Skip to content

Y
yolov5
提交 7fc7ed77 authored 作者: Glenn Jocher's avatar Glenn Jocher
浏览文件
操作

Created using Colaboratory

上级 2ecaa96c
显示空白字符变更
内嵌 并排
正在显示 包含 31 行增加 和 37 行删除
segment/tutorial.ipynb
浏览文件 @ 7fc7ed77
...@@ -42,14 +42,14 @@ ...@@ -42,14 +42,14 @@
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"id": "wbvMlHd_QwMG", "id": "wbvMlHd_QwMG",
"outputId": "d1e33dfc-9ad4-436e-f1e5-01acee40c029" "outputId": "664f49fa-554a-4dca-8d0e-5c9dd60f6d28"
}, },
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stderr", "name": "stderr",
"text": [ "text": [
"YOLOv5 🚀 v6.2-251-g241d798 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n" "YOLOv5 🚀 v6.2-257-g2ecaa96 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n"
] ]
}, },
{ {
...@@ -100,7 +100,7 @@ ...@@ -100,7 +100,7 @@
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"id": "zR9ZbuQCH7FX", "id": "zR9ZbuQCH7FX",
"outputId": "e206fcec-cf42-4754-8a42-39bc3603eba8" "outputId": "6392c9ff-0863-4665-faf9-b3af9881c305"
}, },
"outputs": [ "outputs": [
{ {
...@@ -108,16 +108,16 @@ ...@@ -108,16 +108,16 @@
"name": "stdout", "name": "stdout",
"text": [ "text": [
"\u001b[34m\u001b[1msegment/predict: \u001b[0mweights=['yolov5s-seg.pt'], source=data/images, data=data/coco128.yaml, 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/predict-seg, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1, retina_masks=False\n", "\u001b[34m\u001b[1msegment/predict: \u001b[0mweights=['yolov5s-seg.pt'], source=data/images, data=data/coco128.yaml, 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/predict-seg, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False, vid_stride=1, retina_masks=False\n",
"YOLOv5 🚀 v6.2-251-g241d798 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n", "YOLOv5 🚀 v6.2-257-g2ecaa96 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"\n", "\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s-seg.pt to yolov5s-seg.pt...\n", "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s-seg.pt to yolov5s-seg.pt...\n",
"100% 14.9M/14.9M [00:03<00:00, 3.93MB/s]\n", "100% 14.9M/14.9M [00:01<00:00, 9.09MB/s]\n",
"\n", "\n",
"Fusing layers... \n", "Fusing layers... \n",
"YOLOv5s-seg summary: 224 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n", "YOLOv5s-seg summary: 224 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 17.2ms\n", "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, 18.0ms\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, 13.7ms\n", "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, 13.5ms\n",
"Speed: 0.4ms pre-process, 15.5ms inference, 22.2ms NMS per image at shape (1, 3, 640, 640)\n", "Speed: 0.5ms pre-process, 15.7ms inference, 18.5ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/predict-seg/exp\u001b[0m\n" "Results saved to \u001b[1mruns/predict-seg/exp\u001b[0m\n"
] ]
} }
...@@ -155,7 +155,7 @@ ...@@ -155,7 +155,7 @@
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"id": "WQPtK1QYVaD_", "id": "WQPtK1QYVaD_",
"outputId": "f7eba0ae-49d1-405b-a1cf-169212fadc2c" "outputId": "4707734e-00c7-43da-d642-32c3c3fe3090"
}, },
"outputs": [ "outputs": [
{ {
...@@ -182,26 +182,23 @@ ...@@ -182,26 +182,23 @@
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"id": "X58w8JLpMnjH", "id": "X58w8JLpMnjH",
"outputId": "73533135-6995-4f2d-adb0-3acb5ef9b300" "outputId": "f96b700d-c779-4a34-930b-e85be4e58974"
}, },
"outputs": [ "outputs": [
{ {
"metadata": {
"tags": null
},
"name": "stdout",
"output_type": "stream", "output_type": "stream",
"name": "stdout",
"text": [ "text": [
"\u001b[34m\u001b[1msegment/val: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5s-seg.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, max_det=300, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=False, project=runs/val-seg, name=exp, exist_ok=False, half=True, dnn=False\n", "\u001b[34m\u001b[1msegment/val: \u001b[0mdata=/content/yolov5/data/coco.yaml, weights=['yolov5s-seg.pt'], batch_size=32, imgsz=640, conf_thres=0.001, iou_thres=0.6, max_det=300, task=val, device=, workers=8, single_cls=False, augment=False, verbose=False, save_txt=False, save_hybrid=False, save_conf=False, save_json=False, project=runs/val-seg, name=exp, exist_ok=False, half=True, dnn=False\n",
"YOLOv5 🚀 v6.2-251-g241d798 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n", "YOLOv5 🚀 v6.2-257-g2ecaa96 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"\n", "\n",
"Fusing layers... \n", "Fusing layers... \n",
"YOLOv5s-seg summary: 224 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n", "YOLOv5s-seg summary: 224 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco/val2017' images and labels...4952 found, 48 missing, 0 empty, 0 corrupt: 100% 5000/5000 [00:03<00:00, 1420.92it/s]\n", "\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco/val2017... 4952 images, 48 backgrounds, 0 corrupt: 100% 5000/5000 [00:03<00:00, 1409.04it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n", "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
" Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 157/157 [01:54<00:00, 1.37it/s]\n", " Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 157/157 [01:53<00:00, 1.38it/s]\n",
" all 5000 36335 0.673 0.517 0.566 0.373 0.672 0.49 0.532 0.319\n", " all 5000 36335 0.673 0.517 0.566 0.373 0.672 0.49 0.532 0.319\n",
"Speed: 0.9ms pre-process, 3.9ms inference, 3.0ms NMS per image at shape (32, 3, 640, 640)\n", "Speed: 0.8ms pre-process, 4.0ms inference, 2.8ms NMS per image at shape (32, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/val-seg/exp\u001b[0m\n" "Results saved to \u001b[1mruns/val-seg/exp\u001b[0m\n"
] ]
} }
...@@ -273,27 +270,24 @@ ...@@ -273,27 +270,24 @@
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"id": "1NcFxRcFdJ_O", "id": "1NcFxRcFdJ_O",
"outputId": "8e349df5-9910-4a91-a845-748def15d3d7" "outputId": "2cdb19cc-69af-4c90-f8de-af02dfedba91"
}, },
"outputs": [ "outputs": [
{ {
"metadata": {
"tags": null
},
"name": "stdout",
"output_type": "stream", "output_type": "stream",
"name": "stdout",
"text": [ "text": [
"\u001b[34m\u001b[1msegment/train: \u001b[0mweights=yolov5s-seg.pt, cfg=, data=coco128-seg.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train-seg, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, mask_ratio=4, no_overlap=False\n", "\u001b[34m\u001b[1msegment/train: \u001b[0mweights=yolov5s-seg.pt, cfg=, data=coco128-seg.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train-seg, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, mask_ratio=4, no_overlap=False\n",
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n", "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 ✅\n",
"YOLOv5 🚀 v6.2-251-g241d798 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n", "YOLOv5 🚀 v6.2-257-g2ecaa96 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"\n", "\n",
"\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.01, 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=0.01, 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[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train-seg', view at http://localhost:6006/\n", "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train-seg', view at http://localhost:6006/\n",
"\n", "\n",
"Dataset not found ⚠️, missing paths ['/content/datasets/coco128-seg/images/train2017']\n", "Dataset not found ⚠️, missing paths ['/content/datasets/coco128-seg/images/train2017']\n",
"Downloading https://ultralytics.com/assets/coco128-seg.zip to coco128-seg.zip...\n", "Downloading https://ultralytics.com/assets/coco128-seg.zip to coco128-seg.zip...\n",
"100% 6.79M/6.79M [00:01<00:00, 4.42MB/s]\n", "100% 6.79M/6.79M [00:01<00:00, 5.87MB/s]\n",
"Dataset download success ✅ (2.8s), saved to \u001b[1m/content/datasets\u001b[0m\n", "Dataset download success ✅ (2.1s), saved to \u001b[1m/content/datasets\u001b[0m\n",
"\n", "\n",
" from n params module arguments \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.Conv [3, 32, 6, 2, 2] \n",
...@@ -327,11 +321,11 @@ ...@@ -327,11 +321,11 @@
"\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n", "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01) with parameter groups 60 weight(decay=0.0), 63 weight(decay=0.0005), 63 bias\n", "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01) with parameter groups 60 weight(decay=0.0), 63 weight(decay=0.0005), 63 bias\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n", "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning '/content/datasets/coco128-seg/labels/train2017' images and labels...126 found, 2 missing, 0 empty, 0 corrupt: 100% 128/128 [00:00<00:00, 1383.68it/s]\n", "\u001b[34m\u001b[1mtrain: \u001b[0mScanning /content/datasets/coco128-seg/labels/train2017... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<00:00, 1439.54it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128-seg/labels/train2017.cache\n", "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128-seg/labels/train2017.cache\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 241.77it/s]\n", "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 253.53it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco128-seg/labels/train2017.cache' images and labels... 126 found, 2 missing, 0 empty, 0 corrupt: 100% 128/128 [00:00<?, ?it/s]\n", "\u001b[34m\u001b[1mval: \u001b[0mScanning /content/datasets/coco128-seg/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 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, 92.38it/s]\n", "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:01<00:00, 93.82it/s]\n",
"\n", "\n",
"\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n", "\u001b[34m\u001b[1mAutoAnchor: \u001b[0m4.27 anchors/target, 0.994 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅\n",
"Plotting labels to runs/train-seg/exp/labels.jpg... \n", "Plotting labels to runs/train-seg/exp/labels.jpg... \n",
...@@ -341,18 +335,18 @@ ...@@ -341,18 +335,18 @@
"Starting training for 3 epochs...\n", "Starting training for 3 epochs...\n",
"\n", "\n",
" Epoch GPU_mem box_loss seg_loss obj_loss cls_loss Instances Size\n", " Epoch GPU_mem box_loss seg_loss obj_loss cls_loss Instances Size\n",
" 0/2 4.92G 0.0417 0.04646 0.06066 0.02126 192 640: 100% 8/8 [00:07<00:00, 1.13it/s]\n", " 0/2 4.92G 0.0417 0.04646 0.06066 0.02126 192 640: 100% 8/8 [00:07<00:00, 1.11it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:02<00:00, 1.79it/s]\n", " Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:02<00:00, 1.85it/s]\n",
" all 128 929 0.737 0.649 0.715 0.492 0.719 0.617 0.658 0.408\n", " all 128 929 0.737 0.649 0.715 0.492 0.719 0.617 0.658 0.408\n",
"\n", "\n",
" Epoch GPU_mem box_loss seg_loss obj_loss cls_loss Instances Size\n", " Epoch GPU_mem box_loss seg_loss obj_loss cls_loss Instances Size\n",
" 1/2 6.29G 0.04157 0.04503 0.05772 0.01777 208 640: 100% 8/8 [00:09<00:00, 1.18s/it]\n", " 1/2 6.29G 0.04157 0.04503 0.05772 0.01777 208 640: 100% 8/8 [00:09<00:00, 1.19s/it]\n",
" Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:02<00:00, 1.85it/s]\n", " Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:02<00:00, 1.75it/s]\n",
" all 128 929 0.756 0.674 0.738 0.506 0.725 0.64 0.68 0.422\n", " all 128 929 0.756 0.674 0.738 0.506 0.725 0.64 0.68 0.422\n",
"\n", "\n",
" Epoch GPU_mem box_loss seg_loss obj_loss cls_loss Instances Size\n", " Epoch GPU_mem box_loss seg_loss obj_loss cls_loss Instances Size\n",
" 2/2 6.29G 0.0425 0.04793 0.06784 0.01863 161 640: 100% 8/8 [00:03<00:00, 2.04it/s]\n", " 2/2 6.29G 0.0425 0.04793 0.06784 0.01863 161 640: 100% 8/8 [00:04<00:00, 1.99it/s]\n",
" Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:02<00:00, 1.55it/s]\n", " Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:02<00:00, 1.81it/s]\n",
" all 128 929 0.736 0.694 0.747 0.522 0.769 0.622 0.683 0.427\n", " all 128 929 0.736 0.694 0.747 0.522 0.769 0.622 0.683 0.427\n",
"\n", "\n",
"3 epochs completed in 0.008 hours.\n", "3 epochs completed in 0.008 hours.\n",
...@@ -362,7 +356,7 @@ ...@@ -362,7 +356,7 @@
"Validating runs/train-seg/exp/weights/best.pt...\n", "Validating runs/train-seg/exp/weights/best.pt...\n",
"Fusing layers... \n", "Fusing layers... \n",
"Model summary: 165 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n", "Model summary: 165 layers, 7611485 parameters, 0 gradients, 26.4 GFLOPs\n",
" Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:06<00:00, 1.55s/it]\n", " Class Images Instances Box(P R mAP50 mAP50-95) Mask(P R mAP50 mAP50-95): 100% 4/4 [00:06<00:00, 1.58s/it]\n",
" all 128 929 0.738 0.694 0.746 0.522 0.759 0.625 0.682 0.426\n", " all 128 929 0.738 0.694 0.746 0.522 0.759 0.625 0.682 0.426\n",
" person 128 254 0.845 0.756 0.836 0.55 0.861 0.669 0.759 0.407\n", " person 128 254 0.845 0.756 0.836 0.55 0.861 0.669 0.759 0.407\n",
" bicycle 128 6 0.475 0.333 0.549 0.341 0.711 0.333 0.526 0.322\n", " bicycle 128 6 0.475 0.333 0.549 0.341 0.711 0.333 0.526 0.322\n",
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论