diff --git a/examples/tutorial.ipynb b/examples/tutorial.ipynb index b3e31c5..13dcf05 100644 --- a/examples/tutorial.ipynb +++ b/examples/tutorial.ipynb @@ -60,7 +60,7 @@ "base_uri": "https://localhost:8080/", "height": 1000 }, - "outputId": "9012b4cd-53eb-4c84-f5b7-4976d4b4e58a" + "outputId": "5006941e-44ff-4e27-f53e-31bf87221334" }, "source": [ "# Pip install method (recommended)\n", @@ -117,7 +117,7 @@ "# Run inference on an image with YOLOv8n\n", "!yolo task=detect mode=predict model=yolov8n.pt conf=0.25 source='https://ultralytics.com/images/zidane.jpg'" ], - "execution_count": 2, + "execution_count": null, "outputs": [ { "output_type": "stream", @@ -175,14 +175,114 @@ { "cell_type": "code", "metadata": { - "id": "X58w8JLpMnjH" + "id": "X58w8JLpMnjH", + "outputId": "3e8689b5-e6e6-4764-c1d9-2626f53355f2", + "colab": { + "base_uri": "https://localhost:8080/" + } }, "source": [ "# Validate YOLOv8n on COCO128 val\n", "!yolo task=detect mode=val model=yolov8n.pt data=coco128.yaml" ], - "execution_count": null, - "outputs": [] + "execution_count": 2, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Ultralytics YOLOv8.0.5 🚀 Python-3.8.16 torch-1.13.1+cu116 CUDA:0 (Tesla T4, 15110MiB)\n", + "Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt to yolov8n.pt...\n", + "100% 6.24M/6.24M [00:01<00:00, 6.32MB/s]\n", + "\n", + "Fusing layers... \n", + "YOLOv8n summary: 168 layers, 3151904 parameters, 0 gradients, 8.7 GFLOPs\n", + "\n", + "Dataset not found ⚠️, missing paths ['/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, 71.9MB/s]\n", + "Dataset download success ✅ (0.8s), saved to \u001b[1m/datasets\u001b[0m\n", + "Downloading https://ultralytics.com/assets/Arial.ttf to /root/.config/Ultralytics/Arial.ttf...\n", + "100% 755k/755k [00:00<00:00, 44.6MB/s]\n", + "\u001b[34m\u001b[1mval: \u001b[0mScanning /datasets/coco128/labels/train2017... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00<00:00, 1451.73it/s]\n", + "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /datasets/coco128/labels/train2017.cache\n", + " Class Images Instances Box(P R mAP50 mAP50-95): 100% 8/8 [00:05<00:00, 1.53it/s]\n", + " all 128 929 0.64 0.537 0.605 0.446\n", + " person 128 254 0.797 0.677 0.764 0.538\n", + " bicycle 128 6 0.514 0.333 0.315 0.264\n", + " car 128 46 0.813 0.217 0.273 0.168\n", + " motorcycle 128 5 0.687 0.887 0.898 0.685\n", + " airplane 128 6 0.82 0.833 0.927 0.675\n", + " bus 128 7 0.491 0.714 0.728 0.671\n", + " train 128 3 0.534 0.667 0.706 0.604\n", + " truck 128 12 1 0.332 0.473 0.297\n", + " boat 128 6 0.226 0.167 0.316 0.134\n", + " traffic light 128 14 0.734 0.2 0.202 0.139\n", + " stop sign 128 2 1 0.992 0.995 0.701\n", + " bench 128 9 0.839 0.582 0.62 0.365\n", + " bird 128 16 0.921 0.728 0.864 0.51\n", + " cat 128 4 0.875 1 0.995 0.791\n", + " dog 128 9 0.603 0.889 0.785 0.585\n", + " horse 128 2 0.597 1 0.995 0.518\n", + " elephant 128 17 0.849 0.765 0.9 0.679\n", + " bear 128 1 0.593 1 0.995 0.995\n", + " zebra 128 4 0.848 1 0.995 0.965\n", + " giraffe 128 9 0.72 1 0.951 0.722\n", + " backpack 128 6 0.589 0.333 0.376 0.232\n", + " umbrella 128 18 0.804 0.5 0.643 0.414\n", + " handbag 128 19 0.424 0.0526 0.165 0.0889\n", + " tie 128 7 0.804 0.714 0.674 0.476\n", + " suitcase 128 4 0.635 0.883 0.745 0.534\n", + " frisbee 128 5 0.675 0.8 0.759 0.688\n", + " skis 128 1 0.567 1 0.995 0.497\n", + " snowboard 128 7 0.742 0.714 0.747 0.5\n", + " sports ball 128 6 0.716 0.433 0.485 0.278\n", + " kite 128 10 0.817 0.45 0.569 0.184\n", + " baseball bat 128 4 0.551 0.25 0.353 0.175\n", + " baseball glove 128 7 0.624 0.429 0.429 0.293\n", + " skateboard 128 5 0.846 0.6 0.6 0.41\n", + " tennis racket 128 7 0.726 0.387 0.487 0.33\n", + " bottle 128 18 0.448 0.389 0.376 0.208\n", + " wine glass 128 16 0.743 0.362 0.584 0.333\n", + " cup 128 36 0.58 0.278 0.404 0.29\n", + " fork 128 6 0.527 0.167 0.246 0.184\n", + " knife 128 16 0.564 0.5 0.59 0.36\n", + " spoon 128 22 0.597 0.182 0.328 0.19\n", + " bowl 128 28 0.648 0.643 0.618 0.491\n", + " banana 128 1 0 0 0.124 0.0379\n", + " sandwich 128 2 0.249 0.5 0.308 0.308\n", + " orange 128 4 1 0.31 0.995 0.623\n", + " broccoli 128 11 0.374 0.182 0.249 0.203\n", + " carrot 128 24 0.648 0.458 0.572 0.362\n", + " hot dog 128 2 0.351 0.553 0.745 0.721\n", + " pizza 128 5 0.644 1 0.995 0.843\n", + " donut 128 14 0.657 1 0.94 0.864\n", + " cake 128 4 0.618 1 0.945 0.845\n", + " chair 128 35 0.506 0.514 0.442 0.239\n", + " couch 128 6 0.463 0.5 0.706 0.555\n", + " potted plant 128 14 0.65 0.643 0.711 0.472\n", + " bed 128 3 0.698 0.667 0.789 0.625\n", + " dining table 128 13 0.432 0.615 0.485 0.366\n", + " toilet 128 2 0.615 0.5 0.695 0.676\n", + " tv 128 2 0.373 0.62 0.745 0.696\n", + " laptop 128 3 1 0 0.451 0.361\n", + " mouse 128 2 1 0 0.0625 0.00625\n", + " remote 128 8 0.843 0.5 0.605 0.529\n", + " cell phone 128 8 0 0 0.0549 0.0393\n", + " microwave 128 3 0.435 0.667 0.806 0.718\n", + " oven 128 5 0.412 0.4 0.339 0.27\n", + " sink 128 6 0.35 0.167 0.182 0.129\n", + " refrigerator 128 5 0.589 0.4 0.604 0.452\n", + " book 128 29 0.629 0.103 0.346 0.178\n", + " clock 128 9 0.788 0.83 0.875 0.74\n", + " vase 128 2 0.376 1 0.828 0.795\n", + " scissors 128 1 1 0 0.249 0.0746\n", + " teddy bear 128 21 0.877 0.333 0.591 0.394\n", + " toothbrush 128 5 0.743 0.6 0.638 0.374\n", + "Speed: 1.1ms pre-process, 5.7ms inference, 0.0ms loss, 3.7ms post-process per image\n" + ] + } + ] }, { "cell_type": "markdown", @@ -200,14 +300,163 @@ { "cell_type": "code", "metadata": { - "id": "1NcFxRcFdJ_O" + "id": "1NcFxRcFdJ_O", + "outputId": "3e6ce168-7f91-4253-d2f1-84c8254a66ee", + "colab": { + "base_uri": "https://localhost:8080/" + } }, "source": [ "# Train YOLOv8n on COCO128 for 3 epochs\n", "!yolo task=detect mode=train model=yolov8n.pt data=coco128.yaml epochs=3 imgsz=640" ], - "execution_count": null, - "outputs": [] + "execution_count": 3, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Ultralytics YOLOv8.0.5 🚀 Python-3.8.16 torch-1.13.1+cu116 CUDA:0 (Tesla T4, 15110MiB)\n", + "\u001b[34m\u001b[1myolo/engine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8n.pt, data=coco128.yaml, epochs=3, patience=50, batch=16, imgsz=640, save=True, cache=False, device=, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=False, seed=0, deterministic=True, single_cls=False, image_weights=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, show=False, save_txt=False, save_conf=False, save_crop=False, hide_labels=False, hide_conf=False, vid_stride=1, line_thickness=3, visualize=False, augment=False, agnostic_nms=False, retina_masks=False, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=17, workspace=4, nms=False, lr0=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=7.5, cls=0.5, dfl=1.5, fl_gamma=0.0, label_smoothing=0.0, nbs=64, 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, cfg=None, hydra={'output_subdir': None, 'run': {'dir': '.'}}, v5loader=False, save_dir=runs/detect/train\n", + "\n", + " from n params module arguments \n", + " 0 -1 1 464 ultralytics.nn.modules.Conv [3, 16, 3, 2] \n", + " 1 -1 1 4672 ultralytics.nn.modules.Conv [16, 32, 3, 2] \n", + " 2 -1 1 7360 ultralytics.nn.modules.C2f [32, 32, 1, True] \n", + " 3 -1 1 18560 ultralytics.nn.modules.Conv [32, 64, 3, 2] \n", + " 4 -1 2 49664 ultralytics.nn.modules.C2f [64, 64, 2, True] \n", + " 5 -1 1 73984 ultralytics.nn.modules.Conv [64, 128, 3, 2] \n", + " 6 -1 2 197632 ultralytics.nn.modules.C2f [128, 128, 2, True] \n", + " 7 -1 1 295424 ultralytics.nn.modules.Conv [128, 256, 3, 2] \n", + " 8 -1 1 460288 ultralytics.nn.modules.C2f [256, 256, 1, True] \n", + " 9 -1 1 164608 ultralytics.nn.modules.SPPF [256, 256, 5] \n", + " 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", + " 11 [-1, 6] 1 0 ultralytics.nn.modules.Concat [1] \n", + " 12 -1 1 148224 ultralytics.nn.modules.C2f [384, 128, 1] \n", + " 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", + " 14 [-1, 4] 1 0 ultralytics.nn.modules.Concat [1] \n", + " 15 -1 1 37248 ultralytics.nn.modules.C2f [192, 64, 1] \n", + " 16 -1 1 36992 ultralytics.nn.modules.Conv [64, 64, 3, 2] \n", + " 17 [-1, 12] 1 0 ultralytics.nn.modules.Concat [1] \n", + " 18 -1 1 123648 ultralytics.nn.modules.C2f [192, 128, 1] \n", + " 19 -1 1 147712 ultralytics.nn.modules.Conv [128, 128, 3, 2] \n", + " 20 [-1, 9] 1 0 ultralytics.nn.modules.Concat [1] \n", + " 21 -1 1 493056 ultralytics.nn.modules.C2f [384, 256, 1] \n", + " 22 [15, 18, 21] 1 897664 ultralytics.nn.modules.Detect [80, [64, 128, 256]] \n", + "Model summary: 225 layers, 3157200 parameters, 3157184 gradients, 8.9 GFLOPs\n", + "\n", + "Transferred 355/355 items from pretrained weights\n", + "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias\n", + "\u001b[34m\u001b[1mtrain: \u001b[0mScanning /datasets/coco128/labels/train2017.cache... 126 images, 2 backgrounds, 0 corrupt: 100% 128/128 [00:00