Skip to content

GitLab

Commit 17bc28d5 authored by sunxx1's avatar sunxx1
Browse files

Merge branch 'main' into 'main' 

yolov5增加了mpi单机多卡和多机多卡启动方式，其readme文件进行了更新，对maskrcnn的debug输出日志进行了删除，并更新了该模型的readme文件

See merge request dcutoolkit/deeplearing/dlexamples_new!46
parents 7143f128 5a567950
Show whitespace changes
Inline Side-by-side
Showing with 436 additions and 745 deletions
PyTorch/Compute-Vision/Objection/yolov5/tutorial.ipynb
View file @ 17bc28d5
......@@ -15,7 +15,7 @@
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"eb95db7cae194218b3fcefb439b6352f": {
"484511f272e64eab8b42e68dac5f7a66": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
......@@ -28,16 +28,16 @@
"_view_count": null,
"_view_module_version": "1.5.0",
"box_style": "",
"layout": "IPY_MODEL_769ecde6f2e64bacb596ce972f8d3d2d",
"layout": "IPY_MODEL_78cceec059784f2bb36988d3336e4d56",
"_model_module": "@jupyter-widgets/controls",
"children": [
"IPY_MODEL_384a001876054c93b0af45cd1e960bfe",
"IPY_MODEL_dded0aeae74440f7ba2ffa0beb8dd612",
"IPY_MODEL_5296d28be75740b2892ae421bbec3657"
"IPY_MODEL_ab93d8b65c134605934ff9ec5efb1bb6",
"IPY_MODEL_30df865ded4c434191bce772c9a82f3a",
"IPY_MODEL_20cdc61eb3404f42a12b37901b0d85fb"
]
}
},
"769ecde6f2e64bacb596ce972f8d3d2d": {
"78cceec059784f2bb36988d3336e4d56": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -89,13 +89,13 @@
"left": null
}
},
"384a001876054c93b0af45cd1e960bfe": {
"ab93d8b65c134605934ff9ec5efb1bb6": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_9f09facb2a6c4a7096810d327c8b551c",
"style": "IPY_MODEL_2d7239993a9645b09b221405ac682743",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
......@@ -107,16 +107,16 @@
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_25621cff5d16448cb7260e839fd0f543"
"layout": "IPY_MODEL_17b5a87f92104ec7ab96bf507637d0d2"
}
},
"dded0aeae74440f7ba2ffa0beb8dd612": {
"30df865ded4c434191bce772c9a82f3a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "ProgressView",
"style": "IPY_MODEL_0ce7164fc0c74bb9a2b5c7037375a727",
"style": "IPY_MODEL_2358bfb2270247359e94b066b3cc3d1f",
"_dom_classes": [],
"description": "",
"_model_name": "FloatProgressModel",
......@@ -131,31 +131,31 @@
"min": 0,
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_c4c4593c10904cb5b8a5724d60c7e181"
"layout": "IPY_MODEL_3e984405db654b0b83b88b2db08baffd"
}
},
"5296d28be75740b2892ae421bbec3657": {
"20cdc61eb3404f42a12b37901b0d85fb": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_view_name": "HTMLView",
"style": "IPY_MODEL_473371611126476c88d5d42ec7031ed6",
"style": "IPY_MODEL_654d8a19b9f949c6bbdaf8b0875c931e",
"_dom_classes": [],
"description": "",
"_model_name": "HTMLModel",
"placeholder": "​",
"_view_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"value": " 780M/780M [00:11<00:00, 91.9MB/s]",
"value": " 780M/780M [00:33<00:00, 24.4MB/s]",
"_view_count": null,
"_view_module_version": "1.5.0",
"description_tooltip": null,
"_model_module": "@jupyter-widgets/controls",
"layout": "IPY_MODEL_65efdfd0d26c46e79c8c5ff3b77126cc"
"layout": "IPY_MODEL_896030c5d13b415aaa05032818d81a6e"
}
},
"9f09facb2a6c4a7096810d327c8b551c": {
"2d7239993a9645b09b221405ac682743": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
......@@ -170,7 +170,7 @@
"_model_module": "@jupyter-widgets/controls"
}
},
"25621cff5d16448cb7260e839fd0f543": {
"17b5a87f92104ec7ab96bf507637d0d2": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -222,7 +222,7 @@
"left": null
}
},
"0ce7164fc0c74bb9a2b5c7037375a727": {
"2358bfb2270247359e94b066b3cc3d1f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
......@@ -238,7 +238,7 @@
"_model_module": "@jupyter-widgets/controls"
}
},
"c4c4593c10904cb5b8a5724d60c7e181": {
"3e984405db654b0b83b88b2db08baffd": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -290,7 +290,7 @@
"left": null
}
},
"473371611126476c88d5d42ec7031ed6": {
"654d8a19b9f949c6bbdaf8b0875c931e": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
......@@ -305,7 +305,7 @@
"_model_module": "@jupyter-widgets/controls"
}
},
"65efdfd0d26c46e79c8c5ff3b77126cc": {
"896030c5d13b415aaa05032818d81a6e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
......@@ -402,26 +402,27 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "3809e5a9-dd41-4577-fe62-5531abf7cca2"
"outputId": "4d67116a-43e9-4d84-d19e-1edd83f23a04"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone\n",
"!git clone https://github.com/ultralytics/yolov5 # clone repo\n",
"%cd yolov5\n",
"%pip install -qr requirements.txt # install\n",
"%pip install -qr requirements.txt # install dependencies\n",
"\n",
"import torch\n",
"from yolov5 import utils\n",
"display = utils.notebook_init() # checks"
"from IPython.display import Image, clear_output # to display images\n",
"\n",
"clear_output()\n",
"print(f\"Setup complete. Using torch {torch.__version__} ({torch.cuda.get_device_properties(0).name if torch.cuda.is_available() else 'CPU'})\")"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"Setup complete ✅\n"
]
"Setup complete. Using torch 1.9.0+cu102 (Tesla V100-SXM2-16GB)\n"
],
"name": "stdout"
}
]
},
......@@ -437,11 +438,11 @@
"\n",
"```shell\n",
"python detect.py --source 0 # webcam\n",
" img.jpg # image \n",
" vid.mp4 # video\n",
" file.jpg # image \n",
" file.mp4 # video\n",
" path/ # directory\n",
" path/*.jpg # glob\n",
" 'https://youtu.be/Zgi9g1ksQHc' # YouTube\n",
" 'https://youtu.be/NUsoVlDFqZg' # YouTube\n",
" 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream\n",
"```"
]
......@@ -453,28 +454,28 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "8f7e6588-215d-4ebd-93af-88b871e770a7"
"outputId": "8b728908-81ab-4861-edb0-4d0c46c439fb"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
"display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",
"Image(filename='runs/detect/exp/zidane.jpg', width=600)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
"YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.pt'], source=data/images/, imgsz=640, conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False\n",
"YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"Fusing layers... \n",
"Model Summary: 213 layers, 7225885 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.007s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, Done. (0.007s)\n",
"Speed: 0.5ms pre-process, 6.9ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
]
"Model Summary: 224 layers, 7266973 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 fire hydrant, Done. (0.007s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.007s)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n",
"Done. (0.091s)\n"
],
"name": "stdout"
}
]
},
......@@ -504,7 +505,7 @@
"id": "eyTZYGgRjnMc"
},
"source": [
"## COCO val\n",
"## COCO val2017\n",
"Download [COCO val 2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L14) dataset (1GB - 5000 images), and test model accuracy."
]
},
......@@ -516,24 +517,24 @@
"base_uri": "https://localhost:8080/",
"height": 48,
"referenced_widgets": [
"eb95db7cae194218b3fcefb439b6352f",
"769ecde6f2e64bacb596ce972f8d3d2d",
"384a001876054c93b0af45cd1e960bfe",
"dded0aeae74440f7ba2ffa0beb8dd612",
"5296d28be75740b2892ae421bbec3657",
"9f09facb2a6c4a7096810d327c8b551c",
"25621cff5d16448cb7260e839fd0f543",
"0ce7164fc0c74bb9a2b5c7037375a727",
"c4c4593c10904cb5b8a5724d60c7e181",
"473371611126476c88d5d42ec7031ed6",
"65efdfd0d26c46e79c8c5ff3b77126cc"
"484511f272e64eab8b42e68dac5f7a66",
"78cceec059784f2bb36988d3336e4d56",
"ab93d8b65c134605934ff9ec5efb1bb6",
"30df865ded4c434191bce772c9a82f3a",
"20cdc61eb3404f42a12b37901b0d85fb",
"2d7239993a9645b09b221405ac682743",
"17b5a87f92104ec7ab96bf507637d0d2",
"2358bfb2270247359e94b066b3cc3d1f",
"3e984405db654b0b83b88b2db08baffd",
"654d8a19b9f949c6bbdaf8b0875c931e",
"896030c5d13b415aaa05032818d81a6e"
]
},
"outputId": "bcf9a448-1f9b-4a41-ad49-12f181faf05a"
"outputId": "7e6f5c96-c819-43e1-cd03-d3b9878cf8de"
},
"source": [
"# Download COCO val\n",
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n",
"# Download COCO val2017\n",
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017val.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
],
"execution_count": null,
......@@ -542,7 +543,7 @@
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "eb95db7cae194218b3fcefb439b6352f",
"model_id": "484511f272e64eab8b42e68dac5f7a66",
"version_minor": 0,
"version_major": 2
},
......@@ -550,7 +551,9 @@
" 0%| | 0.00/780M [00:00<?, ?B/s]"
]
},
"metadata": {}
"metadata": {
"tags": []
}
}
]
},
......@@ -561,31 +564,30 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "74f1dfa9-6b6d-4b36-f67e-bbae243869f9"
"outputId": "3dd0e2fc-aecf-4108-91b1-6392da1863cb"
},
"source": [
"# Run YOLOv5x on COCO val\n",
"# Run YOLOv5x on COCO val2017\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mval: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True\n",
"YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\u001b[34m\u001b[1mval: \u001b[0mdata=./data/coco.yaml, weights=['yolov5x.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.65, task=val, device=, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=True, project=runs/val, name=exp, exist_ok=False, half=True\n",
"YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5x.pt to yolov5x.pt...\n",
"100% 166M/166M [00:03<00:00, 54.1MB/s]\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v5.0/yolov5x.pt to yolov5x.pt...\n",
"100% 168M/168M [00:08<00:00, 20.6MB/s]\n",
"\n",
"Fusing layers... \n",
"Model Summary: 444 layers, 86705005 parameters, 0 gradients\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2636.64it/s]\n",
"Model Summary: 476 layers, 87730285 parameters, 0 gradients\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupted: 100% 5000/5000 [00:01<00:00, 2749.96it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: ../datasets/coco/val2017.cache\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:12<00:00, 2.17it/s]\n",
" all 5000 36335 0.729 0.63 0.683 0.496\n",
"Speed: 0.1ms pre-process, 4.9ms inference, 1.9ms NMS per image at shape (32, 3, 640, 640)\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:08<00:00, 2.28it/s]\n",
" all 5000 36335 0.746 0.626 0.68 0.49\n",
"Speed: 0.1ms pre-process, 5.1ms inference, 1.6ms NMS per image at shape (32, 3, 640, 640)\n",
"\n",
"Evaluating pycocotools mAP... saving runs/val/exp/yolov5x_predictions.json...\n",
"loading annotations into memory...\n",
......@@ -593,28 +595,29 @@
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=5.15s)\n",
"DONE (t=4.94s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=90.39s).\n",
"DONE (t=83.60s).\n",
"Accumulating evaluation results...\n",
"DONE (t=14.54s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.507\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.689\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.552\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.345\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.559\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.652\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.381\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.630\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.682\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.526\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.732\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.829\n",
"DONE (t=13.22s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.504\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.546\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.351\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.551\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.644\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.382\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.629\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.681\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.524\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.735\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.827\n",
"Results saved to \u001b[1mruns/val/exp\u001b[0m\n"
]
],
"name": "stdout"
}
]
},
......@@ -624,7 +627,7 @@
"id": "rc_KbFk0juX2"
},
"source": [
"## COCO test\n",
"## COCO test-dev2017\n",
"Download [COCO test2017](https://github.com/ultralytics/yolov5/blob/74b34872fdf41941cddcf243951cdb090fbac17b/data/coco.yaml#L15) dataset (7GB - 40,000 images), to test model accuracy on test-dev set (**20,000 images, no labels**). Results are saved to a `*.json` file which should be **zipped** and submitted to the evaluation server at https://competitions.codalab.org/competitions/20794."
]
},
......@@ -635,9 +638,10 @@
},
"source": [
"# Download COCO test-dev2017\n",
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017labels.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip\n",
"!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f -d ../datasets/coco/images"
"torch.hub.download_url_to_file('https://github.com/ultralytics/yolov5/releases/download/v1.0/coco2017labels.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../ && rm tmp.zip # unzip labels\n",
"!f=\"test2017.zip\" && curl http://images.cocodataset.org/zips/$f -o $f && unzip -q $f && rm $f # 7GB, 41k images\n",
"%mv ./test2017 ../coco/images # move to /coco"
],
"execution_count": null,
"outputs": []
......@@ -648,8 +652,8 @@
"id": "29GJXAP_lPrt"
},
"source": [
"# Run YOLOv5x on COCO test\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half --task test"
"# Run YOLOv5s on COCO test-dev2017 using --task test\n",
"!python val.py --weights yolov5s.pt --data coco.yaml --task test"
],
"execution_count": null,
"outputs": []
......@@ -719,7 +723,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "8724d13d-6711-4a12-d96a-1c655e5c3549"
"outputId": "00ea4b14-a75c-44a2-a913-03b431b69de5"
},
"source": [
"# Train YOLOv5s on COCO128 for 3 epochs\n",
......@@ -729,27 +733,27 @@
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, entity=None, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, upload_dataset=False, bbox_interval=-1, save_period=-1, artifact_alias=latest, local_rank=-1, freeze=0\n",
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
"YOLOv5 🚀 v6.0-48-g84a8099 torch 1.10.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"YOLOv5 🚀 v5.0-367-g01cdb76 torch 1.9.0+cu102 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)\n",
"\n",
"\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
"\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.2, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0\n",
"\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
"2021-08-15 14:40:43.449642: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcudart.so.11.0\n",
"\n",
" from n params module arguments \n",
" 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n",
" 0 -1 1 3520 models.common.Focus [3, 32, 3] \n",
" 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
" 2 -1 1 18816 models.common.C3 [64, 64, 1] \n",
" 3 -1 1 73984 models.common.Conv [64, 128, 3, 2] \n",
" 4 -1 2 115712 models.common.C3 [128, 128, 2] \n",
" 4 -1 3 156928 models.common.C3 [128, 128, 3] \n",
" 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n",
" 6 -1 3 625152 models.common.C3 [256, 256, 3] \n",
" 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n",
" 8 -1 1 1182720 models.common.C3 [512, 512, 1] \n",
" 9 -1 1 656896 models.common.SPPF [512, 512, 5] \n",
" 8 -1 1 656896 models.common.SPP [512, 512, [5, 9, 13]] \n",
" 9 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
" 10 -1 1 131584 models.common.Conv [512, 256, 1, 1] \n",
" 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
" 12 [-1, 6] 1 0 models.common.Concat [1] \n",
......@@ -765,121 +769,48 @@
" 22 [-1, 10] 1 0 models.common.Concat [1] \n",
" 23 -1 1 1182720 models.common.C3 [512, 512, 1, False] \n",
" 24 [17, 20, 23] 1 229245 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]\n",
"Model Summary: 270 layers, 7235389 parameters, 7235389 gradients, 16.5 GFLOPs\n",
"Model Summary: 283 layers, 7276605 parameters, 7276605 gradients, 17.1 GFLOPs\n",
"\n",
"Transferred 349/349 items from yolov5s.pt\n",
"Transferred 362/362 items from yolov5s.pt\n",
"Scaled weight_decay = 0.0005\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 57 weight, 60 weight (no decay), 60 bias\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 59 weight, 62 weight (no decay), 62 bias\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv5, but version 0.1.12 is currently installed\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 296.04it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 2440.28it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 302.61it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupted: 100% 128/128 [00:00<?, ?it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 121.58it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 142.55it/s]\n",
"[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
"[W pthreadpool-cpp.cc:90] Warning: Leaking Caffe2 thread-pool after fork. (function pthreadpool)\n",
"Plotting labels... \n",
"\n",
"\u001b[34m\u001b[1mAutoAnchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
"\u001b[34m\u001b[1mautoanchor: \u001b[0mAnalyzing anchors... anchors/target = 4.27, Best Possible Recall (BPR) = 0.9935\n",
"Image sizes 640 train, 640 val\n",
"Using 2 dataloader workers\n",
"Logging results to \u001b[1mruns/train/exp\u001b[0m\n",
"Logging results to runs/train/exp\n",
"Starting training for 3 epochs...\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 0/2 3.62G 0.04621 0.0711 0.02112 203 640: 100% 8/8 [00:04<00:00, 1.99it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.37it/s]\n",
" all 128 929 0.655 0.547 0.622 0.41\n",
" 0/2 3.64G 0.04492 0.0674 0.02213 298 640: 100% 8/8 [00:03<00:00, 2.05it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.70it/s]\n",
" all 128 929 0.686 0.565 0.642 0.421\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 1/2 5.31G 0.04564 0.06898 0.02116 143 640: 100% 8/8 [00:01<00:00, 4.77it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.27it/s]\n",
" all 128 929 0.68 0.554 0.632 0.419\n",
" 1/2 5.04G 0.04403 0.0611 0.01986 232 640: 100% 8/8 [00:01<00:00, 5.59it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.46it/s]\n",
" all 128 929 0.694 0.563 0.654 0.425\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
" 2/2 5.31G 0.04487 0.06883 0.01998 253 640: 100% 8/8 [00:01<00:00, 4.91it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.30it/s]\n",
" all 128 929 0.71 0.544 0.629 0.423\n",
"\n",
"3 epochs completed in 0.003 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
"Optimizer stripped from runs/train/exp/weights/best.pt, 14.9MB\n",
" 2/2 5.04G 0.04616 0.07056 0.02071 214 640: 100% 8/8 [00:01<00:00, 5.94it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.52it/s]\n",
" all 128 929 0.711 0.562 0.66 0.431\n",
"\n",
"Validating runs/train/exp/weights/best.pt...\n",
"Fusing layers... \n",
"Model Summary: 213 layers, 7225885 parameters, 0 gradients, 16.5 GFLOPs\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.04it/s]\n",
" all 128 929 0.71 0.544 0.63 0.423\n",
" person 128 254 0.816 0.669 0.774 0.507\n",
" bicycle 128 6 0.799 0.667 0.614 0.371\n",
" car 128 46 0.803 0.355 0.486 0.209\n",
" motorcycle 128 5 0.704 0.6 0.791 0.583\n",
" airplane 128 6 1 0.795 0.995 0.717\n",
" bus 128 7 0.656 0.714 0.72 0.606\n",
" train 128 3 0.852 1 0.995 0.682\n",
" truck 128 12 0.521 0.25 0.395 0.215\n",
" boat 128 6 0.795 0.333 0.445 0.137\n",
" traffic light 128 14 0.576 0.143 0.24 0.161\n",
" stop sign 128 2 0.636 0.5 0.828 0.713\n",
" bench 128 9 0.972 0.444 0.575 0.25\n",
" bird 128 16 0.939 0.968 0.988 0.645\n",
" cat 128 4 0.984 0.75 0.822 0.694\n",
" dog 128 9 0.888 0.667 0.903 0.54\n",
" horse 128 2 0.689 1 0.995 0.697\n",
" elephant 128 17 0.96 0.882 0.943 0.681\n",
" bear 128 1 0.549 1 0.995 0.995\n",
" zebra 128 4 0.86 1 0.995 0.952\n",
" giraffe 128 9 0.822 0.778 0.905 0.57\n",
" backpack 128 6 1 0.309 0.457 0.195\n",
" umbrella 128 18 0.775 0.576 0.74 0.418\n",
" handbag 128 19 0.628 0.105 0.167 0.111\n",
" tie 128 7 0.96 0.571 0.701 0.441\n",
" suitcase 128 4 1 0.895 0.995 0.621\n",
" frisbee 128 5 0.641 0.8 0.798 0.664\n",
" skis 128 1 0.627 1 0.995 0.497\n",
" snowboard 128 7 0.988 0.714 0.768 0.556\n",
" sports ball 128 6 0.671 0.5 0.579 0.339\n",
" kite 128 10 0.631 0.515 0.598 0.221\n",
" baseball bat 128 4 0.47 0.456 0.277 0.137\n",
" baseball glove 128 7 0.459 0.429 0.334 0.182\n",
" skateboard 128 5 0.7 0.48 0.736 0.548\n",
" tennis racket 128 7 0.559 0.571 0.538 0.315\n",
" bottle 128 18 0.607 0.389 0.484 0.282\n",
" wine glass 128 16 0.722 0.812 0.82 0.385\n",
" cup 128 36 0.881 0.361 0.532 0.312\n",
" fork 128 6 0.384 0.167 0.239 0.191\n",
" knife 128 16 0.908 0.616 0.681 0.443\n",
" spoon 128 22 0.836 0.364 0.536 0.264\n",
" bowl 128 28 0.793 0.536 0.633 0.471\n",
" banana 128 1 0 0 0.142 0.0995\n",
" sandwich 128 2 0 0 0.0951 0.0717\n",
" orange 128 4 1 0 0.67 0.317\n",
" broccoli 128 11 0.345 0.182 0.283 0.243\n",
" carrot 128 24 0.688 0.459 0.612 0.402\n",
" hot dog 128 2 0.424 0.771 0.497 0.473\n",
" pizza 128 5 0.622 1 0.824 0.551\n",
" donut 128 14 0.703 1 0.952 0.853\n",
" cake 128 4 0.733 1 0.945 0.777\n",
" chair 128 35 0.512 0.486 0.488 0.222\n",
" couch 128 6 0.68 0.36 0.746 0.406\n",
" potted plant 128 14 0.797 0.714 0.808 0.482\n",
" bed 128 3 1 0 0.474 0.318\n",
" dining table 128 13 0.852 0.445 0.478 0.315\n",
" toilet 128 2 0.512 0.5 0.554 0.487\n",
" tv 128 2 0.754 1 0.995 0.895\n",
" laptop 128 3 1 0 0.39 0.147\n",
" mouse 128 2 1 0 0.0283 0.0226\n",
" remote 128 8 0.747 0.625 0.636 0.488\n",
" cell phone 128 8 0.555 0.166 0.417 0.222\n",
" microwave 128 3 0.417 1 0.995 0.732\n",
" oven 128 5 0.37 0.4 0.432 0.249\n",
" sink 128 6 0.356 0.167 0.269 0.149\n",
" refrigerator 128 5 0.705 0.8 0.814 0.45\n",
" book 128 29 0.628 0.138 0.298 0.136\n",
" clock 128 9 0.857 0.778 0.893 0.574\n",
" vase 128 2 0.242 1 0.663 0.622\n",
" scissors 128 1 1 0 0.0207 0.00207\n",
" teddy bear 128 21 0.847 0.381 0.622 0.345\n",
" toothbrush 128 5 0.99 0.6 0.662 0.45\n",
"3 epochs completed in 0.005 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.8MB\n",
"Optimizer stripped from runs/train/exp/weights/best.pt, 14.8MB\n",
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
]
],
"name": "stdout"
}
]
},
......@@ -984,7 +915,7 @@
"source": [
"# Reproduce\n",
"for x in 'yolov5s', 'yolov5m', 'yolov5l', 'yolov5x':\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed # speed\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.25 --iou 0.45 # speed\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAP"
],
"execution_count": null,
......@@ -1023,19 +954,19 @@
"%%shell\n",
"export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n",
"rm -rf runs # remove runs/\n",
"for m in yolov5n; do # models\n",
" python train.py --img 64 --batch 32 --weights $m.pt --epochs 1 --device 0 # train pretrained\n",
" python train.py --img 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device 0 # train scratch\n",
"for m in yolov5s; do # models\n",
" python train.py --weights $m.pt --epochs 3 --img 320 --device 0 # train pretrained\n",
" python train.py --weights '' --cfg $m.yaml --epochs 3 --img 320 --device 0 # train scratch\n",
" for d in 0 cpu; do # devices\n",
" python val.py --weights $m.pt --device $d # val official\n",
" python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
" python detect.py --weights $m.pt --device $d # detect official\n",
" python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n",
" python val.py --weights $m.pt --device $d # val official\n",
" python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n",
" done\n",
" python hubconf.py # hub\n",
" python models/yolo.py --cfg $m.yaml # build PyTorch model\n",
" python models/tf.py --weights $m.pt # build TensorFlow model\n",
" python export.py --img 64 --batch 1 --weights $m.pt --include torchscript onnx # export\n",
"python hubconf.py # hub\n",
"python models/yolo.py --cfg $m.yaml # build PyTorch model\n",
"python models/tf.py --weights $m.pt # build TensorFlow model\n",
"python export.py --img 128 --batch 1 --weights $m.pt --include torchscript onnx # export\n",
"done"
],
"execution_count": null,
......@@ -1082,21 +1013,6 @@
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "VTRwsvA9u7ln"
},
"source": [
"# TensorRT \n",
"# https://docs.nvidia.com/deeplearning/tensorrt/install-guide/index.html#installing-pip\n",
"!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com # install\n",
"!python export.py --weights yolov5s.pt --include engine --imgsz 640 640 --device 0 # export\n",
"!python detect.py --weights yolov5s.engine --imgsz 640 640 --device 0 # inference"
],
"execution_count": null,
"outputs": []
}
]
}
\ No newline at end of file
PyTorch/Compute-Vision/Objection/yolov5/utils/__init__.py
View file @ 17bc28d5
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
utils/initialization
"""
def notebook_init(verbose=True):
# Check system software and hardware
print('Checking setup...')
import os
import shutil
from utils.general import check_requirements, emojis, is_colab
from utils.torch_utils import select_device # imports
check_requirements(('psutil', 'IPython'))
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
if verbose:
# System info
# gb = 1 / 1000 ** 3 # bytes to GB
gib = 1 / 1024 ** 3 # bytes to GiB
ram = psutil.virtual_memory().total
total, used, free = shutil.disk_usage("/")
display.clear_output()
s = f'({os.cpu_count()} CPUs, {ram * gib:.1f} GB RAM, {(total - free) * gib:.1f}/{total * gib:.1f} GB disk)'
else:
s = ''
select_device(newline=False)
print(emojis(f'Setup complete ✅ {s}'))
return display
PyTorch/Compute-Vision/Objection/yolov5/utils/activations.py
View file @ 17bc28d5
......@@ -18,8 +18,8 @@ class SiLU(nn.Module): # export-friendly version of nn.SiLU()
class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
@staticmethod
def forward(x):
# return x * F.hardsigmoid(x) # for TorchScript and CoreML
return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0 # for TorchScript, CoreML and ONNX
# return x * F.hardsigmoid(x) # for torchscript and CoreML
return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX
# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
......
PyTorch/Compute-Vision/Objection/yolov5/utils/augmentations.py
View file @ 17bc28d5
......@@ -3,13 +3,14 @@
Image augmentation functions
"""
import logging
import math
import random
import cv2
import numpy as np
from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box
from utils.general import colorstr, segment2box, resample_segments, check_version
from utils.metrics import bbox_ioa
......@@ -19,7 +20,7 @@ class Albumentations:
self.transform = None
try:
import albumentations as A
check_version(A.__version__, '1.0.3', hard=True) # version requirement
check_version(A.__version__, '1.0.3') # version requirement
self.transform = A.Compose([
A.Blur(p=0.01),
......@@ -31,11 +32,11 @@ class Albumentations:
A.ImageCompression(quality_lower=75, p=0.0)],
bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
except ImportError: # package not installed, skip
pass
except Exception as e:
LOGGER.info(colorstr('albumentations: ') + f'{e}')
logging.info(colorstr('albumentations: ') + f'{e}')
def __call__(self, im, labels, p=1.0):
if self.transform and random.random() < p:
......@@ -123,7 +124,7 @@ def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleF
def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
border=(0, 0)):
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
# torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
# targets = [cls, xyxy]
height = im.shape[0] + border[0] * 2 # shape(h,w,c)
......@@ -269,7 +270,7 @@ def mixup(im, labels, im2, labels2):
return im, labels
def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
......
PyTorch/Compute-Vision/Objection/yolov5/utils/autoanchor.py
View file @ 17bc28d5
......@@ -10,9 +10,7 @@ import torch
import yaml
from tqdm import tqdm
from utils.general import LOGGER, colorstr, emojis
PREFIX = colorstr('AutoAnchor: ')
from utils.general import colorstr
def check_anchor_order(m):
......@@ -21,12 +19,14 @@ def check_anchor_order(m):
da = a[-1] - a[0] # delta a
ds = m.stride[-1] - m.stride[0] # delta s
if da.sign() != ds.sign(): # same order
LOGGER.info(f'{PREFIX}Reversing anchor order')
print('Reversing anchor order')
m.anchors[:] = m.anchors.flip(0)
def check_anchors(dataset, model, thr=4.0, imgsz=640):
# Check anchor fit to data, recompute if necessary
prefix = colorstr('autoanchor: ')
print(f'\n{prefix}Analyzing anchors... ', end='')
m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
......@@ -34,32 +34,31 @@ def check_anchors(dataset, model, thr=4.0, imgsz=640):
def metric(k): # compute metric
r = wh[:, None] / k[None]
x = torch.min(r, 1 / r).min(2)[0] # ratio metric
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
best = x.max(1)[0] # best_x
aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold
bpr = (best > 1 / thr).float().mean() # best possible recall
aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold
bpr = (best > 1. / thr).float().mean() # best possible recall
return bpr, aat
anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors
bpr, aat = metric(anchors.cpu().view(-1, 2))
s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). '
if bpr > 0.98: # threshold to recompute
LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset ✅'))
else:
LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...'))
print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
if bpr < 0.98: # threshold to recompute
print('. Attempting to improve anchors, please wait...')
na = m.anchors.numel() // 2 # number of anchors
try:
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
except Exception as e:
LOGGER.info(f'{PREFIX}ERROR: {e}')
print(f'{prefix}ERROR: {e}')
new_bpr = metric(anchors)[0]
if new_bpr > bpr: # replace anchors
anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
check_anchor_order(m)
LOGGER.info(f'{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
else:
LOGGER.info(f'{PREFIX}Original anchors better than new anchors. Proceeding with original anchors.')
print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
print('') # newline
def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
......@@ -81,11 +80,12 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
"""
from scipy.cluster.vq import kmeans
thr = 1 / thr
thr = 1. / thr
prefix = colorstr('autoanchor: ')
def metric(k, wh): # compute metrics
r = wh[:, None] / k[None]
x = torch.min(r, 1 / r).min(2)[0] # ratio metric
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
# x = wh_iou(wh, torch.tensor(k)) # iou metric
return x, x.max(1)[0] # x, best_x
......@@ -93,17 +93,15 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
_, best = metric(torch.tensor(k, dtype=torch.float32), wh)
return (best * (best > thr).float()).mean() # fitness
def print_results(k, verbose=True):
def print_results(k):
k = k[np.argsort(k.prod(1))] # sort small to large
x, best = metric(k, wh0)
bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr
s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \
f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \
f'past_thr={x[x > thr].mean():.3f}-mean: '
print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
for i, x in enumerate(k):
s += '%i,%i, ' % (round(x[0]), round(x[1]))
if verbose:
LOGGER.info(s[:-2])
print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg
return k
if isinstance(dataset, str): # *.yaml file
......@@ -119,19 +117,19 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
# Filter
i = (wh0 < 3.0).any(1).sum()
if i:
LOGGER.info(f'{PREFIX}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
# wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
# Kmeans calculation
LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...')
print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
s = wh.std(0) # sigmas for whitening
k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
assert len(k) == n, f'{PREFIX}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
assert len(k) == n, f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
k *= s
wh = torch.tensor(wh, dtype=torch.float32) # filtered
wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
k = print_results(k, verbose=False)
k = print_results(k)
# Plot
# k, d = [None] * 20, [None] * 20
......@@ -148,7 +146,7 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
# Evolve
npr = np.random
f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
pbar = tqdm(range(gen), desc=f'{PREFIX}Evolving anchors with Genetic Algorithm:') # progress bar
pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar
for _ in pbar:
v = np.ones(sh)
while (v == 1).all(): # mutate until a change occurs (prevent duplicates)
......@@ -157,8 +155,8 @@ def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen
fg = anchor_fitness(kg)
if fg > f:
f, k = fg, kg.copy()
pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
if verbose:
print_results(k, verbose)
print_results(k)
return print_results(k)
PyTorch/Compute-Vision/Objection/yolov5/utils/autobatch.py deleted 100644 → 0
View file @ 7143f128
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Auto-batch utils
"""
from copy import deepcopy
import numpy as np
import torch
from torch.cuda import amp
from utils.general import LOGGER, colorstr
from utils.torch_utils import profile
def check_train_batch_size(model, imgsz=640):
# Check YOLOv5 training batch size
with amp.autocast():
return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size
def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
# Automatically estimate best batch size to use `fraction` of available CUDA memory
# Usage:
# import torch
# from utils.autobatch import autobatch
# model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)
# print(autobatch(model))
prefix = colorstr('AutoBatch: ')
LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}')
device = next(model.parameters()).device # get model device
if device.type == 'cpu':
LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}')
return batch_size
d = str(device).upper() # 'CUDA:0'
properties = torch.cuda.get_device_properties(device) # device properties
t = properties.total_memory / 1024 ** 3 # (GiB)
r = torch.cuda.memory_reserved(device) / 1024 ** 3 # (GiB)
a = torch.cuda.memory_allocated(device) / 1024 ** 3 # (GiB)
f = t - (r + a) # free inside reserved
LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free')
batch_sizes = [1, 2, 4, 8, 16]
try:
img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
y = profile(img, model, n=3, device=device)
except Exception as e:
LOGGER.warning(f'{prefix}{e}')
y = [x[2] for x in y if x] # memory [2]
batch_sizes = batch_sizes[:len(y)]
p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit
b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size)
LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)')
return b
PyTorch/Compute-Vision/Objection/yolov5/utils/callbacks.py
View file @ 17bc28d5
......@@ -9,9 +9,8 @@ class Callbacks:
Handles all registered callbacks for YOLOv5 Hooks
"""
def __init__(self):
# Define the available callbacks
self._callbacks = {
_callbacks = {
'on_pretrain_routine_start': [],
'on_pretrain_routine_end': [],
......@@ -32,7 +31,7 @@ class Callbacks:
'on_fit_epoch_end': [], # fit = train + val
'on_model_save': [],
'on_train_end': [],
'on_params_update': [],
'teardown': [],
}
......
PyTorch/Compute-Vision/Objection/yolov5/utils/datasets.py
View file @ 17bc28d5
......@@ -6,13 +6,13 @@ Dataloaders and dataset utils
import glob
import hashlib
import json
import math
import logging
import os
import random
import shutil
import time
from itertools import repeat
from multiprocessing.pool import Pool, ThreadPool
from multiprocessing.pool import ThreadPool, Pool
from pathlib import Path
from threading import Thread
from zipfile import ZipFile
......@@ -22,20 +22,20 @@ import numpy as np
import torch
import torch.nn.functional as F
import yaml
from PIL import ExifTags, Image, ImageOps
from torch.utils.data import DataLoader, Dataset, dataloader, distributed
from PIL import Image, ExifTags
from torch.utils.data import Dataset
from tqdm import tqdm
from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective
from utils.general import (LOGGER, NUM_THREADS, check_dataset, check_requirements, check_yaml, clean_str,
segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn)
from utils.general import check_dataset, check_requirements, check_yaml, clean_str, segments2boxes, \
xywh2xyxy, xywhn2xyxy, xyxy2xywhn, xyn2xy
from utils.torch_utils import torch_distributed_zero_first
# Parameters
HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
IMG_FORMATS = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo'] # acceptable image suffixes
VID_FORMATS = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes
WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1)) # DPP
NUM_THREADS = min(8, os.cpu_count()) # number of multiprocessing threads
# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
......@@ -69,7 +69,7 @@ def exif_size(img):
def exif_transpose(image):
"""
Transpose a PIL image accordingly if it has an EXIF Orientation tag.
Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose()
From https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py
:param image: The image to transpose.
:return: An image.
......@@ -93,15 +93,13 @@ def exif_transpose(image):
def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0,
rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix='', shuffle=False):
if rect and shuffle:
LOGGER.warning('WARNING: --rect is incompatible with DataLoader shuffle, setting shuffle=False')
shuffle = False
with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix=''):
# Make sure only the first process in DDP process the dataset first, and the following others can use the cache
with torch_distributed_zero_first(rank):
dataset = LoadImagesAndLabels(path, imgsz, batch_size,
augment=augment, # augmentation
hyp=hyp, # hyperparameters
rect=rect, # rectangular batches
augment=augment, # augment images
hyp=hyp, # augmentation hyperparameters
rect=rect, # rectangular training
cache_images=cache,
single_cls=single_cls,
stride=int(stride),
......@@ -110,19 +108,20 @@ def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=Non
prefix=prefix)
batch_size = min(batch_size, len(dataset))
nw = min([os.cpu_count() // WORLD_SIZE, batch_size if batch_size > 1 else 0, workers]) # number of workers
sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates
return loader(dataset,
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, workers]) # number of workers
sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None
loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader
# Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader()
dataloader = loader(dataset,
batch_size=batch_size,
shuffle=shuffle and sampler is None,
num_workers=nw,
sampler=sampler,
pin_memory=True,
collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn), dataset
collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn)
return dataloader, dataset
class InfiniteDataLoader(dataloader.DataLoader):
class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
""" Dataloader that reuses workers
Uses same syntax as vanilla DataLoader
......@@ -141,7 +140,7 @@ class InfiniteDataLoader(dataloader.DataLoader):
yield next(self.iterator)
class _RepeatSampler:
class _RepeatSampler(object):
""" Sampler that repeats forever
Args:
......@@ -200,7 +199,7 @@ class LoadImages:
# Read video
self.mode = 'video'
ret_val, img0 = self.cap.read()
while not ret_val:
if not ret_val:
self.count += 1
self.cap.release()
if self.count == self.nf: # last video
......@@ -211,14 +210,14 @@ class LoadImages:
ret_val, img0 = self.cap.read()
self.frame += 1
s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: ', end='')
else:
# Read image
self.count += 1
img0 = cv2.imread(path) # BGR
assert img0 is not None, f'Image Not Found {path}'
s = f'image {self.count}/{self.nf} {path}: '
assert img0 is not None, 'Image Not Found ' + path
print(f'image {self.count}/{self.nf} {path}: ', end='')
# Padded resize
img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]
......@@ -227,7 +226,7 @@ class LoadImages:
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return path, img, img0, self.cap, s
return path, img, img0, self.cap
def new_video(self, path):
self.frame = 0
......@@ -265,7 +264,7 @@ class LoadWebcam: # for inference
# Print
assert ret_val, f'Camera Error {self.pipe}'
img_path = 'webcam.jpg'
s = f'webcam {self.count}: '
print(f'webcam {self.count}: ', end='')
# Padded resize
img = letterbox(img0, self.img_size, stride=self.stride)[0]
......@@ -274,7 +273,7 @@ class LoadWebcam: # for inference
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return img_path, img, img0, None, s
return img_path, img, img0, None
def __len__(self):
return 0
......@@ -288,7 +287,7 @@ class LoadStreams:
self.stride = stride
if os.path.isfile(sources):
with open(sources) as f:
with open(sources, 'r') as f:
sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
else:
sources = [sources]
......@@ -299,31 +298,30 @@ class LoadStreams:
self.auto = auto
for i, s in enumerate(sources): # index, source
# Start thread to read frames from video stream
st = f'{i + 1}/{n}: {s}... '
print(f'{i + 1}/{n}: {s}... ', end='')
if 'youtube.com/' in s or 'youtu.be/' in s: # if source is YouTube video
check_requirements(('pafy', 'youtube_dl'))
import pafy
s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL
s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
cap = cv2.VideoCapture(s)
assert cap.isOpened(), f'{st}Failed to open {s}'
assert cap.isOpened(), f'Failed to open {s}'
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan
self.fps[i] = max(cap.get(cv2.CAP_PROP_FPS) % 100, 0) or 30.0 # 30 FPS fallback
self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback
_, 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)")
print(f" success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
self.threads[i].start()
LOGGER.info('') # newline
print('') # newline
# check for common shapes
s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
if not self.rect:
LOGGER.warning('WARNING: Stream shapes differ. For optimal performance supply similarly-shaped streams.')
print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
def update(self, i, cap, stream):
# Read stream `i` frames in daemon thread
......@@ -337,8 +335,8 @@ class LoadStreams:
if success:
self.imgs[i] = im
else:
LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.')
self.imgs[i] = np.zeros_like(self.imgs[i])
print('WARNING: Video stream unresponsive, please check your IP camera connection.')
self.imgs[i] *= 0
cap.open(stream) # re-open stream if signal was lost
time.sleep(1 / self.fps[i]) # wait time
......@@ -363,7 +361,7 @@ class LoadStreams:
img = img[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW
img = np.ascontiguousarray(img)
return self.sources, img, img0, None, ''
return self.sources, img, img0, None
def __len__(self):
return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years
......@@ -377,7 +375,7 @@ def img2label_paths(img_paths):
class LoadImagesAndLabels(Dataset):
# YOLOv5 train_loader/val_loader, loads images and labels for training and validation
cache_version = 0.6 # dataset labels *.cache version
cache_version = 0.5 # dataset labels *.cache version
def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
......@@ -398,17 +396,17 @@ class LoadImagesAndLabels(Dataset):
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / '**' / '*.*'), recursive=True)
# f = list(p.rglob('*.*')) # pathlib
# f = list(p.rglob('**/*.*')) # pathlib
elif p.is_file(): # file
with open(p) as t:
with open(p, 'r') as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path
# f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise Exception(f'{prefix}{p} does not exist')
self.img_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib
self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS])
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats]) # pathlib
assert self.img_files, f'{prefix}No images found'
except Exception as e:
raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
......@@ -429,7 +427,7 @@ class LoadImagesAndLabels(Dataset):
d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
tqdm(None, desc=prefix + d, total=n, initial=n) # display cache results
if cache['msgs']:
LOGGER.info('\n'.join(cache['msgs'])) # display warnings
logging.info('\n'.join(cache['msgs'])) # display warnings
assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
# Read cache
......@@ -439,6 +437,10 @@ class LoadImagesAndLabels(Dataset):
self.shapes = np.array(shapes, dtype=np.float64)
self.img_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
if single_cls:
for x in self.labels:
x[:, 0] = 0
n = len(shapes) # number of images
bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
nb = bi[-1] + 1 # number of batches
......@@ -446,20 +448,6 @@ class LoadImagesAndLabels(Dataset):
self.n = n
self.indices = range(n)
# Update labels
include_class = [] # filter labels to include only these classes (optional)
include_class_array = np.array(include_class).reshape(1, -1)
for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
if include_class:
j = (label[:, 0:1] == include_class_array).any(1)
self.labels[i] = label[j]
if segment:
self.segments[i] = segment[j]
if single_cls: # single-class training, merge all classes into 0
self.labels[i][:, 0] = 0
if segment:
self.segments[i][:, 0] = 0
# Rectangular Training
if self.rect:
# Sort by aspect ratio
......@@ -527,9 +515,9 @@ class LoadImagesAndLabels(Dataset):
pbar.close()
if msgs:
LOGGER.info('\n'.join(msgs))
logging.info('\n'.join(msgs))
if nf == 0:
LOGGER.warning(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
logging.info(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
x['hash'] = get_hash(self.label_files + self.img_files)
x['results'] = nf, nm, ne, nc, len(self.img_files)
x['msgs'] = msgs # warnings
......@@ -537,9 +525,9 @@ class LoadImagesAndLabels(Dataset):
try:
np.save(path, x) # save cache for next time
path.with_suffix('.cache.npy').rename(path) # remove .npy suffix
LOGGER.info(f'{prefix}New cache created: {path}')
logging.info(f'{prefix}New cache created: {path}')
except Exception as e:
LOGGER.warning(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # not writeable
logging.info(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # path not writeable
return x
def __len__(self):
......@@ -612,7 +600,6 @@ class LoadImagesAndLabels(Dataset):
# Cutouts
# labels = cutout(img, labels, p=0.5)
# nl = len(labels) # update after cutout
labels_out = torch.zeros((nl, 6))
if nl:
......@@ -637,13 +624,13 @@ class LoadImagesAndLabels(Dataset):
n = len(shapes) // 4
img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]])
wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]])
s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]]) # scale
ho = torch.tensor([[0., 0, 0, 1, 0, 0]])
wo = torch.tensor([[0., 0, 1, 0, 0, 0]])
s = torch.tensor([[1, 1, .5, .5, .5, .5]]) # scale
for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW
i *= 4
if random.random() < 0.5:
im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear', align_corners=False)[
im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[
0].type(img[i].type())
l = label[i]
else:
......@@ -669,7 +656,7 @@ def load_image(self, i):
else: # read image
path = self.img_files[i]
im = cv2.imread(path) # BGR
assert im is not None, f'Image Not Found {path}'
assert im is not None, 'Image Not Found ' + path
h0, w0 = im.shape[:2] # orig hw
r = self.img_size / max(h0, w0) # ratio
if r != 1: # if sizes are not equal
......@@ -684,7 +671,7 @@ def load_mosaic(self, index):
# YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
labels4, segments4 = [], []
s = self.img_size
yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y
yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y
indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices
random.shuffle(indices)
for i, index in enumerate(indices):
......@@ -770,7 +757,7 @@ def load_mosaic9(self, index):
c = s - w, s + h0 - hp - h, s, s + h0 - hp
padx, pady = c[:2]
x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords
x1, y1, x2, y2 = [max(x, 0) for x in c] # allocate coords
# Labels
labels, segments = self.labels[index].copy(), self.segments[index].copy()
......@@ -785,7 +772,7 @@ def load_mosaic9(self, index):
hp, wp = h, w # height, width previous
# Offset
yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border) # mosaic center x, y
yc, xc = [int(random.uniform(0, s)) for _ in self.mosaic_border] # mosaic center x, y
img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
# Concat/clip labels
......@@ -841,7 +828,7 @@ def extract_boxes(path='../datasets/coco128'): # from utils.datasets import *;
# labels
lb_file = Path(img2label_paths([str(im_file)])[0])
if Path(lb_file).exists():
with open(lb_file) as f:
with open(lb_file, 'r') as f:
lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels
for j, x in enumerate(lb):
......@@ -869,7 +856,7 @@ def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annota
annotated_only: Only use images with an annotated txt file
"""
path = Path(path) # images dir
files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS) # image files only
files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in IMG_FORMATS], []) # image files only
n = len(files) # number of files
random.seed(0) # for reproducibility
indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split
......@@ -899,30 +886,24 @@ def verify_image_label(args):
with open(im_file, 'rb') as f:
f.seek(-2, 2)
if f.read() != b'\xff\xd9': # corrupt JPEG
ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100)
msg = f'{prefix}WARNING: {im_file}: corrupt JPEG restored and saved'
Image.open(im_file).save(im_file, format='JPEG', subsampling=0, quality=100) # re-save image
msg = f'{prefix}WARNING: corrupt JPEG restored and saved {im_file}'
# verify labels
if os.path.isfile(lb_file):
nf = 1 # label found
with open(lb_file) as f:
with open(lb_file, 'r') as f:
l = [x.split() for x in f.read().strip().splitlines() if len(x)]
if any([len(x) > 8 for x in l]): # is segment
classes = np.array([x[0] for x in l], dtype=np.float32)
segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l] # (cls, xy1...)
l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh)
l = np.array(l, dtype=np.float32)
nl = len(l)
if nl:
assert l.shape[1] == 5, f'labels require 5 columns, {l.shape[1]} columns detected'
assert (l >= 0).all(), f'negative label values {l[l < 0]}'
assert (l[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {l[:, 1:][l[:, 1:] > 1]}'
_, i = np.unique(l, axis=0, return_index=True)
if len(i) < nl: # duplicate row check
l = l[i] # remove duplicates
if segments:
segments = segments[i]
msg = f'{prefix}WARNING: {im_file}: {nl - len(i)} duplicate labels removed'
if len(l):
assert l.shape[1] == 5, 'labels require 5 columns each'
assert (l >= 0).all(), 'negative labels'
assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels'
assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels'
else:
ne = 1 # label empty
l = np.zeros((0, 5), dtype=np.float32)
......@@ -932,7 +913,7 @@ def verify_image_label(args):
return im_file, l, shape, segments, nm, nf, ne, nc, msg
except Exception as e:
nc = 1
msg = f'{prefix}WARNING: {im_file}: ignoring corrupt image/label: {e}'
msg = f'{prefix}WARNING: Ignoring corrupted image and/or label {im_file}: {e}'
return [None, None, None, None, nm, nf, ne, nc, msg]
......@@ -949,7 +930,7 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profil
def round_labels(labels):
# Update labels to integer class and 6 decimal place floats
return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels]
return [[int(c), *[round(x, 4) for x in points]] for c, *points in labels]
def unzip(path):
# Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
......@@ -969,14 +950,14 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profil
r = max_dim / max(im.height, im.width) # ratio
if r < 1.0: # image too large
im = im.resize((int(im.width * r), int(im.height * r)))
im.save(f_new, 'JPEG', quality=75, optimize=True) # save
im.save(f_new, quality=75) # save
except Exception as e: # use OpenCV
print(f'WARNING: HUB ops PIL failure {f}: {e}')
im = cv2.imread(f)
im_height, im_width = im.shape[:2]
r = max_dim / max(im_height, im_width) # ratio
if r < 1.0: # image too large
im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA)
im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_LINEAR)
cv2.imwrite(str(f_new), im)
zipped, data_dir, yaml_path = unzip(Path(path))
......@@ -1024,7 +1005,7 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profil
with open(file, 'w') as f:
json.dump(stats, f) # save stats *.json
t2 = time.time()
with open(file) as f:
with open(file, 'r') as f:
x = json.load(f) # load hyps dict
print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
......
PyTorch/Compute-Vision/Objection/yolov5/utils/downloads.py
View file @ 17bc28d5
......@@ -49,12 +49,9 @@ def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads i
name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc.
if str(file).startswith(('http:/', 'https:/')): # download
url = str(file).replace(':/', '://') # Pathlib turns :// -> :/
file = name.split('?')[0] # parse authentication https://url.com/file.txt?auth...
if Path(file).is_file():
print(f'Found {url} locally at {file}') # file already exists
else:
safe_download(file=file, url=url, min_bytes=1E5)
return file
name = name.split('?')[0] # parse authentication https://url.com/file.txt?auth...
safe_download(file=name, url=url, min_bytes=1E5)
return name
# GitHub assets
file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required)
......@@ -63,12 +60,12 @@ def attempt_download(file, repo='ultralytics/yolov5'): # from utils.downloads i
assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
tag = response['tag_name'] # i.e. 'v1.0'
except: # fallback plan
assets = ['yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
'yolov5n6.pt', 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
assets = ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
try:
tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
except:
tag = 'v6.0' # current release
tag = 'v5.0' # current release
if name in assets:
safe_download(file,
......
PyTorch/Compute-Vision/Objection/yolov5/utils/flask_rest_api/restapi.py
View file @ 17bc28d5
......@@ -5,8 +5,8 @@ import argparse
import io
import torch
from flask import Flask, request
from PIL import Image
from flask import Flask, request
app = Flask(__name__)
......
PyTorch/Compute-Vision/Objection/yolov5/utils/general.py
View file @ 17bc28d5
......@@ -11,7 +11,6 @@ import os
import platform
import random
import re
import shutil
import signal
import time
import urllib
......@@ -33,38 +32,14 @@ from utils.downloads import gsutil_getsize
from utils.metrics import box_iou, fitness
# Settings
FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
NUM_THREADS = min(8, max(1, os.cpu_count() - 1)) # number of YOLOv5 multiprocessing threads
torch.set_printoptions(linewidth=320, precision=5, profile='long')
np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
pd.options.display.max_columns = 10
cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
os.environ['NUMEXPR_MAX_THREADS'] = str(NUM_THREADS) # NumExpr max threads
def is_kaggle():
# Is environment a Kaggle Notebook?
try:
assert os.environ.get('PWD') == '/kaggle/working'
assert os.environ.get('KAGGLE_URL_BASE') == 'https://www.kaggle.com'
return True
except AssertionError:
return False
os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8)) # NumExpr max threads
def set_logging(name=None, verbose=True):
# Sets level and returns logger
if is_kaggle():
for h in logging.root.handlers:
logging.root.removeHandler(h) # remove all handlers associated with the root logger object
rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings
logging.basicConfig(format="%(message)s", level=logging.INFO if (verbose and rank in (-1, 0)) else logging.WARNING)
return logging.getLogger(name)
LOGGER = set_logging(__name__) # define globally (used in train.py, val.py, detect.py, etc.)
FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
class Profile(contextlib.ContextDecorator):
......@@ -96,19 +71,6 @@ class Timeout(contextlib.ContextDecorator):
return True
class WorkingDirectory(contextlib.ContextDecorator):
# Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager
def __init__(self, new_dir):
self.dir = new_dir # new dir
self.cwd = Path.cwd().resolve() # current dir
def __enter__(self):
os.chdir(self.dir)
def __exit__(self, exc_type, exc_val, exc_tb):
os.chdir(self.cwd)
def try_except(func):
# try-except function. Usage: @try_except decorator
def handler(*args, **kwargs):
......@@ -125,9 +87,15 @@ def methods(instance):
return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")]
def set_logging(rank=-1, verbose=True):
logging.basicConfig(
format="%(message)s",
level=logging.INFO if (verbose and rank in [-1, 0]) else logging.WARN)
def print_args(name, opt):
# Print argparser arguments
LOGGER.info(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
print(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
def init_seeds(seed=0):
......@@ -140,11 +108,6 @@ def init_seeds(seed=0):
cudnn.benchmark, cudnn.deterministic = (False, True) if seed == 0 else (True, False)
def intersect_dicts(da, db, exclude=()):
# Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
def get_latest_run(search_dir='.'):
# Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
......@@ -173,7 +136,7 @@ def is_writeable(dir, test=False):
pass
file.unlink() # remove file
return True
except OSError:
except IOError:
return False
else: # method 2
return os.access(dir, os.R_OK) # possible issues on Windows
......@@ -236,7 +199,6 @@ def check_online():
@try_except
@WorkingDirectory(ROOT)
def check_git_status():
# Recommend 'git pull' if code is out of date
msg = ', for updates see https://github.com/ultralytics/yolov5'
......@@ -258,19 +220,14 @@ def check_git_status():
def check_python(minimum='3.6.2'):
# Check current python version vs. required python version
check_version(platform.python_version(), minimum, name='Python ', hard=True)
check_version(platform.python_version(), minimum, name='Python ')
def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False, hard=False, verbose=False):
def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False):
# Check version vs. required version
current, minimum = (pkg.parse_version(x) for x in (current, minimum))
result = (current == minimum) if pinned else (current >= minimum) # bool
s = f'{name}{minimum} required by YOLOv5, but {name}{current} is currently installed' # string
if hard:
assert result, s # assert min requirements met
if verbose and not result:
LOGGER.warning(s)
return result
result = (current == minimum) if pinned else (current >= minimum)
assert result, f'{name}{minimum} required by YOLOv5, but {name}{current} is currently installed'
@try_except
......@@ -281,8 +238,7 @@ def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), insta
if isinstance(requirements, (str, Path)): # requirements.txt file
file = Path(requirements)
assert file.exists(), f"{prefix} {file.resolve()} 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]
requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
else: # list or tuple of packages
requirements = [x for x in requirements if x not in exclude]
......@@ -337,14 +293,12 @@ def check_imshow():
def check_suffix(file='yolov5s.pt', suffix=('.pt',), msg=''):
# Check file(s) for acceptable suffix
# Check file(s) for acceptable suffixes
if file and suffix:
if isinstance(suffix, str):
suffix = [suffix]
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 Path(f).suffix.lower() in suffix, f"{msg}{f} acceptable suffix is {suffix}"
def check_yaml(file, suffix=('.yaml', '.yml')):
......@@ -361,9 +315,6 @@ def check_file(file, suffix=''):
elif file.startswith(('http:/', 'https:/')): # download
url = str(Path(file)).replace(':/', '://') # Pathlib turns :// -> :/
file = Path(urllib.parse.unquote(file).split('?')[0]).name # '%2F' to '/', split https://url.com/file.txt?auth
if Path(file).is_file():
print(f'Found {url} locally at {file}') # file already exists
else:
print(f'Downloading {url} to {file}...')
torch.hub.download_url_to_file(url, file)
assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}' # check
......@@ -402,7 +353,7 @@ def check_dataset(data, autodownload=True):
assert 'nc' in data, "Dataset 'nc' key missing."
if 'names' not in data:
data['names'] = [f'class{i}' for i in range(data['nc'])] # assign class names if missing
train, val, test, s = (data.get(x) for x in ('train', 'val', 'test', 'download'))
train, val, test, s = [data.get(x) for x in ('train', 'val', 'test', 'download')]
if val:
val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
if not all(x.exists() for x in val):
......@@ -471,9 +422,7 @@ def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
def make_divisible(x, divisor):
# Returns nearest x divisible by divisor
if isinstance(divisor, torch.Tensor):
divisor = int(divisor.max()) # to int
# Returns x evenly divisible by divisor
return math.ceil(x / divisor) * divisor
......@@ -671,7 +620,7 @@ def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=Non
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
# Settings
min_wh, max_wh = 2, 7680 # (pixels) minimum and maximum box width and height
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
time_limit = 10.0 # seconds to quit after
redundant = True # require redundant detections
......@@ -754,7 +703,7 @@ def strip_optimizer(f='best.pt', s=''): # from utils.general import *; strip_op
x = torch.load(f, map_location=torch.device('cpu'))
if x.get('ema'):
x['model'] = x['ema'] # replace model with ema
for k in 'optimizer', 'best_fitness', 'wandb_id', 'ema', 'updates': # keys
for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates': # keys
x[k] = None
x['epoch'] = -1
x['model'].half() # to FP16
......@@ -795,7 +744,7 @@ def print_mutation(results, hyp, save_dir, bucket):
i = np.argmax(fitness(data.values[:, :7])) #
f.write('# YOLOv5 Hyperparameter Evolution Results\n' +
f'# Best generation: {i}\n' +
f'# Last generation: {len(data) - 1}\n' +
f'# Last generation: {len(data)}\n' +
'# ' + ', '.join(f'{x.strip():>20s}' for x in keys[:7]) + '\n' +
'# ' + ', '.join(f'{x:>20.5g}' for x in data.values[i, :7]) + '\n\n')
yaml.safe_dump(hyp, f, sort_keys=False)
......@@ -805,8 +754,7 @@ def print_mutation(results, hyp, save_dir, bucket):
def apply_classifier(x, model, img, im0):
# Apply a second stage classifier to YOLO outputs
# Example model = torchvision.models.__dict__['efficientnet_b0'](pretrained=True).to(device).eval()
# Apply a second stage classifier to yolo outputs
im0 = [im0] if isinstance(im0, np.ndarray) else im0
for i, d in enumerate(x): # per image
if d is not None and len(d):
......@@ -831,7 +779,7 @@ def apply_classifier(x, model, img, im0):
im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32
im /= 255 # 0 - 255 to 0.0 - 1.0
im /= 255.0 # 0 - 255 to 0.0 - 1.0
ims.append(im)
pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction
......@@ -840,20 +788,33 @@ def apply_classifier(x, model, img, im0):
return x
def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True):
# Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
xyxy = torch.tensor(xyxy).view(-1, 4)
b = xyxy2xywh(xyxy) # boxes
if square:
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square
b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad
xyxy = xywh2xyxy(b).long()
clip_coords(xyxy, im.shape)
crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
if save:
cv2.imwrite(str(increment_path(file, mkdir=True).with_suffix('.jpg')), crop)
return crop
def increment_path(path, exist_ok=False, sep='', mkdir=False):
# Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
path = Path(path) # os-agnostic
if path.exists() and not exist_ok:
path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '')
suffix = path.suffix
path = path.with_suffix('')
dirs = glob.glob(f"{path}{sep}*") # similar paths
matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
i = [int(m.groups()[0]) for m in matches if m] # indices
n = max(i) + 1 if i else 2 # increment number
path = Path(f"{path}{sep}{n}{suffix}") # increment path
if mkdir:
path.mkdir(parents=True, exist_ok=True) # make directory
path = Path(f"{path}{sep}{n}{suffix}") # update path
dir = path if path.suffix == '' else path.parent # directory
if not dir.exists() and mkdir:
dir.mkdir(parents=True, exist_ok=True) # make directory
return path
# Variables
NCOLS = 0 if is_docker() else shutil.get_terminal_size().columns # terminal window size for tqdm
PyTorch/Compute-Vision/Objection/yolov5/utils/google_app_engine/additional_requirements.txt
View file @ 17bc28d5
# add these requirements in your app on top of the existing ones
pip==21.1
pip==19.2
Flask==1.0.2
gunicorn==19.9.0
PyTorch/Compute-Vision/Objection/yolov5/utils/loggers/__init__.py
View file @ 17bc28d5
......@@ -3,11 +3,9 @@
Logging utils
"""
import os
import warnings
from threading import Thread
import pkg_resources as pkg
import torch
from torch.utils.tensorboard import SummaryWriter
......@@ -17,19 +15,11 @@ from utils.plots import plot_images, plot_results
from utils.torch_utils import de_parallel
LOGGERS = ('csv', 'tb', 'wandb') # text-file, TensorBoard, Weights & Biases
RANK = int(os.getenv('RANK', -1))
try:
import wandb
assert hasattr(wandb, '__version__') # verify package import not local dir
if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]:
try:
wandb_login_success = wandb.login(timeout=30)
except wandb.errors.UsageError: # known non-TTY terminal issue
wandb_login_success = False
if not wandb_login_success:
wandb = None
except (ImportError, AssertionError):
wandb = None
......@@ -47,7 +37,6 @@ class Loggers():
'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', # metrics
'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss
'x/lr0', 'x/lr1', 'x/lr2'] # params
self.best_keys = ['best/epoch', 'best/precision', 'best/recall', 'best/mAP_0.5', 'best/mAP_0.5:0.95',]
for k in LOGGERS:
setattr(self, k, None) # init empty logger dictionary
self.csv = True # always log to csv
......@@ -126,10 +115,6 @@ class Loggers():
self.tb.add_scalar(k, v, epoch)
if self.wandb:
if best_fitness == fi:
best_results = [epoch] + vals[3:7]
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)
......@@ -139,11 +124,11 @@ class Loggers():
if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1:
self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi)
def on_train_end(self, last, best, plots, epoch, results):
def on_train_end(self, last, best, plots, epoch):
# Callback runs on training end
if plots:
plot_results(file=self.save_dir / 'results.csv') # save results.png
files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))]
files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter
if self.tb:
......@@ -152,7 +137,6 @@ class Loggers():
self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC')
if self.wandb:
self.wandb.log({k: v for k, v in zip(self.keys[3:10], results)}) # log best.pt val results
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:
......@@ -163,9 +147,3 @@ class Loggers():
else:
self.wandb.finish_run()
self.wandb = WandbLogger(self.opt)
def on_params_update(self, params):
# Update hyperparams or configs of the experiment
# params: A dict containing {param: value} pairs
if self.wandb:
self.wandb.wandb_run.config.update(params, allow_val_change=True)
PyTorch/Compute-Vision/Objection/yolov5/utils/loggers/wandb/README.md
View file @ 17bc28d5
......@@ -2,7 +2,6 @@
* [About Weights & Biases](#about-weights-&-biases)
* [First-Time Setup](#first-time-setup)
* [Viewing runs](#viewing-runs)
* [Disabling wandb](#disabling-wandb)
* [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage)
* [Reports: Share your work with the world!](#reports)
......@@ -50,36 +49,31 @@ Run information streams from your environment to the W&B cloud console as you tr
* Environment: OS and Python types, Git repository and state, **training command**
<p align="center"><img width="900" alt="Weights & Biases dashboard" src="https://user-images.githubusercontent.com/26833433/135390767-c28b050f-8455-4004-adb0-3b730386e2b2.png"></p>
</details>
## Disabling wandb
* training after running `wandb disabled` inside that directory creates no wandb run
![Screenshot (84)](https://user-images.githubusercontent.com/15766192/143441777-c780bdd7-7cb4-4404-9559-b4316030a985.png)
* To enable wandb again, run `wandb online`
![Screenshot (85)](https://user-images.githubusercontent.com/15766192/143441866-7191b2cb-22f0-4e0f-ae64-2dc47dc13078.png)
</details>
## Advanced Usage
You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started.
<details open>
<h3> 1: Train and Log Evaluation simultaneousy </h3>
This is an extension of the previous section, but it'll also training after uploading the dataset. <b> This also evaluation Table</b>
Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets,
so no images will be uploaded from your system more than once.
<details open>
<h3>1. Visualize and Version Datasets</h3>
Log, visualize, dynamically query, and understand your data with <a href='https://docs.wandb.ai/guides/data-vis/tables'>W&B Tables</a>. You can use the following command to log your dataset as a W&B Table. This will generate a <code>{dataset}_wandb.yaml</code> file which can be used to train from dataset artifact.
<details>
<summary> <b>Usage</b> </summary>
<b>Code</b> <code> $ python train.py --upload_data val</code>
<b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. </code>
![Screenshot from 2021-11-21 17-40-06](https://user-images.githubusercontent.com/15766192/142761183-c1696d8c-3f38-45ab-991a-bb0dfd98ae7d.png)
![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png)
</details>
<h3>2. Visualize and Version Datasets</h3>
Log, visualize, dynamically query, and understand your data with <a href='https://docs.wandb.ai/guides/data-vis/tables'>W&B Tables</a>. You can use the following command to log your dataset as a W&B Table. This will generate a <code>{dataset}_wandb.yaml</code> file which can be used to train from dataset artifact.
<h3> 2: Train and Log Evaluation simultaneousy </h3>
This is an extension of the previous section, but it'll also training after uploading the dataset. <b> This also evaluation Table</b>
Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets,
so no images will be uploaded from your system more than once.
<details>
<summary> <b>Usage</b> </summary>
<b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data .. </code>
<b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --data .. --upload_data </code>
![Screenshot (64)](https://user-images.githubusercontent.com/15766192/128486078-d8433890-98a3-4d12-8986-b6c0e3fc64b9.png)
![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png)
</details>
<h3> 3: Train using dataset artifact </h3>
......@@ -87,7 +81,7 @@ You can leverage W&B artifacts and Tables integration to easily visualize and ma
can be used to train a model directly from the dataset artifact. <b> This also logs evaluation </b>
<details>
<summary> <b>Usage</b> </summary>
<b>Code</b> <code> $ python train.py --data {data}_wandb.yaml </code>
<b>Code</b> <code> $ python utils/logger/wandb/log_dataset.py --data {data}_wandb.yaml </code>
![Screenshot (72)](https://user-images.githubusercontent.com/15766192/128979739-4cf63aeb-a76f-483f-8861-1c0100b938a5.png)
</details>
......@@ -129,6 +123,7 @@ Any run can be resumed using artifacts if the <code>--resume</code> argument sta
</details>
<h3> Reports </h3>
W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all four YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)).
......
PyTorch/Compute-Vision/Objection/yolov5/utils/loggers/wandb/log_dataset.py
View file @ 17bc28d5
......@@ -2,15 +2,11 @@ import argparse
from wandb_utils import WandbLogger
from utils.general import LOGGER
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
def create_dataset_artifact(opt):
logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused
if not logger.wandb:
LOGGER.info("install wandb using `pip install wandb` to log the dataset")
if __name__ == '__main__':
......
PyTorch/Compute-Vision/Objection/yolov5/utils/loggers/wandb/sweep.py
View file @ 17bc28d5
......@@ -8,10 +8,10 @@ ROOT = FILE.parents[3] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
from train import parse_opt, train
from utils.callbacks import Callbacks
from train import train, parse_opt
from utils.general import increment_path
from utils.torch_utils import select_device
from utils.callbacks import Callbacks
def sweep():
......@@ -26,11 +26,6 @@ def sweep():
opt.epochs = hyp_dict.get("epochs")
opt.nosave = True
opt.data = hyp_dict.get("data")
opt.weights = str(opt.weights)
opt.cfg = str(opt.cfg)
opt.data = str(opt.data)
opt.hyp = str(opt.hyp)
opt.project = str(opt.project)
device = select_device(opt.device, batch_size=opt.batch_size)
# train
......
PyTorch/Compute-Vision/Objection/yolov5/utils/loggers/wandb/wandb_utils.py
View file @ 17bc28d5
......@@ -5,8 +5,8 @@ import os
import sys
from contextlib import contextmanager
from pathlib import Path
from typing import Dict
import pkg_resources as pkg
import yaml
from tqdm import tqdm
......@@ -15,17 +15,21 @@ 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.datasets import LoadImagesAndLabels, img2label_paths
from utils.general import LOGGER, check_dataset, check_file
from utils.datasets import LoadImagesAndLabels
from utils.datasets import img2label_paths
from utils.general import check_dataset, check_file
RANK = int(os.getenv('RANK', -1))
try:
import wandb
assert hasattr(wandb, '__version__') # verify package import not local dir
if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]:
wandb.login(timeout=30)
except (ImportError, AssertionError):
wandb = None
RANK = int(os.getenv('RANK', -1))
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
......@@ -141,8 +145,7 @@ class WandbLogger():
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
# 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)
......@@ -186,7 +189,6 @@ class WandbLogger():
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):
......@@ -203,6 +205,7 @@ class WandbLogger():
config_path = self.log_dataset_artifact(opt.data,
opt.single_cls,
'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
print("Created dataset config file ", config_path)
with open(config_path, errors='ignore') as f:
wandb_data_dict = yaml.safe_load(f)
return wandb_data_dict
......@@ -244,9 +247,7 @@ class WandbLogger():
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.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
self.val_table = self.val_artifact.get("val")
if self.val_table_path_map is None:
self.map_val_table_path()
......@@ -317,7 +318,7 @@ 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}")
print("Saving model artifact on epoch ", epoch + 1)
def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
"""
......@@ -333,41 +334,28 @@ class WandbLogger():
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('train'):
data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train')
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 = Path('data') / path
path = Path(data_file).stem
path = (path if overwrite_config else path + '_wandb') + '.yaml' # updated data.yaml 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.wandb_run.use_artifact(self.train_artifact)
self.val_artifact.wait()
self.val_table = self.val_artifact.get('val')
self.map_val_table_path()
......@@ -382,18 +370,18 @@ class WandbLogger():
Useful for - referencing artifacts for evaluation.
"""
self.val_table_path_map = {}
LOGGER.info("Mapping dataset")
print("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'):
def create_dataset_table(self, dataset, class_to_id, name='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
dataset (LoadImagesAndLabels) -- instance of LoadImagesAndLabels class used to iterate over the data to build Table
class_to_id (dict(int, str)) -- hash map that maps class ids to labels
name (str) -- name of the artifact
returns:
dataset artifact to be logged or used
......@@ -439,34 +427,23 @@ class WandbLogger():
"""
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 = {}
total_conf = 0
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}",
"class_id": int(cls),
"box_caption": "%s %.3f" % (names[cls], conf),
"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]
total_conf = total_conf + conf
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
total_conf / max(1, len(box_data))
)
def val_one_image(self, pred, predn, path, names, im):
......@@ -485,7 +462,7 @@ class WandbLogger():
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[cls]} {conf:.3f}",
"box_caption": "%s %.3f" % (names[cls], conf),
"scores": {"class_score": conf},
"domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space
......@@ -512,15 +489,8 @@ 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:
self.log_dict["Bounding Box Debugger/Images"] = self.bbox_media_panel_images
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}")
self.wandb_run.finish()
self.wandb_run = None
self.log_dict = {}
self.bbox_media_panel_images = []
if self.result_artifact:
......@@ -529,9 +499,7 @@ class WandbLogger():
('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_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
def finish_run(self):
......
PyTorch/Compute-Vision/Objection/yolov5/utils/loss.py
View file @ 17bc28d5
......@@ -18,7 +18,7 @@ def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#iss
class BCEBlurWithLogitsLoss(nn.Module):
# BCEwithLogitLoss() with reduced missing label effects.
def __init__(self, alpha=0.05):
super().__init__()
super(BCEBlurWithLogitsLoss, self).__init__()
self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss()
self.alpha = alpha
......@@ -35,7 +35,7 @@ class BCEBlurWithLogitsLoss(nn.Module):
class FocalLoss(nn.Module):
# Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
super().__init__()
super(FocalLoss, self).__init__()
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
self.gamma = gamma
self.alpha = alpha
......@@ -65,7 +65,7 @@ class FocalLoss(nn.Module):
class QFocalLoss(nn.Module):
# Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
super().__init__()
super(QFocalLoss, self).__init__()
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
self.gamma = gamma
self.alpha = alpha
......@@ -108,7 +108,7 @@ class ComputeLoss:
BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module
self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7
self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, .02]) # P3-P7
self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index
self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
for k in 'na', 'nc', 'nl', 'anchors':
......@@ -129,7 +129,7 @@ class ComputeLoss:
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
# Regression
pxy = ps[:, :2].sigmoid() * 2 - 0.5
pxy = ps[:, :2].sigmoid() * 2. - 0.5
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
pbox = torch.cat((pxy, pwh), 1) # predicted box
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target)
......@@ -189,15 +189,15 @@ class ComputeLoss:
if nt:
# Matches
r = t[:, :, 4:6] / anchors[:, None] # wh ratio
j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare
j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t'] # compare
# j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
t = t[j] # filter
# Offsets
gxy = t[:, 2:4] # grid xy
gxi = gain[[2, 3]] - gxy # inverse
j, k = ((gxy % 1 < g) & (gxy > 1)).T
l, m = ((gxi % 1 < g) & (gxi > 1)).T
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
l, m = ((gxi % 1. < g) & (gxi > 1.)).T
j = torch.stack((torch.ones_like(j), j, k, l, m))
t = t.repeat((5, 1, 1))[j]
offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment