diff --git a/tutorial.ipynb b/tutorial.ipynb
index 1f537c516ede..664cbc156082 100644
--- a/tutorial.ipynb
+++ b/tutorial.ipynb
@@ -16,7 +16,7 @@
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
- "d90eeb56398f458086e3b2b41dbd9fec": {
+ "572de771c7b34c1481def33bd5ed690d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
@@ -31,14 +31,14 @@
"_view_name": "HBoxView",
"box_style": "",
"children": [
- "IPY_MODEL_d91d8347f17349a4987cea29eac0a49c",
- "IPY_MODEL_8f4ffda703ac4348ab7edf1d12a188e1",
- "IPY_MODEL_8c2d91f564de45f8a403386eeeccac27"
+ "IPY_MODEL_20c89dc0d82a4bdf8756bf5e34152292",
+ "IPY_MODEL_61026f684725441db2a640e531807675",
+ "IPY_MODEL_8d2e16d90e13449598d7b3fac75f78a3"
],
- "layout": "IPY_MODEL_5dd95d3eda8b49f7910620edcdcbdcdc"
+ "layout": "IPY_MODEL_a09d90f1bd374ece9a29bc6cfe07c072"
}
},
- "d91d8347f17349a4987cea29eac0a49c": {
+ "20c89dc0d82a4bdf8756bf5e34152292": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
@@ -53,13 +53,13 @@
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
- "layout": "IPY_MODEL_520e5b7e80eb450188261cffbc574d25",
+ "layout": "IPY_MODEL_801e720897804703b4d32f99f84cc3b8",
"placeholder": "",
- "style": "IPY_MODEL_3cef138c5f7743858bb0f87b65dd3c76",
+ "style": "IPY_MODEL_c9fb2e268cc94d508d909b3b72ac9df3",
"value": "100%"
}
},
- "8f4ffda703ac4348ab7edf1d12a188e1": {
+ "61026f684725441db2a640e531807675": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
@@ -75,15 +75,15 @@
"bar_style": "success",
"description": "",
"description_tooltip": null,
- "layout": "IPY_MODEL_c3782c6dda80400ba7f8c5345624bf87",
+ "layout": "IPY_MODEL_bfbc16e88df24fae93e8c80538e78273",
"max": 818322941,
"min": 0,
"orientation": "horizontal",
- "style": "IPY_MODEL_11415bab172a4904b73e29ff60f6fce1",
+ "style": "IPY_MODEL_d9ffa50bddb7455ca4d67ec220c4a10c",
"value": 818322941
}
},
- "8c2d91f564de45f8a403386eeeccac27": {
+ "8d2e16d90e13449598d7b3fac75f78a3": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
@@ -98,13 +98,13 @@
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
- "layout": "IPY_MODEL_eac18040908042dbae67a47d23e95b47",
+ "layout": "IPY_MODEL_8be83ee30f804775aa55aeb021bf515b",
"placeholder": "",
- "style": "IPY_MODEL_e0fc1d6eb478469c9098aa9518d7b358",
- "value": " 780M/780M [01:17<00:00, 17.7MB/s]"
+ "style": "IPY_MODEL_78e5b8dba72942bfacfee54ceec53784",
+ "value": " 780M/780M [01:28<00:00, 9.08MB/s]"
}
},
- "5dd95d3eda8b49f7910620edcdcbdcdc": {
+ "a09d90f1bd374ece9a29bc6cfe07c072": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
@@ -156,7 +156,7 @@
"width": null
}
},
- "520e5b7e80eb450188261cffbc574d25": {
+ "801e720897804703b4d32f99f84cc3b8": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
@@ -208,7 +208,7 @@
"width": null
}
},
- "3cef138c5f7743858bb0f87b65dd3c76": {
+ "c9fb2e268cc94d508d909b3b72ac9df3": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
@@ -223,7 +223,7 @@
"description_width": ""
}
},
- "c3782c6dda80400ba7f8c5345624bf87": {
+ "bfbc16e88df24fae93e8c80538e78273": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
@@ -275,7 +275,7 @@
"width": null
}
},
- "11415bab172a4904b73e29ff60f6fce1": {
+ "d9ffa50bddb7455ca4d67ec220c4a10c": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
@@ -291,7 +291,7 @@
"description_width": ""
}
},
- "eac18040908042dbae67a47d23e95b47": {
+ "8be83ee30f804775aa55aeb021bf515b": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
@@ -343,7 +343,7 @@
"width": null
}
},
- "e0fc1d6eb478469c9098aa9518d7b358": {
+ "78e5b8dba72942bfacfee54ceec53784": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
@@ -369,7 +369,7 @@
"colab_type": "text"
},
"source": [
- ""
+ ""
]
},
{
@@ -403,7 +403,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
- "outputId": "ebf225bd-e109-4dbd-8561-3b15514ca47c"
+ "outputId": "4bf03330-c2e8-43ec-c5da-b7f5e0b2b123"
},
"source": [
"!git clone https://github.com/ultralytics/yolov5 # clone\n",
@@ -420,14 +420,14 @@
"output_type": "stream",
"name": "stderr",
"text": [
- "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
+ "YOLOv5 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
- "Setup complete ✅ (8 CPUs, 51.0 GB RAM, 38.2/166.8 GB disk)\n"
+ "Setup complete ✅ (8 CPUs, 51.0 GB RAM, 38.8/166.8 GB disk)\n"
]
}
]
@@ -460,7 +460,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
- "outputId": "2f43338d-f533-4277-ef9f-b37b565e2702"
+ "outputId": "1d1bb361-c8f3-4ddd-8a19-864bb993e7ac"
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images\n",
@@ -473,16 +473,16 @@
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov5s.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/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n",
- "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
+ "YOLOv5 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt to yolov5s.pt...\n",
- "100% 14.1M/14.1M [00:00<00:00, 220MB/s]\n",
+ "100% 14.1M/14.1M [00:00<00:00, 225MB/s]\n",
"\n",
"Fusing layers... \n",
"YOLOv5s summary: 213 layers, 7225885 parameters, 0 gradients\n",
- "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.012s)\n",
- "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.013s)\n",
- "Speed: 0.5ms pre-process, 12.5ms inference, 17.3ms NMS per image at shape (1, 3, 640, 640)\n",
+ "image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.013s)\n",
+ "image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.015s)\n",
+ "Speed: 0.6ms pre-process, 14.1ms inference, 23.9ms NMS per image at shape (1, 3, 640, 640)\n",
"Results saved to \u001b[1mruns/detect/exp\u001b[0m\n"
]
}
@@ -526,20 +526,20 @@
"base_uri": "https://localhost:8080/",
"height": 49,
"referenced_widgets": [
- "d90eeb56398f458086e3b2b41dbd9fec",
- "d91d8347f17349a4987cea29eac0a49c",
- "8f4ffda703ac4348ab7edf1d12a188e1",
- "8c2d91f564de45f8a403386eeeccac27",
- "5dd95d3eda8b49f7910620edcdcbdcdc",
- "520e5b7e80eb450188261cffbc574d25",
- "3cef138c5f7743858bb0f87b65dd3c76",
- "c3782c6dda80400ba7f8c5345624bf87",
- "11415bab172a4904b73e29ff60f6fce1",
- "eac18040908042dbae67a47d23e95b47",
- "e0fc1d6eb478469c9098aa9518d7b358"
+ "572de771c7b34c1481def33bd5ed690d",
+ "20c89dc0d82a4bdf8756bf5e34152292",
+ "61026f684725441db2a640e531807675",
+ "8d2e16d90e13449598d7b3fac75f78a3",
+ "a09d90f1bd374ece9a29bc6cfe07c072",
+ "801e720897804703b4d32f99f84cc3b8",
+ "c9fb2e268cc94d508d909b3b72ac9df3",
+ "bfbc16e88df24fae93e8c80538e78273",
+ "d9ffa50bddb7455ca4d67ec220c4a10c",
+ "8be83ee30f804775aa55aeb021bf515b",
+ "78e5b8dba72942bfacfee54ceec53784"
]
},
- "outputId": "26f3c005-cc13-4b7c-8523-844b56a0b0e3"
+ "outputId": "47c358af-138d-42d9-ca89-4364283df9e3"
},
"source": [
"# Download COCO val\n",
@@ -557,7 +557,7 @@
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
- "model_id": "d90eeb56398f458086e3b2b41dbd9fec"
+ "model_id": "572de771c7b34c1481def33bd5ed690d"
}
},
"metadata": {}
@@ -571,7 +571,7 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
- "outputId": "c73097d6-02a8-43af-9962-ba6500b793ff"
+ "outputId": "979fe4c2-a058-44de-b401-3cb67878a1b9"
},
"source": [
"# Run YOLOv5x on COCO val\n",
@@ -584,35 +584,35 @@
"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=, workers=8, 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, dnn=False\n",
- "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
+ "YOLOv5 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
"\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5x.pt to yolov5x.pt...\n",
- "100% 166M/166M [00:05<00:00, 33.5MB/s]\n",
+ "100% 166M/166M [00:04<00:00, 39.4MB/s]\n",
"\n",
"Fusing layers... \n",
"YOLOv5x summary: 444 layers, 86705005 parameters, 0 gradients\n",
"Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n",
- "100% 755k/755k [00:00<00:00, 49.6MB/s]\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 [00:00<00:00, 10667.19it/s]\n",
+ "100% 755k/755k [00:00<00:00, 47.9MB/s]\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 [00:00<00:00, 8742.34it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /content/datasets/coco/val2017.cache\n",
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [00:58<00:00, 2.70it/s]\n",
- " all 5000 36335 0.743 0.626 0.683 0.496\n",
- "Speed: 0.1ms pre-process, 4.8ms inference, 1.2ms NMS per image at shape (32, 3, 640, 640)\n",
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 157/157 [01:11<00:00, 2.21it/s]\n",
+ " all 5000 36335 0.743 0.625 0.683 0.504\n",
+ "Speed: 0.1ms pre-process, 4.9ms inference, 1.2ms 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",
- "Done (t=0.38s)\n",
+ "Done (t=0.42s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
- "DONE (t=5.42s)\n",
+ "DONE (t=4.91s)\n",
"creating index...\n",
"index created!\n",
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
- "DONE (t=72.67s).\n",
+ "DONE (t=77.89s).\n",
"Accumulating evaluation results...\n",
- "DONE (t=13.48s).\n",
+ "DONE (t=15.36s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.506\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.688\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.549\n",
@@ -731,13 +731,13 @@
"colab": {
"base_uri": "https://localhost:8080/"
},
- "outputId": "6735ae8b-fd75-4ecd-9d32-71d1881e2481"
+ "outputId": "be9424b5-34d6-4de0-e951-2c5ae334721e"
},
"source": [
"# Train YOLOv5s on COCO128 for 3 epochs\n",
"!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache"
],
- "execution_count": 5,
+ "execution_count": 7,
"outputs": [
{
"output_type": "stream",
@@ -745,17 +745,12 @@
"text": [
"\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov5s.pt, cfg=, data=coco128.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, name=exp, exist_ok=False, quad=False, cos_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/yolov5 ✅\n",
- "YOLOv5 🚀 v6.1-174-gc4cb7c6 torch 1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\n",
+ "YOLOv5 🚀 v6.1-257-g669f707 Python-3.7.13 torch-1.11.0+cu113 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)\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[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",
"\n",
- "Dataset not found ⚠, missing 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, 41.0MB/s]\n",
- "Dataset download success ✅ (0.9s), saved to \u001b[1m/content/datasets\u001b[0m\n",
- "\n",
" from n params module arguments \n",
" 0 -1 1 3520 models.common.Conv [3, 32, 6, 2, 2] \n",
" 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n",
@@ -782,17 +777,17 @@
" 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: 270 layers, 7235389 parameters, 7235389 gradients\n",
"\n",
"Transferred 349/349 items from yolov5s.pt\n",
+ "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
"Scaled weight_decay = 0.0005\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 57 weight (no decay), 60 weight, 60 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 '/content/datasets/coco128/labels/train2017' images and labels...128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00<00:00, 405.04it/s]\n",
- "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /content/datasets/coco128/labels/train2017.cache\n",
- "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 977.19it/s]\n",
+ "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupt: 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, 978.19it/s]\n",
"\u001b[34m\u001b[1mval: \u001b[0mScanning '/content/datasets/coco128/labels/train2017.cache' images and labels... 128 found, 0 missing, 2 empty, 0 corrupt: 100% 128/128 [00:00, ?it/s]\n",
- "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 219.82it/s]\n",
+ "\u001b[34m\u001b[1mval: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 207.08it/s]\n",
"Plotting labels to runs/train/exp/labels.jpg... \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",
@@ -802,19 +797,19 @@
"Starting training for 3 epochs...\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
- " 0/2 3.72G 0.04609 0.06259 0.01898 260 640: 100% 8/8 [00:03<00:00, 2.30it/s]\n",
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 6.54it/s]\n",
- " all 128 929 0.727 0.63 0.717 0.469\n",
+ " 0/2 3.72G 0.04609 0.06258 0.01898 260 640: 100% 8/8 [00:03<00:00, 2.38it/s]\n",
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.45it/s]\n",
+ " all 128 929 0.724 0.638 0.718 0.477\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
- " 1/2 4.57G 0.04466 0.06904 0.01721 210 640: 100% 8/8 [00:00<00:00, 8.54it/s]\n",
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 6.79it/s]\n",
- " all 128 929 0.76 0.646 0.746 0.48\n",
+ " 1/2 4.57G 0.04466 0.06904 0.01721 210 640: 100% 8/8 [00:00<00:00, 8.21it/s]\n",
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.62it/s]\n",
+ " all 128 929 0.732 0.658 0.746 0.488\n",
"\n",
" Epoch gpu_mem box obj cls labels img_size\n",
- " 2/2 4.57G 0.04489 0.06446 0.01634 269 640: 100% 8/8 [00:00<00:00, 9.18it/s]\n",
- " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 6.04it/s]\n",
- " all 128 929 0.807 0.641 0.76 0.494\n",
+ " 2/2 4.57G 0.04489 0.06445 0.01634 269 640: 100% 8/8 [00:00<00:00, 9.12it/s]\n",
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:00<00:00, 4.59it/s]\n",
+ " all 128 929 0.783 0.652 0.758 0.502\n",
"\n",
"3 epochs completed in 0.003 hours.\n",
"Optimizer stripped from runs/train/exp/weights/last.pt, 14.9MB\n",
@@ -822,80 +817,80 @@
"\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, 1.31it/s]\n",
- " all 128 929 0.809 0.642 0.76 0.493\n",
- " person 128 254 0.872 0.693 0.82 0.519\n",
- " bicycle 128 6 0.75 0.501 0.623 0.376\n",
- " car 128 46 0.666 0.521 0.557 0.207\n",
- " motorcycle 128 5 1 0.919 0.995 0.678\n",
- " airplane 128 6 0.948 1 0.995 0.751\n",
- " bus 128 7 0.84 0.714 0.723 0.642\n",
- " train 128 3 1 0.631 0.863 0.561\n",
- " truck 128 12 0.638 0.417 0.481 0.241\n",
- " boat 128 6 1 0.299 0.418 0.0863\n",
- " traffic light 128 14 0.637 0.254 0.372 0.225\n",
- " stop sign 128 2 0.812 1 0.995 0.796\n",
- " bench 128 9 0.737 0.444 0.615 0.233\n",
- " bird 128 16 0.965 1 0.995 0.666\n",
- " cat 128 4 0.856 1 0.995 0.797\n",
- " dog 128 9 1 0.65 0.886 0.637\n",
- " horse 128 2 0.822 1 0.995 0.647\n",
- " elephant 128 17 0.963 0.882 0.932 0.69\n",
- " bear 128 1 0.699 1 0.995 0.895\n",
- " zebra 128 4 0.877 1 0.995 0.947\n",
- " giraffe 128 9 0.898 1 0.995 0.644\n",
- " backpack 128 6 0.994 0.667 0.808 0.333\n",
- " umbrella 128 18 0.828 0.667 0.865 0.493\n",
- " handbag 128 19 0.882 0.211 0.357 0.175\n",
- " tie 128 7 0.834 0.719 0.837 0.493\n",
- " suitcase 128 4 0.853 1 0.995 0.522\n",
- " frisbee 128 5 0.706 0.8 0.8 0.74\n",
- " skis 128 1 0.796 1 0.995 0.398\n",
- " snowboard 128 7 0.903 0.714 0.852 0.546\n",
- " sports ball 128 6 0.621 0.667 0.603 0.293\n",
- " kite 128 10 0.846 0.553 0.625 0.259\n",
- " baseball bat 128 4 0.465 0.25 0.384 0.163\n",
- " baseball glove 128 7 0.731 0.429 0.466 0.304\n",
- " skateboard 128 5 1 0.557 0.858 0.49\n",
- " tennis racket 128 7 0.78 0.429 0.635 0.298\n",
- " bottle 128 18 0.55 0.339 0.578 0.283\n",
- " wine glass 128 16 0.7 0.938 0.925 0.499\n",
- " cup 128 36 0.802 0.789 0.844 0.492\n",
- " fork 128 6 1 0.326 0.439 0.302\n",
- " knife 128 16 0.779 0.5 0.68 0.392\n",
- " spoon 128 22 0.821 0.417 0.629 0.338\n",
- " bowl 128 28 0.781 0.607 0.753 0.51\n",
- " banana 128 1 0.923 1 0.995 0.0995\n",
+ "Model summary: 213 layers, 7225885 parameters, 0 gradients\n",
+ " Class Images Labels P R mAP@.5 mAP@.5:.95: 100% 4/4 [00:03<00:00, 1.27it/s]\n",
+ " all 128 929 0.785 0.653 0.761 0.503\n",
+ " person 128 254 0.866 0.71 0.82 0.531\n",
+ " bicycle 128 6 0.764 0.546 0.62 0.375\n",
+ " car 128 46 0.615 0.556 0.565 0.211\n",
+ " motorcycle 128 5 1 0.952 0.995 0.761\n",
+ " airplane 128 6 0.937 1 0.995 0.751\n",
+ " bus 128 7 0.816 0.714 0.723 0.642\n",
+ " train 128 3 0.985 0.667 0.863 0.561\n",
+ " truck 128 12 0.553 0.417 0.481 0.258\n",
+ " boat 128 6 1 0.317 0.418 0.132\n",
+ " traffic light 128 14 0.668 0.287 0.372 0.227\n",
+ " stop sign 128 2 0.789 1 0.995 0.796\n",
+ " bench 128 9 0.691 0.444 0.614 0.265\n",
+ " bird 128 16 0.955 1 0.995 0.666\n",
+ " cat 128 4 0.811 1 0.995 0.797\n",
+ " dog 128 9 1 0.657 0.886 0.637\n",
+ " horse 128 2 0.806 1 0.995 0.647\n",
+ " elephant 128 17 0.955 0.882 0.932 0.691\n",
+ " bear 128 1 0.681 1 0.995 0.895\n",
+ " zebra 128 4 0.87 1 0.995 0.947\n",
+ " giraffe 128 9 0.881 1 0.995 0.734\n",
+ " backpack 128 6 0.926 0.667 0.808 0.359\n",
+ " umbrella 128 18 0.811 0.667 0.864 0.507\n",
+ " handbag 128 19 0.768 0.211 0.352 0.183\n",
+ " tie 128 7 0.778 0.714 0.822 0.495\n",
+ " suitcase 128 4 0.805 1 0.995 0.534\n",
+ " frisbee 128 5 0.697 0.8 0.8 0.74\n",
+ " skis 128 1 0.734 1 0.995 0.4\n",
+ " snowboard 128 7 0.859 0.714 0.852 0.563\n",
+ " sports ball 128 6 0.612 0.667 0.603 0.328\n",
+ " kite 128 10 0.855 0.592 0.624 0.249\n",
+ " baseball bat 128 4 0.403 0.25 0.401 0.171\n",
+ " baseball glove 128 7 0.7 0.429 0.467 0.323\n",
+ " skateboard 128 5 1 0.57 0.862 0.512\n",
+ " tennis racket 128 7 0.753 0.429 0.635 0.327\n",
+ " bottle 128 18 0.59 0.4 0.578 0.293\n",
+ " wine glass 128 16 0.654 1 0.925 0.503\n",
+ " cup 128 36 0.77 0.806 0.845 0.521\n",
+ " fork 128 6 0.988 0.333 0.44 0.312\n",
+ " knife 128 16 0.755 0.579 0.684 0.404\n",
+ " spoon 128 22 0.827 0.436 0.629 0.354\n",
+ " bowl 128 28 0.784 0.648 0.753 0.528\n",
+ " banana 128 1 0.802 1 0.995 0.108\n",
" sandwich 128 2 1 0 0.606 0.545\n",
- " orange 128 4 0.959 1 0.995 0.691\n",
- " broccoli 128 11 0.483 0.455 0.466 0.337\n",
- " carrot 128 24 0.85 0.542 0.73 0.506\n",
- " hot dog 128 2 0.587 1 0.828 0.712\n",
- " pizza 128 5 0.882 0.8 0.962 0.687\n",
- " donut 128 14 0.702 1 0.981 0.846\n",
- " cake 128 4 0.875 1 0.995 0.858\n",
- " chair 128 35 0.639 0.608 0.624 0.303\n",
- " couch 128 6 1 0.592 0.857 0.539\n",
- " potted plant 128 14 0.76 0.786 0.835 0.471\n",
- " bed 128 3 1 0 0.806 0.557\n",
- " dining table 128 13 0.824 0.362 0.602 0.403\n",
- " toilet 128 2 0.978 1 0.995 0.846\n",
- " tv 128 2 0.702 1 0.995 0.796\n",
+ " orange 128 4 0.921 1 0.995 0.691\n",
+ " broccoli 128 11 0.379 0.455 0.468 0.338\n",
+ " carrot 128 24 0.777 0.542 0.73 0.503\n",
+ " hot dog 128 2 0.562 1 0.828 0.712\n",
+ " pizza 128 5 0.802 0.814 0.962 0.694\n",
+ " donut 128 14 0.694 1 0.981 0.848\n",
+ " cake 128 4 0.864 1 0.995 0.858\n",
+ " chair 128 35 0.636 0.648 0.628 0.319\n",
+ " couch 128 6 1 0.606 0.857 0.555\n",
+ " potted plant 128 14 0.739 0.786 0.837 0.476\n",
+ " bed 128 3 1 0 0.806 0.568\n",
+ " dining table 128 13 0.862 0.483 0.602 0.405\n",
+ " toilet 128 2 0.941 1 0.995 0.846\n",
+ " tv 128 2 0.677 1 0.995 0.796\n",
" laptop 128 3 1 0 0.83 0.532\n",
" mouse 128 2 1 0 0.0931 0.0466\n",
- " remote 128 8 1 0.6 0.659 0.534\n",
- " cell phone 128 8 0.712 0.25 0.439 0.204\n",
- " microwave 128 3 0.811 1 0.995 0.734\n",
- " oven 128 5 0.46 0.4 0.44 0.29\n",
- " sink 128 6 0.359 0.167 0.302 0.211\n",
- " refrigerator 128 5 0.657 0.8 0.804 0.532\n",
- " book 128 29 0.624 0.207 0.298 0.165\n",
- " clock 128 9 0.798 0.889 0.888 0.692\n",
- " vase 128 2 0.495 1 0.995 0.92\n",
+ " remote 128 8 1 0.612 0.659 0.534\n",
+ " cell phone 128 8 0.645 0.25 0.437 0.227\n",
+ " microwave 128 3 0.797 1 0.995 0.734\n",
+ " oven 128 5 0.435 0.4 0.44 0.29\n",
+ " sink 128 6 0.345 0.167 0.301 0.211\n",
+ " refrigerator 128 5 0.645 0.8 0.804 0.545\n",
+ " book 128 29 0.603 0.207 0.301 0.171\n",
+ " clock 128 9 0.785 0.889 0.888 0.734\n",
+ " vase 128 2 0.477 1 0.995 0.92\n",
" scissors 128 1 1 0 0.995 0.199\n",
- " teddy bear 128 21 0.871 0.646 0.826 0.527\n",
- " toothbrush 128 5 0.828 1 0.962 0.647\n",
+ " teddy bear 128 21 0.862 0.667 0.823 0.549\n",
+ " toothbrush 128 5 0.809 1 0.995 0.65\n",
"Results saved to \u001b[1mruns/train/exp\u001b[0m\n"
]
}