimizer_id", type=str, help="Comet: ID of the Comet Optimizer sweep.") - parser.add_argument("--comet_optimizer_objective", type=str, help="Comet: Set to 'minimize' or 'maximize'.") - parser.add_argument("--comet_optimizer_metric", type=str, help="Comet: Metric to Optimize.") - parser.add_argument("--comet_optimizer_workers", + parser.add_argument('--comet_optimizer_config', type=str, help='Comet: Path to a Comet Optimizer Config File.') + parser.add_argument('--comet_optimizer_id', type=str, help='Comet: ID of the Comet Optimizer sweep.') + parser.add_argument('--comet_optimizer_objective', type=str, help="Comet: Set to 'minimize' or 'maximize'.") + parser.add_argument('--comet_optimizer_metric', type=str, help='Comet: Metric to Optimize.') + parser.add_argument('--comet_optimizer_workers', type=int, default=1, - help="Comet: Number of Parallel Workers to use with the Comet Optimizer.") + help='Comet: Number of Parallel Workers to use with the Comet Optimizer.') return parser.parse_known_args()[0] if known else parser.parse_args() def run(parameters, opt): - hyp_dict = {k: v for k, v in parameters.items() if k not in ["epochs", "batch_size"]} + hyp_dict = {k: v for k, v in parameters.items() if k not in ['epochs', 'batch_size']} opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve)) - opt.batch_size = parameters.get("batch_size") - opt.epochs = parameters.get("epochs") + opt.batch_size = parameters.get('batch_size') + opt.epochs = parameters.get('epochs') device = select_device(opt.device, batch_size=opt.batch_size) train(hyp_dict, opt, device, callbacks=Callbacks()) -if __name__ == "__main__": +if __name__ == '__main__': opt = get_args(known=True) opt.weights = str(opt.weights) @@ -99,7 +99,7 @@ if __name__ == "__main__": opt.data = str(opt.data) opt.project = str(opt.project) - optimizer_id = os.getenv("COMET_OPTIMIZER_ID") + optimizer_id = os.getenv('COMET_OPTIMIZER_ID') if optimizer_id is None: with open(opt.comet_optimizer_config) as f: optimizer_config = json.load(f) @@ -110,9 +110,9 @@ if __name__ == "__main__": opt.comet_optimizer_id = optimizer.id status = optimizer.status() - opt.comet_optimizer_objective = status["spec"]["objective"] - opt.comet_optimizer_metric = status["spec"]["metric"] + opt.comet_optimizer_objective = status['spec']['objective'] + opt.comet_optimizer_metric = status['spec']['metric'] - logger.info("COMET INFO: Starting Hyperparameter Sweep") + logger.info('COMET INFO: Starting Hyperparameter Sweep') for parameter in optimizer.get_parameters(): - run(parameter["parameters"], opt) + run(parameter['parameters'], opt) diff --git a/utils/loggers/wandb/wandb_utils.py b/utils/loggers/wandb/wandb_utils.py index 238f4ed..c8ab381 100644 --- a/utils/loggers/wandb/wandb_utils.py +++ b/utils/loggers/wandb/wandb_utils.py @@ -1,110 +1,32 @@ -"""Utilities and tools for tracking runs with Weights & Biases.""" +# YOLOv5 🚀 by Ultralytics, GPL-3.0 license + +# WARNING ⚠️ wandb is deprecated and will be removed in future release. +# See supported integrations at https://github.com/ultralytics/yolov5#integrations import logging import os import sys from contextlib import contextmanager from pathlib import Path -from typing import Dict -import yaml -from tqdm import tqdm +from utils.general import LOGGER, colorstr FILE = Path(__file__).resolve() ROOT = FILE.parents[3] # YOLOv5 root directory if str(ROOT) not in sys.path: sys.path.append(str(ROOT)) # add ROOT to PATH - -from utils.dataloaders import LoadImagesAndLabels, img2label_paths -from utils.general import LOGGER, check_dataset, check_file +RANK = int(os.getenv('RANK', -1)) +DEPRECATION_WARNING = f"{colorstr('wandb')}: WARNING ⚠️ wandb is deprecated and will be removed in a future release. " \ + f'See supported integrations at https://github.com/ultralytics/yolov5#integrations.' try: import wandb assert hasattr(wandb, '__version__') # verify package import not local dir + LOGGER.warning(DEPRECATION_WARNING) except (ImportError, AssertionError): wandb = None -RANK = int(os.getenv('RANK', -1)) -WANDB_ARTIFACT_PREFIX = 'wandb-artifact://' - - -def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX): - return from_string[len(prefix):] - - -def check_wandb_config_file(data_config_file): - wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1)) # updated data.yaml path - if Path(wandb_config).is_file(): - return wandb_config - return data_config_file - - -def check_wandb_dataset(data_file): - is_trainset_wandb_artifact = False - is_valset_wandb_artifact = False - if isinstance(data_file, dict): - # In that case another dataset manager has already processed it and we don't have to - return data_file - if check_file(data_file) and data_file.endswith('.yaml'): - with open(data_file, errors='ignore') as f: - data_dict = yaml.safe_load(f) - is_trainset_wandb_artifact = isinstance(data_dict['train'], - str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX) - is_valset_wandb_artifact = isinstance(data_dict['val'], - str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX) - if is_trainset_wandb_artifact or is_valset_wandb_artifact: - return data_dict - else: - return check_dataset(data_file) - - -def get_run_info(run_path): - run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX)) - run_id = run_path.stem - project = run_path.parent.stem - entity = run_path.parent.parent.stem - model_artifact_name = 'run_' + run_id + '_model' - return entity, project, run_id, model_artifact_name - - -def check_wandb_resume(opt): - process_wandb_config_ddp_mode(opt) if RANK not in [-1, 0] else None - if isinstance(opt.resume, str): - if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - if RANK not in [-1, 0]: # For resuming DDP runs - entity, project, run_id, model_artifact_name = get_run_info(opt.resume) - api = wandb.Api() - artifact = api.artifact(entity + '/' + project + '/' + model_artifact_name + ':latest') - modeldir = artifact.download() - opt.weights = str(Path(modeldir) / "last.pt") - return True - return None - - -def process_wandb_config_ddp_mode(opt): - with open(check_file(opt.data), errors='ignore') as f: - data_dict = yaml.safe_load(f) # data dict - train_dir, val_dir = None, None - if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX): - api = wandb.Api() - train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias) - train_dir = train_artifact.download() - train_path = Path(train_dir) / 'data/images/' - data_dict['train'] = str(train_path) - - if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX): - api = wandb.Api() - val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias) - val_dir = val_artifact.download() - val_path = Path(val_dir) / 'data/images/' - data_dict['val'] = str(val_path) - if train_dir or val_dir: - ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml') - with open(ddp_data_path, 'w') as f: - yaml.safe_dump(data_dict, f) - opt.data = ddp_data_path - class WandbLogger(): """Log training runs, datasets, models, and predictions to Weights & Biases. @@ -132,91 +54,33 @@ class WandbLogger(): job_type (str) -- To set the job_type for this run """ - # Temporary-fix - if opt.upload_dataset: - opt.upload_dataset = False - # LOGGER.info("Uploading Dataset functionality is not being supported temporarily due to a bug.") - # Pre-training routine -- self.job_type = job_type - self.wandb, self.wandb_run = wandb, None if not wandb else wandb.run + self.wandb, self.wandb_run = wandb, wandb.run if wandb else None self.val_artifact, self.train_artifact = None, None self.train_artifact_path, self.val_artifact_path = None, None self.result_artifact = None self.val_table, self.result_table = None, None - self.bbox_media_panel_images = [] - self.val_table_path_map = None self.max_imgs_to_log = 16 - self.wandb_artifact_data_dict = None self.data_dict = None - # It's more elegant to stick to 1 wandb.init call, - # but useful config data is overwritten in the WandbLogger's wandb.init call - if isinstance(opt.resume, str): # checks resume from artifact - if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - entity, project, run_id, model_artifact_name = get_run_info(opt.resume) - model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name - assert wandb, 'install wandb to resume wandb runs' - # Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config - self.wandb_run = wandb.init(id=run_id, - project=project, - entity=entity, - resume='allow', - allow_val_change=True) - opt.resume = model_artifact_name - elif self.wandb: + if self.wandb: self.wandb_run = wandb.init(config=opt, - resume="allow", + resume='allow', project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem, entity=opt.entity, name=opt.name if opt.name != 'exp' else None, job_type=job_type, id=run_id, allow_val_change=True) if not wandb.run else wandb.run + if self.wandb_run: if self.job_type == 'Training': - if opt.upload_dataset: - if not opt.resume: - self.wandb_artifact_data_dict = self.check_and_upload_dataset(opt) - if isinstance(opt.data, dict): # This means another dataset manager has already processed the dataset info (e.g. ClearML) # and they will have stored the already processed dict in opt.data self.data_dict = opt.data - elif opt.resume: - # resume from artifact - if isinstance(opt.resume, str) and opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - self.data_dict = dict(self.wandb_run.config.data_dict) - else: # local resume - self.data_dict = check_wandb_dataset(opt.data) - else: - self.data_dict = check_wandb_dataset(opt.data) - self.wandb_artifact_data_dict = self.wandb_artifact_data_dict or self.data_dict - - # write data_dict to config. useful for resuming from artifacts. Do this only when not resuming. - self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict}, allow_val_change=True) self.setup_training(opt) - if self.job_type == 'Dataset Creation': - self.wandb_run.config.update({"upload_dataset": True}) - self.data_dict = self.check_and_upload_dataset(opt) - - def check_and_upload_dataset(self, opt): - """ - Check if the dataset format is compatible and upload it as W&B artifact - - arguments: - opt (namespace)-- Commandline arguments for current run - - returns: - Updated dataset info dictionary where local dataset paths are replaced by WAND_ARFACT_PREFIX links. - """ - assert wandb, 'Install wandb to upload dataset' - config_path = self.log_dataset_artifact(opt.data, opt.single_cls, - 'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem) - with open(config_path, errors='ignore') as f: - wandb_data_dict = yaml.safe_load(f) - return wandb_data_dict - def setup_training(self, opt): """ Setup the necessary processes for training YOLO models: @@ -231,81 +95,18 @@ class WandbLogger(): self.log_dict, self.current_epoch = {}, 0 self.bbox_interval = opt.bbox_interval if isinstance(opt.resume, str): - modeldir, _ = self.download_model_artifact(opt) - if modeldir: - self.weights = Path(modeldir) / "last.pt" + model_dir, _ = self.download_model_artifact(opt) + if model_dir: + self.weights = Path(model_dir) / 'last.pt' config = self.wandb_run.config opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp, opt.imgsz = str( - self.weights), config.save_period, config.batch_size, config.bbox_interval, config.epochs,\ + self.weights), config.save_period, config.batch_size, config.bbox_interval, config.epochs, \ config.hyp, config.imgsz - data_dict = self.data_dict - if self.val_artifact is None: # If --upload_dataset is set, use the existing artifact, don't download - self.train_artifact_path, self.train_artifact = self.download_dataset_artifact( - data_dict.get('train'), opt.artifact_alias) - self.val_artifact_path, self.val_artifact = self.download_dataset_artifact( - data_dict.get('val'), opt.artifact_alias) - if self.train_artifact_path is not None: - train_path = Path(self.train_artifact_path) / 'data/images/' - data_dict['train'] = str(train_path) - if self.val_artifact_path is not None: - val_path = Path(self.val_artifact_path) / 'data/images/' - data_dict['val'] = str(val_path) - - if self.val_artifact is not None: - self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation") - columns = ["epoch", "id", "ground truth", "prediction"] - columns.extend(self.data_dict['names']) - self.result_table = wandb.Table(columns) - self.val_table = self.val_artifact.get("val") - if self.val_table_path_map is None: - self.map_val_table_path() if opt.bbox_interval == -1: self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1 if opt.evolve or opt.noplots: self.bbox_interval = opt.bbox_interval = opt.epochs + 1 # disable bbox_interval - train_from_artifact = self.train_artifact_path is not None and self.val_artifact_path is not None - # Update the the data_dict to point to local artifacts dir - if train_from_artifact: - self.data_dict = data_dict - - def download_dataset_artifact(self, path, alias): - """ - download the model checkpoint artifact if the path starts with WANDB_ARTIFACT_PREFIX - - arguments: - path -- path of the dataset to be used for training - alias (str)-- alias of the artifact to be download/used for training - - returns: - (str, wandb.Artifact) -- path of the downladed dataset and it's corresponding artifact object if dataset - is found otherwise returns (None, None) - """ - if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX): - artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias) - dataset_artifact = wandb.use_artifact(artifact_path.as_posix().replace("\\", "/")) - assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'" - datadir = dataset_artifact.download() - return datadir, dataset_artifact - return None, None - - def download_model_artifact(self, opt): - """ - download the model checkpoint artifact if the resume path starts with WANDB_ARTIFACT_PREFIX - - arguments: - opt (namespace) -- Commandline arguments for this run - """ - if opt.resume.startswith(WANDB_ARTIFACT_PREFIX): - model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest") - assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist' - modeldir = model_artifact.download() - # epochs_trained = model_artifact.metadata.get('epochs_trained') - total_epochs = model_artifact.metadata.get('total_epochs') - is_finished = total_epochs is None - assert not is_finished, 'training is finished, can only resume incomplete runs.' - return modeldir, model_artifact - return None, None def log_model(self, path, opt, epoch, fitness_score, best_model=False): """ @@ -330,192 +131,10 @@ class WandbLogger(): model_artifact.add_file(str(path / 'last.pt'), name='last.pt') wandb.log_artifact(model_artifact, aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else '']) - LOGGER.info(f"Saving model artifact on epoch {epoch + 1}") - - def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False): - """ - Log the dataset as W&B artifact and return the new data file with W&B links - - arguments: - data_file (str) -- the .yaml file with information about the dataset like - path, classes etc. - single_class (boolean) -- train multi-class data as single-class - project (str) -- project name. Used to construct the artifact path - overwrite_config (boolean) -- overwrites the data.yaml file if set to true otherwise creates a new - file with _wandb postfix. Eg -> data_wandb.yaml - - returns: - the new .yaml file with artifact links. it can be used to start training directly from artifacts - """ - upload_dataset = self.wandb_run.config.upload_dataset - log_val_only = isinstance(upload_dataset, str) and upload_dataset == 'val' - self.data_dict = check_dataset(data_file) # parse and check - data = dict(self.data_dict) - nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names']) - names = {k: v for k, v in enumerate(names)} # to index dictionary - - # log train set - if not log_val_only: - self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(data['train'], rect=True, batch_size=1), - names, - name='train') if data.get('train') else None - if data.get('train'): - data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train') - - self.val_artifact = self.create_dataset_table( - LoadImagesAndLabels(data['val'], rect=True, batch_size=1), names, name='val') if data.get('val') else None - if data.get('val'): - data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val') - - path = Path(data_file) - # create a _wandb.yaml file with artifacts links if both train and test set are logged - if not log_val_only: - path = (path.stem if overwrite_config else path.stem + '_wandb') + '.yaml' # updated data.yaml path - path = ROOT / 'data' / path - data.pop('download', None) - data.pop('path', None) - with open(path, 'w') as f: - yaml.safe_dump(data, f) - LOGGER.info(f"Created dataset config file {path}") - - if self.job_type == 'Training': # builds correct artifact pipeline graph - if not log_val_only: - self.wandb_run.log_artifact( - self.train_artifact) # calling use_artifact downloads the dataset. NOT NEEDED! - self.wandb_run.use_artifact(self.val_artifact) - self.val_artifact.wait() - self.val_table = self.val_artifact.get('val') - self.map_val_table_path() - else: - self.wandb_run.log_artifact(self.train_artifact) - self.wandb_run.log_artifact(self.val_artifact) - return path - - def map_val_table_path(self): - """ - Map the validation dataset Table like name of file -> it's id in the W&B Table. - Useful for - referencing artifacts for evaluation. - """ - self.val_table_path_map = {} - LOGGER.info("Mapping dataset") - for i, data in enumerate(tqdm(self.val_table.data)): - self.val_table_path_map[data[3]] = data[0] - - def create_dataset_table(self, dataset: LoadImagesAndLabels, class_to_id: Dict[int, str], name: str = 'dataset'): - """ - Create and return W&B artifact containing W&B Table of the dataset. - - arguments: - dataset -- instance of LoadImagesAndLabels class used to iterate over the data to build Table - class_to_id -- hash map that maps class ids to labels - name -- name of the artifact - - returns: - dataset artifact to be logged or used - """ - # TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging - artifact = wandb.Artifact(name=name, type="dataset") - img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None - img_files = tqdm(dataset.im_files) if not img_files else img_files - for img_file in img_files: - if Path(img_file).is_dir(): - artifact.add_dir(img_file, name='data/images') - labels_path = 'labels'.join(dataset.path.rsplit('images', 1)) - artifact.add_dir(labels_path, name='data/labels') - else: - artifact.add_file(img_file, name='data/images/' + Path(img_file).name) - label_file = Path(img2label_paths([img_file])[0]) - artifact.add_file(str(label_file), name='data/labels/' + - label_file.name) if label_file.exists() else None - table = wandb.Table(columns=["id", "train_image", "Classes", "name"]) - class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()]) - for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)): - box_data, img_classes = [], {} - for cls, *xywh in labels[:, 1:].tolist(): - cls = int(cls) - box_data.append({ - "position": { - "middle": [xywh[0], xywh[1]], - "width": xywh[2], - "height": xywh[3]}, - "class_id": cls, - "box_caption": "%s" % (class_to_id[cls])}) - img_classes[cls] = class_to_id[cls] - boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}} # inference-space - table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), list(img_classes.values()), - Path(paths).name) - artifact.add(table, name) - return artifact - - def log_training_progress(self, predn, path, names): - """ - Build evaluation Table. Uses reference from validation dataset table. - - arguments: - predn (list): list of predictions in the native space in the format - [xmin, ymin, xmax, ymax, confidence, class] - path (str): local path of the current evaluation image - names (dict(int, str)): hash map that maps class ids to labels - """ - class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()]) - box_data = [] - avg_conf_per_class = [0] * len(self.data_dict['names']) - pred_class_count = {} - for *xyxy, conf, cls in predn.tolist(): - if conf >= 0.25: - cls = int(cls) - box_data.append({ - "position": { - "minX": xyxy[0], - "minY": xyxy[1], - "maxX": xyxy[2], - "maxY": xyxy[3]}, - "class_id": cls, - "box_caption": f"{names[cls]} {conf:.3f}", - "scores": { - "class_score": conf}, - "domain": "pixel"}) - avg_conf_per_class[cls] += conf - - if cls in pred_class_count: - pred_class_count[cls] += 1 - else: - pred_class_count[cls] = 1 - - for pred_class in pred_class_count.keys(): - avg_conf_per_class[pred_class] = avg_conf_per_class[pred_class] / pred_class_count[pred_class] - - boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space - id = self.val_table_path_map[Path(path).name] - self.result_table.add_data(self.current_epoch, id, self.val_table.data[id][1], - wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set), - *avg_conf_per_class) + LOGGER.info(f'Saving model artifact on epoch {epoch + 1}') def val_one_image(self, pred, predn, path, names, im): - """ - Log validation data for one image. updates the result Table if validation dataset is uploaded and log bbox media panel - - arguments: - pred (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class] - predn (list): list of predictions in the native space - [xmin, ymin, xmax, ymax, confidence, class] - path (str): local path of the current evaluation image - """ - if self.val_table and self.result_table: # Log Table if Val dataset is uploaded as artifact - self.log_training_progress(predn, path, names) - - if len(self.bbox_media_panel_images) < self.max_imgs_to_log and self.current_epoch > 0: - if self.current_epoch % self.bbox_interval == 0: - box_data = [{ - "position": { - "minX": xyxy[0], - "minY": xyxy[1], - "maxX": xyxy[2], - "maxY": xyxy[3]}, - "class_id": int(cls), - "box_caption": f"{names[int(cls)]} {conf:.3f}", - "scores": { - "class_score": conf}, - "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()] - boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space - self.bbox_media_panel_images.append(wandb.Image(im, boxes=boxes, caption=path.name)) + pass def log(self, log_dict): """ @@ -528,7 +147,7 @@ class WandbLogger(): for key, value in log_dict.items(): self.log_dict[key] = value - def end_epoch(self, best_result=False): + def end_epoch(self): """ commit the log_dict, model artifacts and Tables to W&B and flush the log_dict. @@ -537,31 +156,15 @@ class WandbLogger(): """ if self.wandb_run: with all_logging_disabled(): - if self.bbox_media_panel_images: - self.log_dict["BoundingBoxDebugger"] = self.bbox_media_panel_images try: wandb.log(self.log_dict) except BaseException as e: LOGGER.info( - f"An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}" + f'An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}' ) self.wandb_run.finish() self.wandb_run = None - self.log_dict = {} - self.bbox_media_panel_images = [] - if self.result_artifact: - self.result_artifact.add(self.result_table, 'result') - wandb.log_artifact(self.result_artifact, - aliases=[ - 'latest', 'last', 'epoch ' + str(self.current_epoch), - ('best' if best_result else '')]) - - wandb.log({"evaluation": self.result_table}) - columns = ["epoch", "id", "ground truth", "prediction"] - columns.extend(self.data_dict['names']) - self.result_table = wandb.Table(columns) - self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation") def finish_run(self): """ @@ -572,6 +175,7 @@ class WandbLogger(): with all_logging_disabled(): wandb.log(self.log_dict) wandb.run.finish() + LOGGER.warning(DEPRECATION_WARNING) @contextmanager diff --git a/utils/metrics.py b/utils/metrics.py index c01f823..95f364c 100644 --- a/utils/metrics.py +++ b/utils/metrics.py @@ -28,7 +28,7 @@ def smooth(y, f=0.05): return np.convolve(yp, np.ones(nf) / nf, mode='valid') # y-smoothed -def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=(), eps=1e-16, prefix=""): +def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=(), eps=1e-16, prefix=''): """ Compute the average precision, given the recall and precision curves. Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. # Arguments @@ -194,21 +194,21 @@ class ConfusionMatrix: nc, nn = self.nc, len(names) # number of classes, names sn.set(font_scale=1.0 if nc < 50 else 0.8) # for label size labels = (0 < nn < 99) and (nn == nc) # apply names to ticklabels - ticklabels = (names + ['background']) if labels else "auto" + ticklabels = (names + ['background']) if labels else 'auto' with warnings.catch_warnings(): warnings.simplefilter('ignore') # suppress empty matrix RuntimeWarning: All-NaN slice encountered sn.heatmap(array, ax=ax, annot=nc < 30, annot_kws={ - "size": 8}, + 'size': 8}, cmap='Blues', fmt='.2f', square=True, vmin=0.0, xticklabels=ticklabels, yticklabels=ticklabels).set_facecolor((1, 1, 1)) - ax.set_ylabel('True') + ax.set_xlabel('True') ax.set_ylabel('Predicted') ax.set_title('Confusion Matrix') fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250) @@ -331,7 +331,7 @@ def plot_pr_curve(px, py, ap, save_dir=Path('pr_curve.png'), names=()): ax.set_ylabel('Precision') ax.set_xlim(0, 1) ax.set_ylim(0, 1) - ax.legend(bbox_to_anchor=(1.04, 1), loc="upper left") + ax.legend(bbox_to_anchor=(1.04, 1), loc='upper left') ax.set_title('Precision-Recall Curve') fig.savefig(save_dir, dpi=250) plt.close(fig) @@ -354,7 +354,7 @@ def plot_mc_curve(px, py, save_dir=Path('mc_curve.png'), names=(), xlabel='Confi ax.set_ylabel(ylabel) ax.set_xlim(0, 1) ax.set_ylim(0, 1) - ax.legend(bbox_to_anchor=(1.04, 1), loc="upper left") + ax.legend(bbox_to_anchor=(1.04, 1), loc='upper left') ax.set_title(f'{ylabel}-Confidence Curve') fig.savefig(save_dir, dpi=250) plt.close(fig) diff --git a/utils/plots.py b/utils/plots.py index d2f232d..24c618c 100644 --- a/utils/plots.py +++ b/utils/plots.py @@ -88,7 +88,8 @@ class Annotator: if self.pil or not is_ascii(label): self.draw.rectangle(box, width=self.lw, outline=color) # box if label: - w, h = self.font.getsize(label) # text width, height + w, h = self.font.getsize(label) # text width, height (WARNING: deprecated) in 9.2.0 + # _, _, w, h = self.font.getbbox(label) # text width, height (New) outside = box[1] - h >= 0 # label fits outside box self.draw.rectangle( (box[0], box[1] - h if outside else box[1], box[0] + w + 1, @@ -449,7 +450,7 @@ def imshow_cls(im, labels=None, pred=None, names=None, nmax=25, verbose=False, f plt.savefig(f, dpi=300, bbox_inches='tight') plt.close() if verbose: - LOGGER.info(f"Saving {f}") + LOGGER.info(f'Saving {f}') if labels is not None: LOGGER.info('True: ' + ' '.join(f'{names[i]:3s}' for i in labels[:nmax])) if pred is not None: diff --git a/utils/segment/dataloaders.py b/utils/segment/dataloaders.py index d66b361..097a5d5 100644 --- a/utils/segment/dataloaders.py +++ b/utils/segment/dataloaders.py @@ -95,7 +95,7 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing stride=32, pad=0, min_items=0, - prefix="", + prefix='', downsample_ratio=1, overlap=False, ): @@ -116,7 +116,7 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing shapes = None # MixUp augmentation - if random.random() < hyp["mixup"]: + if random.random() < hyp['mixup']: img, labels, segments = mixup(img, labels, segments, *self.load_mosaic(random.randint(0, self.n - 1))) else: @@ -147,11 +147,11 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing img, labels, segments = random_perspective(img, labels, segments=segments, - degrees=hyp["degrees"], - translate=hyp["translate"], - scale=hyp["scale"], - shear=hyp["shear"], - perspective=hyp["perspective"]) + degrees=hyp['degrees'], + translate=hyp['translate'], + scale=hyp['scale'], + shear=hyp['shear'], + perspective=hyp['perspective']) nl = len(labels) # number of labels if nl: @@ -177,17 +177,17 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing nl = len(labels) # update after albumentations # HSV color-space - augment_hsv(img, hgain=hyp["hsv_h"], sgain=hyp["hsv_s"], vgain=hyp["hsv_v"]) + augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v']) # Flip up-down - if random.random() < hyp["flipud"]: + if random.random() < hyp['flipud']: img = np.flipud(img) if nl: labels[:, 2] = 1 - labels[:, 2] masks = torch.flip(masks, dims=[1]) # Flip left-right - if random.random() < hyp["fliplr"]: + if random.random() < hyp['fliplr']: img = np.fliplr(img) if nl: labels[:, 1] = 1 - labels[:, 1] @@ -251,15 +251,15 @@ class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing # img4, labels4 = replicate(img4, labels4) # replicate # Augment - img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp["copy_paste"]) + img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste']) img4, labels4, segments4 = random_perspective(img4, labels4, segments4, - degrees=self.hyp["degrees"], - translate=self.hyp["translate"], - scale=self.hyp["scale"], - shear=self.hyp["shear"], - perspective=self.hyp["perspective"], + degrees=self.hyp['degrees'], + translate=self.hyp['translate'], + scale=self.hyp['scale'], + shear=self.hyp['shear'], + perspective=self.hyp['perspective'], border=self.mosaic_border) # border to remove return img4, labels4, segments4 diff --git a/utils/segment/loss.py b/utils/segment/loss.py index b45b2c2..2a8a4c6 100644 --- a/utils/segment/loss.py +++ b/utils/segment/loss.py @@ -83,7 +83,7 @@ class ComputeLoss: # Mask regression if tuple(masks.shape[-2:]) != (mask_h, mask_w): # downsample - masks = F.interpolate(masks[None], (mask_h, mask_w), mode="nearest")[0] + masks = F.interpolate(masks[None], (mask_h, mask_w), mode='nearest')[0] marea = xywhn[i][:, 2:].prod(1) # mask width, height normalized mxyxy = xywh2xyxy(xywhn[i] * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=self.device)) for bi in b.unique(): @@ -101,10 +101,10 @@ class ComputeLoss: if self.autobalance: self.balance = [x / self.balance[self.ssi] for x in self.balance] - lbox *= self.hyp["box"] - lobj *= self.hyp["obj"] - lcls *= self.hyp["cls"] - lseg *= self.hyp["box"] / bs + lbox *= self.hyp['box'] + lobj *= self.hyp['obj'] + lcls *= self.hyp['cls'] + lseg *= self.hyp['box'] / bs loss = lbox + lobj + lcls + lseg return loss * bs, torch.cat((lbox, lseg, lobj, lcls)).detach() @@ -112,7 +112,7 @@ class ComputeLoss: def single_mask_loss(self, gt_mask, pred, proto, xyxy, area): # Mask loss for one image pred_mask = (pred @ proto.view(self.nm, -1)).view(-1, *proto.shape[1:]) # (n,32) @ (32,80,80) -> (n,80,80) - loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction="none") + loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction='none') return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean() def build_targets(self, p, targets): diff --git a/utils/segment/metrics.py b/utils/segment/metrics.py index b09ce23..c9f137e 100644 --- a/utils/segment/metrics.py +++ b/utils/segment/metrics.py @@ -21,7 +21,7 @@ def ap_per_class_box_and_mask( pred_cls, target_cls, plot=False, - save_dir=".", + save_dir='.', names=(), ): """ @@ -37,7 +37,7 @@ def ap_per_class_box_and_mask( plot=plot, save_dir=save_dir, names=names, - prefix="Box")[2:] + prefix='Box')[2:] results_masks = ap_per_class(tp_m, conf, pred_cls, @@ -45,21 +45,21 @@ def ap_per_class_box_and_mask( plot=plot, save_dir=save_dir, names=names, - prefix="Mask")[2:] + prefix='Mask')[2:] results = { - "boxes": { - "p": results_boxes[0], - "r": results_boxes[1], - "ap": results_boxes[3], - "f1": results_boxes[2], - "ap_class": results_boxes[4]}, - "masks": { - "p": results_masks[0], - "r": results_masks[1], - "ap": results_masks[3], - "f1": results_masks[2], - "ap_class": results_masks[4]}} + 'boxes': { + 'p': results_boxes[0], + 'r': results_boxes[1], + 'ap': results_boxes[3], + 'f1': results_boxes[2], + 'ap_class': results_boxes[4]}, + 'masks': { + 'p': results_masks[0], + 'r': results_masks[1], + 'ap': results_masks[3], + 'f1': results_masks[2], + 'ap_class': results_masks[4]}} return results @@ -159,8 +159,8 @@ class Metrics: Args: results: Dict{'boxes': Dict{}, 'masks': Dict{}} """ - self.metric_box.update(list(results["boxes"].values())) - self.metric_mask.update(list(results["masks"].values())) + self.metric_box.update(list(results['boxes'].values())) + self.metric_mask.update(list(results['masks'].values())) def mean_results(self): return self.metric_box.mean_results() + self.metric_mask.mean_results() @@ -178,33 +178,33 @@ class Metrics: KEYS = [ - "train/box_loss", - "train/seg_loss", # train loss - "train/obj_loss", - "train/cls_loss", - "metrics/precision(B)", - "metrics/recall(B)", - "metrics/mAP_0.5(B)", - "metrics/mAP_0.5:0.95(B)", # metrics - "metrics/precision(M)", - "metrics/recall(M)", - "metrics/mAP_0.5(M)", - "metrics/mAP_0.5:0.95(M)", # metrics - "val/box_loss", - "val/seg_loss", # val loss - "val/obj_loss", - "val/cls_loss", - "x/lr0", - "x/lr1", - "x/lr2",] + 'train/box_loss', + 'train/seg_loss', # train loss + 'train/obj_loss', + 'train/cls_loss', + 'metrics/precision(B)', + 'metrics/recall(B)', + 'metrics/mAP_0.5(B)', + 'metrics/mAP_0.5:0.95(B)', # metrics + 'metrics/precision(M)', + 'metrics/recall(M)', + 'metrics/mAP_0.5(M)', + 'metrics/mAP_0.5:0.95(M)', # metrics + 'val/box_loss', + 'val/seg_loss', # val loss + 'val/obj_loss', + 'val/cls_loss', + 'x/lr0', + 'x/lr1', + 'x/lr2',] BEST_KEYS = [ - "best/epoch", - "best/precision(B)", - "best/recall(B)", - "best/mAP_0.5(B)", - "best/mAP_0.5:0.95(B)", - "best/precision(M)", - "best/recall(M)", - "best/mAP_0.5(M)", - "best/mAP_0.5:0.95(M)",] + 'best/epoch', + 'best/precision(B)', + 'best/recall(B)', + 'best/mAP_0.5(B)', + 'best/mAP_0.5:0.95(B)', + 'best/precision(M)', + 'best/recall(M)', + 'best/mAP_0.5(M)', + 'best/mAP_0.5:0.95(M)',] diff --git a/utils/segment/plots.py b/utils/segment/plots.py index 9b90900..3ba0976 100644 --- a/utils/segment/plots.py +++ b/utils/segment/plots.py @@ -108,13 +108,13 @@ def plot_images_and_masks(images, targets, masks, paths=None, fname='images.jpg' annotator.im.save(fname) # save -def plot_results_with_masks(file="path/to/results.csv", dir="", best=True): +def plot_results_with_masks(file='path/to/results.csv', dir='', best=True): # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv') save_dir = Path(file).parent if file else Path(dir) fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True) ax = ax.ravel() - files = list(save_dir.glob("results*.csv")) - assert len(files), f"No results.csv files found in {save_dir.resolve()}, nothing to plot." + files = list(save_dir.glob('results*.csv')) + assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.' for f in files: try: data = pd.read_csv(f) @@ -125,19 +125,19 @@ def plot_results_with_masks(file="path/to/results.csv", dir="", best=True): for i, j in enumerate([1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12]): y = data.values[:, j] # y[y == 0] = np.nan # don't show zero values - ax[i].plot(x, y, marker=".", label=f.stem, linewidth=2, markersize=2) + ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=2) if best: # best - ax[i].scatter(index, y[index], color="r", label=f"best:{index}", marker="*", linewidth=3) - ax[i].set_title(s[j] + f"\n{round(y[index], 5)}") + ax[i].scatter(index, y[index], color='r', label=f'best:{index}', marker='*', linewidth=3) + ax[i].set_title(s[j] + f'\n{round(y[index], 5)}') else: # last - ax[i].scatter(x[-1], y[-1], color="r", label="last", marker="*", linewidth=3) - ax[i].set_title(s[j] + f"\n{round(y[-1], 5)}") + ax[i].scatter(x[-1], y[-1], color='r', label='last', marker='*', linewidth=3) + ax[i].set_title(s[j] + f'\n{round(y[-1], 5)}') # if j in [8, 9, 10]: # share train and val loss y axes # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5]) except Exception as e: - print(f"Warning: Plotting error for {f}: {e}") + print(f'Warning: Plotting error for {f}: {e}') ax[1].legend() - fig.savefig(save_dir / "results.png", dpi=200) + fig.savefig(save_dir / 'results.png', dpi=200) plt.close() diff --git a/utils/torch_utils.py b/utils/torch_utils.py index 77549b0..5b67b3f 100644 --- a/utils/torch_utils.py +++ b/utils/torch_utils.py @@ -291,7 +291,7 @@ def model_info(model, verbose=False, imgsz=640): fs = '' name = Path(model.yaml_file).stem.replace('yolov5', 'YOLOv5') if hasattr(model, 'yaml_file') else 'Model' - LOGGER.info(f"{name} summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}") + LOGGER.info(f'{name} summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}') def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416) @@ -342,7 +342,7 @@ def smart_optimizer(model, name='Adam', lr=0.001, momentum=0.9, decay=1e-5): optimizer.add_param_group({'params': g[0], 'weight_decay': decay}) # add g0 with weight_decay optimizer.add_param_group({'params': g[1], 'weight_decay': 0.0}) # add g1 (BatchNorm2d weights) LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__}(lr={lr}) with parameter groups " - f"{len(g[1])} weight(decay=0.0), {len(g[0])} weight(decay={decay}), {len(g[2])} bias") + f'{len(g[1])} weight(decay=0.0), {len(g[0])} weight(decay={decay}), {len(g[2])} bias') return optimizer diff --git a/utils/triton.py b/utils/triton.py index a94ef0a..2592802 100644 --- a/utils/triton.py +++ b/utils/triton.py @@ -21,7 +21,7 @@ class TritonRemoteModel: """ parsed_url = urlparse(url) - if parsed_url.scheme == "grpc": + if parsed_url.scheme == 'grpc': from tritonclient.grpc import InferenceServerClient, InferInput self.client = InferenceServerClient(parsed_url.netloc) # Triton GRPC client @@ -31,7 +31,7 @@ class TritonRemoteModel: def create_input_placeholders() -> typing.List[InferInput]: return [ - InferInput(i['name'], [int(s) for s in i["shape"]], i['datatype']) for i in self.metadata['inputs']] + InferInput(i['name'], [int(s) for s in i['shape']], i['datatype']) for i in self.metadata['inputs']] else: from tritonclient.http import InferenceServerClient, InferInput @@ -43,14 +43,14 @@ class TritonRemoteModel: def create_input_placeholders() -> typing.List[InferInput]: return [ - InferInput(i['name'], [int(s) for s in i["shape"]], i['datatype']) for i in self.metadata['inputs']] + InferInput(i['name'], [int(s) for s in i['shape']], i['datatype']) for i in self.metadata['inputs']] self._create_input_placeholders_fn = create_input_placeholders @property def runtime(self): """Returns the model runtime""" - return self.metadata.get("backend", self.metadata.get("platform")) + return self.metadata.get('backend', self.metadata.get('platform')) def __call__(self, *args, **kwargs) -> typing.Union[torch.Tensor, typing.Tuple[torch.Tensor, ...]]: """ Invokes the model. Parameters can be provided via args or kwargs. @@ -68,14 +68,14 @@ class TritonRemoteModel: def _create_inputs(self, *args, **kwargs): args_len, kwargs_len = len(args), len(kwargs) if not args_len and not kwargs_len: - raise RuntimeError("No inputs provided.") + raise RuntimeError('No inputs provided.') if args_len and kwargs_len: - raise RuntimeError("Cannot specify args and kwargs at the same time") + raise RuntimeError('Cannot specify args and kwargs at the same time') placeholders = self._create_input_placeholders_fn() if args_len: if args_len != len(placeholders): - raise RuntimeError(f"Expected {len(placeholders)} inputs, got {args_len}.") + raise RuntimeError(f'Expected {len(placeholders)} inputs, got {args_len}.') for input, value in zip(placeholders, args): input.set_data_from_numpy(value.cpu().numpy()) else: