apoorva/greenhouse
2
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Created using Colaboratory

Browse Source
This commit is contained in:
Glenn Jocher 2022-12-19 10:57:59 +01:00
parent a441ab1593
commit 2813de7cc3
1 changed files with 116 additions and 146 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

262
tutorial.ipynb vendored
View File

@ -5,7 +5,6 @@
"colab": { "colab": {
"name": "YOLOv3 Tutorial", "name": "YOLOv3 Tutorial",
"provenance": [], "provenance": [],
"collapsed_sections": [],
"include_colab_link": true "include_colab_link": true
}, },
"kernelspec": { "kernelspec": {
@ -402,7 +401,7 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "7efd38e6-c41f-4fe3-9864-ce4fa43fbb5b" "outputId": "141002fc-fe49-48d2-a575-2555bf903413"
}, },
"source": [ "source": [
"!git clone https://github.com/ultralytics/yolov3 # clone\n", "!git clone https://github.com/ultralytics/yolov3 # clone\n",
@ -413,15 +412,8 @@
"from yolov3 import utils\n", "from yolov3 import utils\n",
"display = utils.notebook_init() # checks" "display = utils.notebook_init() # checks"
], ],
"execution_count": 24, "execution_count": 1,
"outputs": [ "outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"YOLOv3 🚀 v9.6.0-1-g93a2bcc torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n"
]
},
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
@ -459,27 +451,27 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "486202a4-bae2-454f-da62-2c74676a3058" "outputId": "c29b082a-8e56-4799-b32a-056425f130d1"
}, },
"source": [ "source": [
"!python detect.py --weights yolov3.pt --img 640 --conf 0.25 --source data/images\n", "!python detect.py --weights yolov3.pt --img 640 --conf 0.25 --source data/images\n",
"display.Image(filename='runs/detect/exp/zidane.jpg', width=600)" "# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)"
], ],
"execution_count": 22, "execution_count": 4,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
"name": "stdout", "name": "stdout",
"text": [ "text": [
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov3.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", "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov3.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",
"YOLOv3 🚀 v9.6.0-1-g93a2bcc torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n", "YOLOv3 🚀 v9.6.0-29-ga441ab1 torch 1.13.0+cu116 CUDA:0 (Tesla T4, 15110MiB)\n",
"\n", "\n",
"Fusing layers... \n", "Fusing layers... \n",
"Model Summary: 261 layers, 61922845 parameters, 0 gradients, 156.1 GFLOPs\n", "Model Summary: 261 layers, 61922845 parameters, 0 gradients\n",
"image 1/2 /content/yolov3/data/images/bus.jpg: 640x480 4 persons, 1 bus, 1 tie, 1 sports ball, Done. (0.020s)\n", "image 1/2 /content/yolov3/data/images/bus.jpg: 640x480 4 persons, 1 bicycle, 1 bus, Done. (0.050s)\n",
"image 2/2 /content/yolov3/data/images/zidane.jpg: 384x640 2 persons, 3 ties, Done. (0.020s)\n", "image 2/2 /content/yolov3/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.038s)\n",
"Speed: 0.5ms pre-process, 20.0ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n", "Speed: 0.5ms pre-process, 44.3ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n" "Results saved to \u001b[1mruns/detect/exp2\u001b[0m\n"
] ]
} }
] ]
@ -542,7 +534,7 @@
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n", "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip" "!unzip -q tmp.zip -d ../datasets && rm tmp.zip"
], ],
"execution_count": 4, "execution_count": null,
"outputs": [ "outputs": [
{ {
"output_type": "display_data", "output_type": "display_data",
@ -573,7 +565,7 @@
"# Run YOLOv3 on COCO val\n", "# Run YOLOv3 on COCO val\n",
"!python val.py --weights yolov3.pt --data coco.yaml --img 640 --iou 0.65 --half" "!python val.py --weights yolov3.pt --data coco.yaml --img 640 --iou 0.65 --half"
], ],
"execution_count": 23, "execution_count": null,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
@ -690,20 +682,6 @@
"execution_count": null, "execution_count": null,
"outputs": [] "outputs": []
}, },
{
"cell_type": "code",
"metadata": {
"id": "2fLAV42oNb7M"
},
"source": [
"# Weights & Biases (optional)\n",
"%pip install -q wandb\n",
"import wandb\n",
"wandb.login()"
],
"execution_count": null,
"outputs": []
},
{ {
"cell_type": "code", "cell_type": "code",
"metadata": { "metadata": {
@ -711,13 +689,13 @@
"colab": { "colab": {
"base_uri": "https://localhost:8080/" "base_uri": "https://localhost:8080/"
}, },
"outputId": "a601aa72-687c-4dda-a16c-c0b2d9073910" "outputId": "c77013e3-347d-42a4-84de-3ca42ea3aee9"
}, },
"source": [ "source": [
"# Train YOLOv3 on COCO128 for 3 epochs\n", "# Train YOLOv3 on COCO128 for 3 epochs\n",
"!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov3.pt --cache" "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov3.pt --cache"
], ],
"execution_count": 21, "execution_count": 3,
"outputs": [ "outputs": [
{ {
"output_type": "stream", "output_type": "stream",
@ -725,12 +703,18 @@
"text": [ "text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov3.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=yolov3.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[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov3 ✅\n", "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov3 ✅\n",
"YOLOv3 🚀 v9.6.0-1-g93a2bcc torch 1.10.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)\n", "YOLOv3 🚀 v9.6.0-29-ga441ab1 torch 1.13.0+cu116 CUDA:0 (Tesla T4, 15110MiB)\n",
"\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=0.1, 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[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv3 🚀 runs (RECOMMENDED)\n", "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv3 🚀 runs (RECOMMENDED)\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n", "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n",
"\n", "\n",
"WARNING: Dataset not found, nonexistent paths: ['/content/datasets/coco128/images/train2017']\n",
"Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n",
"100% 6.66M/6.66M [00:00<00:00, 10.2MB/s]\n",
"Dataset autodownload success, saved to ../datasets\n",
"\n",
"\n",
" from n params module arguments \n", " from n params module arguments \n",
" 0 -1 1 928 models.common.Conv [3, 32, 3, 1] \n", " 0 -1 1 928 models.common.Conv [3, 32, 3, 1] \n",
" 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n", " 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
@ -744,7 +728,7 @@
" 9 -1 1 4720640 models.common.Conv [512, 1024, 3, 2] \n", " 9 -1 1 4720640 models.common.Conv [512, 1024, 3, 2] \n",
" 10 -1 4 20983808 models.common.Bottleneck [1024, 1024] \n", " 10 -1 4 20983808 models.common.Bottleneck [1024, 1024] \n",
" 11 -1 1 5245952 models.common.Bottleneck [1024, 1024, False] \n", " 11 -1 1 5245952 models.common.Bottleneck [1024, 1024, False] \n",
" 12 -1 1 525312 models.common.Conv [1024, 512, [1, 1]] \n", " 12 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n",
" 13 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n", " 13 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n",
" 14 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n", " 14 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n",
" 15 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n", " 15 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n",
@ -761,119 +745,120 @@
" 26 -1 1 344832 models.common.Bottleneck [384, 256, False] \n", " 26 -1 1 344832 models.common.Bottleneck [384, 256, False] \n",
" 27 -1 2 656896 models.common.Bottleneck [256, 256, False] \n", " 27 -1 2 656896 models.common.Bottleneck [256, 256, False] \n",
" 28 [27, 22, 15] 1 457725 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 512, 1024]]\n", " 28 [27, 22, 15] 1 457725 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 512, 1024]]\n",
"Model Summary: 333 layers, 61949149 parameters, 61949149 gradients, 156.3 GFLOPs\n", "Model Summary: 333 layers, 61949149 parameters, 61949149 gradients, 156.6 GFLOPs\n",
"\n", "\n",
"Transferred 439/439 items from yolov3.pt\n", "Transferred 439/439 items from yolov3.pt\n",
"Scaled weight_decay = 0.0005\n", "Scaled weight_decay = 0.0005\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 72 weight, 75 weight (no decay), 75 bias\n", "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 72 weight, 75 weight (no decay), 75 bias\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mversion 1.0.3 required by YOLOv3, but version 0.1.12 is currently installed\n", "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), MedianBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), ToGray(always_apply=False, p=0.01), CLAHE(always_apply=False, p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\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[0mScanning '../datasets/coco128/labels/train2017' images and labels...126 found, 2 missing, 0 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 1542.80it/s]\n",
"\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 1333.45it/s]\n", "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\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[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 327.35it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 377.72it/s]\n", "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 126 found, 2 missing, 0 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, 124.89it/s]\n",
"Plotting labels to runs/train/exp/labels.jpg... \n", "Plotting labels to runs/train/exp/labels.jpg... \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",
"Image sizes 640 train, 640 val\n", "Image sizes 640 train, 640 val\n",
"Using 8 dataloader workers\n", "Using 2 dataloader workers\n",
"Logging results to \u001b[1mruns/train/exp\u001b[0m\n", "Logging results to \u001b[1mruns/train/exp\u001b[0m\n",
"Starting training for 3 epochs...\n", "Starting training for 3 epochs...\n",
"\n", "\n",
" Epoch gpu_mem box obj cls labels img_size\n", " Epoch gpu_mem box obj cls labels img_size\n",
" 0/2 12.2G 0.03673 0.05445 0.0102 186 640: 100% 8/8 [00:04<00:00, 1.93it/s]\n", " 0/2 11.9G 0.03646 0.05139 0.01218 170 640: 100% 8/8 [00:11<00:00, 1.41s/it]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 5.11it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.18it/s]\n",
" all 128 929 0.769 0.747 0.822 0.584\n", " all 128 929 0.701 0.771 0.81 0.578\n",
"\n", "\n",
" Epoch gpu_mem box obj cls labels img_size\n", " Epoch gpu_mem box obj cls labels img_size\n",
" 1/2 16.3G 0.03681 0.05345 0.01067 164 640: 100% 8/8 [00:01<00:00, 4.77it/s]\n", " 1/2 10.7G 0.03638 0.05337 0.01048 204 640: 100% 8/8 [00:06<00:00, 1.28it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.98it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.94it/s]\n",
" all 128 929 0.745 0.77 0.827 0.589\n", " all 128 929 0.708 0.774 0.814 0.58\n",
"\n", "\n",
" Epoch gpu_mem box obj cls labels img_size\n", " Epoch gpu_mem box obj cls labels img_size\n",
" 2/2 16.3G 0.03496 0.04829 0.01105 192 640: 100% 8/8 [00:01<00:00, 4.77it/s]\n", " 2/2 12.1G 0.03671 0.05941 0.01124 281 640: 100% 8/8 [00:06<00:00, 1.26it/s]\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 5.20it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.91it/s]\n",
" all 128 929 0.779 0.752 0.829 0.588\n", " all 128 929 0.706 0.776 0.816 0.583\n",
"\n", "\n",
"3 epochs completed in 0.005 hours.\n", "3 epochs completed in 0.012 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 124.4MB\n", "Optimizer stripped from runs/train/exp/weights/last.pt, 124.4MB\n",
"Optimizer stripped from runs/train/exp/weights/best.pt, 124.4MB\n", "Optimizer stripped from runs/train/exp/weights/best.pt, 124.4MB\n",
"\n", "\n",
"Validating runs/train/exp/weights/best.pt...\n", "Validating runs/train/exp/weights/best.pt...\n",
"Fusing layers... \n", "Fusing layers... \n",
"Model Summary: 261 layers, 61922845 parameters, 0 gradients, 156.1 GFLOPs\n", "Model Summary: 261 layers, 61922845 parameters, 0 gradients, 155.9 GFLOPs\n",
" Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:02<00:00, 1.36it/s]\n", " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:04<00:00, 1.11s/it]\n",
" all 128 929 0.746 0.77 0.827 0.589\n", " all 128 929 0.733 0.755 0.814 0.583\n",
" person 128 254 0.862 0.787 0.863 0.624\n", " person 128 254 0.827 0.803 0.861 0.627\n",
" bicycle 128 6 0.723 0.667 0.723 0.47\n", " bicycle 128 6 0.534 0.58 0.586 0.386\n",
" car 128 46 0.851 0.435 0.681 0.305\n", " car 128 46 0.847 0.565 0.688 0.331\n",
" motorcycle 128 5 0.816 1 0.962 0.784\n", " motorcycle 128 5 0.776 1 0.995 0.817\n",
" airplane 128 6 0.916 1 0.995 0.786\n", " airplane 128 6 0.915 1 0.995 0.837\n",
" bus 128 7 1 0.684 0.937 0.797\n", " bus 128 7 1 0.764 0.978 0.817\n",
" train 128 3 0.989 1 0.995 0.863\n", " train 128 3 0.844 1 0.995 0.797\n",
" truck 128 12 0.728 0.5 0.61 0.414\n", " truck 128 12 0.644 0.583 0.649 0.417\n",
" boat 128 6 0.7 0.5 0.582 0.337\n", " boat 128 6 0.6 0.501 0.695 0.493\n",
" traffic light 128 14 1 0.452 0.58 0.268\n", " traffic light 128 14 0.854 0.429 0.539 0.276\n",
" stop sign 128 2 0.712 1 0.995 0.747\n", " stop sign 128 2 0.723 1 0.995 0.796\n",
" bench 128 9 0.793 0.853 0.848 0.507\n", " bench 128 9 1 0.657 0.796 0.369\n",
" bird 128 16 0.966 1 0.995 0.655\n", " bird 128 16 0.962 1 0.995 0.672\n",
" cat 128 4 0.862 1 0.995 0.958\n", " cat 128 4 0.751 1 0.995 0.933\n",
" dog 128 9 0.787 1 0.995 0.774\n", " dog 128 9 0.773 1 0.955 0.746\n",
" horse 128 2 0.695 1 0.995 0.697\n", " horse 128 2 0.638 1 0.995 0.623\n",
" elephant 128 17 0.938 0.894 0.943 0.767\n", " elephant 128 17 0.995 0.941 0.947 0.782\n",
" bear 128 1 0.672 1 0.995 0.895\n", " bear 128 1 0.604 1 0.995 0.895\n",
" zebra 128 4 0.869 1 0.995 0.995\n", " zebra 128 4 0.863 1 0.995 0.946\n",
" giraffe 128 9 0.942 1 0.995 0.733\n", " giraffe 128 9 0.962 1 0.995 0.822\n",
" backpack 128 6 0.668 0.67 0.754 0.505\n", " backpack 128 6 0.874 0.667 0.714 0.486\n",
" umbrella 128 18 0.893 0.889 0.948 0.646\n", " umbrella 128 18 0.792 0.833 0.867 0.564\n",
" handbag 128 19 0.71 0.526 0.55 0.336\n", " handbag 128 19 0.644 0.526 0.544 0.359\n",
" tie 128 7 0.905 0.857 0.857 0.6\n", " tie 128 7 0.872 0.857 0.858 0.604\n",
" suitcase 128 4 0.857 1 0.995 0.722\n", " suitcase 128 4 0.61 1 0.995 0.672\n",
" frisbee 128 5 0.729 0.8 0.761 0.658\n", " frisbee 128 5 0.717 0.8 0.76 0.61\n",
" skis 128 1 0.685 1 0.995 0.497\n", " skis 128 1 0.672 1 0.995 0.597\n",
" snowboard 128 7 0.923 0.714 0.824 0.628\n", " snowboard 128 7 0.852 0.829 0.873 0.632\n",
" sports ball 128 6 0.565 0.667 0.712 0.435\n", " sports ball 128 6 0.766 0.833 0.78 0.559\n",
" kite 128 10 0.668 0.6 0.671 0.188\n", " kite 128 10 0.377 0.6 0.57 0.172\n",
" baseball bat 128 4 0.663 1 0.945 0.422\n", " baseball bat 128 4 0.637 0.888 0.912 0.365\n",
" baseball glove 128 7 0.697 0.663 0.649 0.331\n", " baseball glove 128 7 0.512 0.571 0.597 0.428\n",
" skateboard 128 5 0.792 0.8 0.766 0.455\n", " skateboard 128 5 0.625 0.8 0.803 0.427\n",
" tennis racket 128 7 0.862 0.714 0.718 0.359\n", " tennis racket 128 7 0.776 0.714 0.718 0.36\n",
" bottle 128 18 0.69 0.722 0.764 0.497\n", " bottle 128 18 0.744 0.889 0.741 0.482\n",
" wine glass 128 16 0.759 0.875 0.891 0.559\n", " wine glass 128 16 0.82 0.688 0.888 0.494\n",
" cup 128 36 0.865 0.889 0.916 0.635\n", " cup 128 36 0.801 0.889 0.884 0.628\n",
" fork 128 6 0.671 0.5 0.76 0.474\n", " fork 128 6 0.565 0.5 0.596 0.418\n",
" knife 128 16 0.751 0.812 0.842 0.512\n", " knife 128 16 0.829 0.812 0.822 0.519\n",
" spoon 128 22 0.832 0.636 0.687 0.473\n", " spoon 128 22 0.593 0.5 0.583 0.397\n",
" bowl 128 28 0.873 0.75 0.774 0.625\n", " bowl 128 28 0.869 0.75 0.798 0.635\n",
" banana 128 1 0.767 1 0.995 0.597\n", " banana 128 1 0.694 1 0.995 0.895\n",
" sandwich 128 2 0.134 0.134 0.448 0.408\n", " sandwich 128 2 0 0 0.497 0.202\n",
" orange 128 4 0.534 1 0.995 0.746\n", " orange 128 4 1 0.679 0.888 0.691\n",
" broccoli 128 11 0.474 0.364 0.36 0.3\n", " broccoli 128 11 0.449 0.364 0.469 0.353\n",
" carrot 128 24 0.762 0.75 0.861 0.573\n", " carrot 128 24 0.727 0.777 0.814 0.526\n",
" hot dog 128 2 0.561 1 0.995 0.995\n", " hot dog 128 2 0.56 1 0.828 0.828\n",
" pizza 128 5 0.893 1 0.995 0.771\n", " pizza 128 5 0.722 1 0.962 0.689\n",
" donut 128 14 0.735 1 0.959 0.903\n", " donut 128 14 0.716 1 0.973 0.875\n",
" cake 128 4 0.711 1 0.995 0.908\n", " cake 128 4 0.714 1 0.995 0.871\n",
" chair 128 35 0.639 0.771 0.793 0.505\n", " chair 128 35 0.65 0.857 0.856 0.546\n",
" couch 128 6 0.702 0.667 0.796 0.599\n", " couch 128 6 0.983 0.833 0.899 0.583\n",
" potted plant 128 14 0.697 0.714 0.827 0.555\n", " potted plant 128 14 0.832 0.857 0.92 0.567\n",
" bed 128 3 1 1 0.995 0.643\n", " bed 128 3 0.474 0.316 0.608 0.487\n",
" dining table 128 13 0.566 0.403 0.521 0.32\n", " dining table 128 13 0.663 0.615 0.666 0.4\n",
" toilet 128 2 0.8 1 0.995 0.945\n", " toilet 128 2 0.744 1 0.995 0.896\n",
" tv 128 2 0.473 1 0.995 0.821\n", " tv 128 2 0.685 1 0.995 0.846\n",
" laptop 128 3 0.507 0.347 0.72 0.481\n", " laptop 128 3 1 0 0.913 0.445\n",
" mouse 128 2 1 0 0.828 0.5\n", " mouse 128 2 0.962 0.5 0.745 0.35\n",
" remote 128 8 0.845 0.625 0.751 0.628\n", " remote 128 8 0.856 0.625 0.712 0.581\n",
" cell phone 128 8 0.503 0.375 0.571 0.35\n", " cell phone 128 8 0.598 0.5 0.637 0.386\n",
" microwave 128 3 0.643 1 0.995 0.816\n", " microwave 128 3 0.723 1 0.995 0.852\n",
" oven 128 5 0.47 0.6 0.615 0.465\n", " oven 128 5 0.556 0.6 0.499 0.379\n",
" sink 128 6 0.403 0.333 0.465 0.32\n", " sink 128 6 0.549 0.416 0.528 0.31\n",
" refrigerator 128 5 0.923 0.8 0.862 0.659\n", " refrigerator 128 5 0.6 0.8 0.845 0.587\n",
" book 128 29 0.552 0.241 0.354 0.161\n", " book 128 29 0.552 0.276 0.411 0.216\n",
" clock 128 9 0.915 1 0.995 0.8\n", " clock 128 9 0.731 1 0.975 0.798\n",
" vase 128 2 0.44 1 0.663 0.622\n", " vase 128 2 0.588 1 0.995 0.995\n",
" scissors 128 1 0.634 1 0.995 0.0995\n", " scissors 128 1 1 0 0.332 0.0663\n",
" teddy bear 128 21 0.874 0.658 0.926 0.621\n", " teddy bear 128 21 0.898 0.838 0.934 0.631\n",
" toothbrush 128 5 0.902 1 0.995 0.794\n", " toothbrush 128 5 0.791 1 0.995 0.754\n",
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n" "Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
] ]
} }
@ -888,21 +873,6 @@
"# 4. Visualize" "# 4. Visualize"
] ]
}, },
{
"cell_type": "markdown",
"metadata": {
"id": "DLI1JmHU7B0l"
},
"source": [
"## Weights & Biases Logging 🌟 NEW\n",
"\n",
"[Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_notebook) (W&B) is now integrated with YOLOv3 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration for teams. To enable W&B `pip install wandb`, and then train normally (you will be guided through setup on first use). \n",
"\n",
"During training you will see live updates at [https://wandb.ai/home](https://wandb.ai/home?utm_campaign=repo_yolo_notebook), and you can create and share detailed [Reports](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY) of your results. For more information see the [YOLOv5 Weights & Biases Tutorial](https://github.com/ultralytics/yolov5/issues/1289). \n",
"\n",
"<p align=\"left\"><img width=\"900\" alt=\"Weights & Biases dashboard\" src=\"https://user-images.githubusercontent.com/26833433/135390767-c28b050f-8455-4004-adb0-3b730386e2b2.png\"></p>"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"metadata": { "metadata": {
@ -1080,4 +1050,4 @@
"outputs": [] "outputs": []
} }
] ]
} }