{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "c8bdf258",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "New https://pypi.org/project/ultralytics/8.3.172 available 😃 Update with 'pip install -U ultralytics'\n",
      "Ultralytics 8.3.171 🚀 Python-3.12.3 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 3060, 11910MiB)\n",
      "\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, augment=False, auto_augment=randaugment, batch=16, bgr=0.0, box=7.5, cache=False, cfg=None, classes=None, close_mosaic=10, cls=0.5, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=/home/xd/Documents/ML_AI/ui_detection_yolo/data.yml, degrees=0.0, deterministic=True, device=0, dfl=1.5, dnn=False, dropout=0.0, dynamic=False, embed=None, epochs=20, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, half=False, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, int8=False, iou=0.7, keras=False, kobj=1.0, line_width=None, lr0=0.01, lrf=0.01, mask_ratio=4, max_det=300, mixup=0.0, mode=train, model=yolov8n.pt, momentum=0.937, mosaic=1.0, multi_scale=False, name=train5, nbs=64, nms=False, opset=None, optimize=False, optimizer=auto, overlap_mask=True, patience=100, perspective=0.0, plots=True, pose=12.0, pretrained=True, profile=False, project=None, rect=False, resume=False, retina_masks=False, save=True, save_conf=False, save_crop=False, save_dir=runs/detect/train5, save_frames=False, save_json=False, save_period=-1, save_txt=False, scale=0.5, seed=0, shear=0.0, show=False, show_boxes=True, show_conf=True, show_labels=True, simplify=True, single_cls=False, source=None, split=val, stream_buffer=False, task=detect, time=None, tracker=botsort.yaml, translate=0.1, val=True, verbose=True, vid_stride=1, visualize=False, warmup_bias_lr=0.1, warmup_epochs=3.0, warmup_momentum=0.8, weight_decay=0.0005, workers=8, workspace=None\n",
      "Overriding model.yaml nc=80 with nc=21\n",
      "\n",
      "                   from  n    params  module                                       arguments                     \n",
      "  0                  -1  1       464  ultralytics.nn.modules.conv.Conv             [3, 16, 3, 2]                 \n",
      "  1                  -1  1      4672  ultralytics.nn.modules.conv.Conv             [16, 32, 3, 2]                \n",
      "  2                  -1  1      7360  ultralytics.nn.modules.block.C2f             [32, 32, 1, True]             \n",
      "  3                  -1  1     18560  ultralytics.nn.modules.conv.Conv             [32, 64, 3, 2]                \n",
      "  4                  -1  2     49664  ultralytics.nn.modules.block.C2f             [64, 64, 2, True]             \n",
      "  5                  -1  1     73984  ultralytics.nn.modules.conv.Conv             [64, 128, 3, 2]               \n",
      "  6                  -1  2    197632  ultralytics.nn.modules.block.C2f             [128, 128, 2, True]           \n",
      "  7                  -1  1    295424  ultralytics.nn.modules.conv.Conv             [128, 256, 3, 2]              \n",
      "  8                  -1  1    460288  ultralytics.nn.modules.block.C2f             [256, 256, 1, True]           \n",
      "  9                  -1  1    164608  ultralytics.nn.modules.block.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.conv.Concat           [1]                           \n",
      " 12                  -1  1    148224  ultralytics.nn.modules.block.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.conv.Concat           [1]                           \n",
      " 15                  -1  1     37248  ultralytics.nn.modules.block.C2f             [192, 64, 1]                  \n",
      " 16                  -1  1     36992  ultralytics.nn.modules.conv.Conv             [64, 64, 3, 2]                \n",
      " 17            [-1, 12]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
      " 18                  -1  1    123648  ultralytics.nn.modules.block.C2f             [192, 128, 1]                 \n",
      " 19                  -1  1    147712  ultralytics.nn.modules.conv.Conv             [128, 128, 3, 2]              \n",
      " 20             [-1, 9]  1         0  ultralytics.nn.modules.conv.Concat           [1]                           \n",
      " 21                  -1  1    493056  ultralytics.nn.modules.block.C2f             [384, 256, 1]                 \n",
      " 22        [15, 18, 21]  1    755407  ultralytics.nn.modules.head.Detect           [21, [64, 128, 256]]          \n",
      "Model summary: 129 layers, 3,014,943 parameters, 3,014,927 gradients, 8.2 GFLOPs\n",
      "\n",
      "Transferred 319/355 items from pretrained weights\n",
      "Freezing layer 'model.22.dfl.conv.weight'\n",
      "\u001b[34m\u001b[1mAMP: \u001b[0mrunning Automatic Mixed Precision (AMP) checks...\n",
      "\u001b[34m\u001b[1mAMP: \u001b[0mchecks passed ✅\n",
      "\u001b[34m\u001b[1mtrain: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 5872.4±1709.8 MB/s, size: 167.0 KB)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/xd/Documents/ML_AI/ui_detection_yolo/dataset/train/labels... 3845 images, 0 backgrounds, 0 corrupt: 100%|██████████| 3845/3845 [00:03<00:00, 1107.02it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mtrain: \u001b[0m/home/xd/Documents/ML_AI/ui_detection_yolo/dataset/train/images/69825a2b08bd43c7a9ca4fcd3cd8c8c2.jpg: 1 duplicate labels removed\n",
      "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /home/xd/Documents/ML_AI/ui_detection_yolo/dataset/train/labels.cache\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 754.3±135.6 MB/s, size: 109.7 KB)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mval: \u001b[0mScanning /home/xd/Documents/ML_AI/ui_detection_yolo/dataset/val/labels... 481 images, 0 backgrounds, 0 corrupt: 100%|██████████| 481/481 [00:00<00:00, 1961.08it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mval: \u001b[0mNew cache created: /home/xd/Documents/ML_AI/ui_detection_yolo/dataset/val/labels.cache\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Plotting labels to runs/detect/train5/labels.jpg... \n",
      "\u001b[34m\u001b[1moptimizer:\u001b[0m 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... \n",
      "\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.0004, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)\n",
      "Image sizes 640 train, 640 val\n",
      "Using 8 dataloader workers\n",
      "Logging results to \u001b[1mruns/detect/train5\u001b[0m\n",
      "Starting training for 20 epochs...\n",
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       1/20      2.88G      1.154      2.561      1.105         78        640: 100%|██████████| 241/241 [00:30<00:00,  8.00it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00,  8.99it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.827      0.327      0.359      0.282\n",
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       2/20      3.31G     0.8688      1.187     0.9828        103        640: 100%|██████████| 241/241 [00:29<00:00,  8.27it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.55it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.823      0.449      0.501      0.405\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       3/20      3.32G      0.784      1.012     0.9498        119        640: 100%|██████████| 241/241 [00:28<00:00,  8.38it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.34it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.856      0.476      0.519      0.428\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       4/20      3.56G     0.7496     0.9416     0.9344        106        640: 100%|██████████| 241/241 [00:28<00:00,  8.35it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.47it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875       0.85      0.518      0.597      0.508\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       5/20      3.56G     0.7189     0.8863     0.9241        136        640: 100%|██████████| 241/241 [00:28<00:00,  8.38it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.63it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.725       0.59      0.618      0.521\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       6/20      3.57G     0.6922     0.8384     0.9155        144        640: 100%|██████████| 241/241 [00:28<00:00,  8.38it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.61it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.774      0.584      0.635      0.541\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       7/20      3.58G     0.6745     0.8128     0.9085        124        640: 100%|██████████| 241/241 [00:28<00:00,  8.34it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.58it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.769      0.601      0.673      0.576\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       8/20      3.86G     0.6598       0.78     0.9037         87        640: 100%|██████████| 241/241 [00:28<00:00,  8.34it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.48it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.776      0.622      0.682      0.598\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "       9/20      3.86G     0.6381     0.7502     0.8973        162        640: 100%|██████████| 241/241 [00:28<00:00,  8.37it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.77it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.692      0.609      0.654      0.573\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      10/20      3.86G     0.6308     0.7258     0.8911        114        640: 100%|██████████| 241/241 [00:29<00:00,  8.28it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.66it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.721      0.625      0.664      0.582\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Closing dataloader mosaic\n",
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      11/20      3.86G     0.6223     0.7513     0.8781         44        640: 100%|██████████| 241/241 [00:28<00:00,  8.55it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.53it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.716      0.631      0.667      0.583\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      12/20      3.86G     0.6038     0.7067     0.8681         59        640: 100%|██████████| 241/241 [00:27<00:00,  8.71it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.62it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.769      0.633      0.691      0.609\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      13/20      3.86G     0.5843      0.675     0.8647         41        640: 100%|██████████| 241/241 [00:27<00:00,  8.71it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.58it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.759      0.627      0.673      0.597\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      14/20      3.86G     0.5757     0.6552     0.8599         55        640: 100%|██████████| 241/241 [00:27<00:00,  8.71it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.85it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.809      0.639      0.704       0.63\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      15/20      3.86G     0.5684     0.6373      0.857        105        640: 100%|██████████| 241/241 [00:27<00:00,  8.73it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.79it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.764      0.646      0.692      0.619\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      16/20      3.86G     0.5521     0.6189     0.8535         53        640: 100%|██████████| 241/241 [00:27<00:00,  8.68it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.79it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.751      0.623       0.68      0.612\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      17/20      3.86G      0.544     0.6061     0.8504         45        640: 100%|██████████| 241/241 [00:27<00:00,  8.74it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.99it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.753      0.664      0.692      0.624\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      18/20      3.86G      0.548     0.5979     0.8497         56        640: 100%|██████████| 241/241 [00:27<00:00,  8.73it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.85it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.752      0.647      0.689      0.624\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      19/20      3.86G     0.5285       0.58     0.8455         73        640: 100%|██████████| 241/241 [00:27<00:00,  8.74it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 11.85it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.735      0.672      0.691      0.625\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "      Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "      20/20      3.86G      0.525     0.5689     0.8472         72        640: 100%|██████████| 241/241 [00:27<00:00,  8.74it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:01<00:00, 10.56it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.786      0.679      0.707      0.641\n",
      "\n",
      "20 epochs completed in 0.166 hours.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Optimizer stripped from runs/detect/train5/weights/last.pt, 6.2MB\n",
      "Optimizer stripped from runs/detect/train5/weights/best.pt, 6.2MB\n",
      "\n",
      "Validating runs/detect/train5/weights/best.pt...\n",
      "Ultralytics 8.3.171 🚀 Python-3.12.3 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 3060, 11910MiB)\n",
      "Model summary (fused): 72 layers, 3,009,743 parameters, 0 gradients, 8.1 GFLOPs\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 16/16 [00:02<00:00,  7.23it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.786      0.678      0.707       0.64\n",
      "       BackgroundImage         56         56      0.872       0.73      0.875      0.842\n",
      "     Bottom_Navigation          2          2          1          0     0.0326     0.0271\n",
      "                  Card          6         14      0.469      0.786      0.501      0.444\n",
      "       CheckedTextView         23        107      0.837      0.832      0.881        0.7\n",
      "                Drawer         30         30      0.938      0.967      0.993      0.987\n",
      "              EditText        112        246      0.927      0.879      0.945      0.849\n",
      "                  Icon        297       1269      0.883      0.864      0.925      0.759\n",
      "                 Image        370        868      0.781      0.841      0.894      0.833\n",
      "                   Map          1          1          0          0          0          0\n",
      "                 Modal         41         41      0.918      0.854      0.937      0.911\n",
      "             Multi_Tab          3          3          1          0      0.056     0.0474\n",
      "         PageIndicator        151        151      0.971      0.854      0.961      0.715\n",
      "               Spinner          1          1          0          0          0          0\n",
      "                Switch         10         28      0.957      0.929      0.984      0.915\n",
      "                  Text        479       3164      0.932      0.946       0.97      0.839\n",
      "            TextButton        290        493      0.925      0.974      0.976       0.95\n",
      "               Toolbar         26         26      0.747      0.808      0.797      0.783\n",
      "          UpperTaskBar        375        375      0.996      0.949      0.992      0.927\n",
      "Speed: 0.1ms preprocess, 1.0ms inference, 0.0ms loss, 2.3ms postprocess per image\n",
      "Results saved to \u001b[1mruns/detect/train5\u001b[0m\n",
      "Ultralytics 8.3.171 🚀 Python-3.12.3 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 3060, 11910MiB)\n",
      "Model summary (fused): 72 layers, 3,009,743 parameters, 0 gradients, 8.1 GFLOPs\n",
      "\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 4011.9±2287.7 MB/s, size: 279.8 KB)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mval: \u001b[0mScanning /home/xd/Documents/ML_AI/ui_detection_yolo/dataset/val/labels.cache... 481 images, 0 backgrounds, 0 corrupt: 100%|██████████| 481/481 [00:00<?, ?it/s]\n",
      "                 Class     Images  Instances      Box(P          R      mAP50  mAP50-95): 100%|██████████| 31/31 [00:02<00:00, 11.50it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                   all        481       6875      0.786      0.678      0.707      0.645\n",
      "       BackgroundImage         56         56      0.872       0.73      0.878      0.847\n",
      "     Bottom_Navigation          2          2          1          0     0.0326      0.028\n",
      "                  Card          6         14      0.468      0.786      0.502      0.442\n",
      "       CheckedTextView         23        107      0.837      0.832      0.883       0.71\n",
      "                Drawer         30         30      0.934      0.967      0.992      0.989\n",
      "              EditText        112        246      0.927       0.88      0.942      0.847\n",
      "                  Icon        297       1269      0.883      0.864      0.926      0.765\n",
      "                 Image        370        868      0.778      0.842      0.895      0.836\n",
      "                   Map          1          1          0          0          0          0\n",
      "                 Modal         41         41      0.919      0.854      0.939      0.914\n",
      "             Multi_Tab          3          3          1          0      0.056     0.0474\n",
      "         PageIndicator        151        151      0.978      0.854      0.962      0.742\n",
      "               Spinner          1          1          0          0          0          0\n",
      "                Switch         10         28      0.956      0.929      0.984      0.932\n",
      "                  Text        479       3164      0.931      0.944      0.969      0.847\n",
      "            TextButton        290        493      0.923      0.974      0.976      0.955\n",
      "               Toolbar         26         26      0.744      0.808      0.795      0.781\n",
      "          UpperTaskBar        375        375      0.996      0.949      0.992      0.927\n",
      "Speed: 0.3ms preprocess, 1.9ms inference, 0.0ms loss, 1.5ms postprocess per image\n",
      "Results saved to \u001b[1mruns/detect/train52\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "from ultralytics import YOLO\n",
    "\n",
    "# Load the YOLOv8 Nano model\n",
    "model = YOLO(\"yolov8n.pt\")\n",
    "\n",
    "# Train the model\n",
    "train_results = model.train(\n",
    "    data=\"/home/xd/Documents/ML_AI/ui_detection_yolo/data.yml\",  # Dataset configuration\n",
    "    epochs=20,         # Number of training cycles\n",
    "    imgsz=640,         # Input image size\n",
    "    device=\"cuda\",\n",
    "    batch=16           # Adjust based on RAM\n",
    ")\n",
    "\n",
    "# Evaluate performance\n",
    "metrics = model.val()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "f35b12d9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "image 1/1 /home/xd/Documents/ML_AI/ui_detection_yolo/test3.png: 640x384 11 CheckedTextViews, 2 EditTexts, 3 Icons, 5 Images, 13 Texts, 1 Toolbar, 1 UpperTaskBar, 33.1ms\n",
      "Speed: 16.0ms preprocess, 33.1ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 384)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Opening in existing browser session.\n"
     ]
    }
   ],
   "source": [
    "\n",
    "\n",
    "# Detect elements in a test image\n",
    "results = model(\"test3.png\")\n",
    "results[0].show()  # Display annotated predictions"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}