663 lines
371 KiB
Plaintext
663 lines
371 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"## DATA AUGMENTATION USING ALBEMENTATIONS"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"100%|██████████| 14/14 [00:02<00:00, 4.74it/s]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import os\n",
|
||
|
|
"import cv2\n",
|
||
|
|
"import albumentations as A\n",
|
||
|
|
"from tqdm import tqdm\n",
|
||
|
|
"\n",
|
||
|
|
"# ==== PATH CONFIG ====\n",
|
||
|
|
"SOURCE_IMAGE_DIR = 'datasets/images/train'\n",
|
||
|
|
"SOURCE_LABEL_DIR = 'datasets/labels/train'\n",
|
||
|
|
"\n",
|
||
|
|
"AUG_IMAGE_DIR = 'augmented_dataset/images'\n",
|
||
|
|
"AUG_LABEL_DIR = 'augmented_dataset/labels'\n",
|
||
|
|
"\n",
|
||
|
|
"os.makedirs(AUG_IMAGE_DIR, exist_ok=True)\n",
|
||
|
|
"os.makedirs(AUG_LABEL_DIR, exist_ok=True)\n",
|
||
|
|
"\n",
|
||
|
|
"# ==== AUGMENTATION PIPELINE ====\n",
|
||
|
|
"transform = A.Compose([\n",
|
||
|
|
" A.HorizontalFlip(p=0.5),\n",
|
||
|
|
" A.RandomBrightnessContrast(p=0.3),\n",
|
||
|
|
" A.Rotate(limit=15, p=0.5),\n",
|
||
|
|
" A.MotionBlur(p=0.2),\n",
|
||
|
|
" A.RandomGamma(p=0.3),\n",
|
||
|
|
"], bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))\n",
|
||
|
|
"\n",
|
||
|
|
"# ==== HELPER FUNCTION TO LOAD YOLO LABEL ====\n",
|
||
|
|
"def load_yolo_labels(label_path):\n",
|
||
|
|
" bboxes = []\n",
|
||
|
|
" class_labels = []\n",
|
||
|
|
" if not os.path.exists(label_path):\n",
|
||
|
|
" return bboxes, class_labels\n",
|
||
|
|
" with open(label_path, 'r') as f:\n",
|
||
|
|
" for line in f.readlines():\n",
|
||
|
|
" parts = line.strip().split()\n",
|
||
|
|
" class_id = int(parts[0])\n",
|
||
|
|
" bbox = list(map(float, parts[1:]))\n",
|
||
|
|
" bboxes.append(bbox)\n",
|
||
|
|
" class_labels.append(class_id)\n",
|
||
|
|
" return bboxes, class_labels\n",
|
||
|
|
"\n",
|
||
|
|
"# ==== AUGMENT IMAGES ====\n",
|
||
|
|
"NUM_AUGS = 10 # Number of augmentations per image\n",
|
||
|
|
"\n",
|
||
|
|
"for img_file in tqdm(os.listdir(SOURCE_IMAGE_DIR)):\n",
|
||
|
|
" if not img_file.endswith(('.jpg', '.jpeg', '.png')):\n",
|
||
|
|
" continue\n",
|
||
|
|
"\n",
|
||
|
|
" img_path = os.path.join(SOURCE_IMAGE_DIR, img_file)\n",
|
||
|
|
" label_path = os.path.join(SOURCE_LABEL_DIR, os.path.splitext(img_file)[0] + '.txt')\n",
|
||
|
|
"\n",
|
||
|
|
" # Load image and bounding boxes\n",
|
||
|
|
" image = cv2.imread(img_path)\n",
|
||
|
|
" height, width = image.shape[:2]\n",
|
||
|
|
" bboxes, class_labels = load_yolo_labels(label_path)\n",
|
||
|
|
"\n",
|
||
|
|
" if not bboxes:\n",
|
||
|
|
" continue # Skip if no annotations\n",
|
||
|
|
"\n",
|
||
|
|
" # Augment multiple times\n",
|
||
|
|
" for i in range(NUM_AUGS):\n",
|
||
|
|
" augmented = transform(image=image, bboxes=bboxes, class_labels=class_labels)\n",
|
||
|
|
" aug_img = augmented['image']\n",
|
||
|
|
" aug_bboxes = augmented['bboxes']\n",
|
||
|
|
" aug_classes = augmented['class_labels']\n",
|
||
|
|
"\n",
|
||
|
|
" # === Save new image ===\n",
|
||
|
|
" new_img_name = f\"{os.path.splitext(img_file)[0]}_aug_{i}.jpg\"\n",
|
||
|
|
" cv2.imwrite(os.path.join(AUG_IMAGE_DIR, new_img_name), aug_img)\n",
|
||
|
|
"\n",
|
||
|
|
" # === Save new label ===\n",
|
||
|
|
" new_label_path = os.path.join(AUG_LABEL_DIR, f\"{os.path.splitext(img_file)[0]}_aug_{i}.txt\")\n",
|
||
|
|
" with open(new_label_path, 'w') as f:\n",
|
||
|
|
" for cls, box in zip(aug_classes, aug_bboxes):\n",
|
||
|
|
" f.write(f\"{cls} {' '.join(map(str, box))}\\n\")\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"### TRAINING THE MODEL"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 17,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"New https://pypi.org/project/ultralytics/8.3.114 available Update with 'pip install -U ultralytics'\n",
|
||
|
|
"Ultralytics 8.3.113 Python-3.11.4 torch-2.6.0+cpu CPU (11th Gen Intel Core(TM) i7-1165G7 2.80GHz)\n",
|
||
|
|
"\u001b[34m\u001b[1mengine\\trainer: \u001b[0mtask=detect, mode=train, model=yolov8n.pt, data=c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\data.yaml, epochs=10, time=None, patience=100, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train8, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=True, opset=None, workspace=None, 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, pose=12.0, kobj=1.0, 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, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, copy_paste_mode=flip, auto_augment=randaugment, erasing=0.4, cfg=None, tracker=botsort.yaml, save_dir=c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\n",
|
||
|
|
"Overriding model.yaml nc=80 with nc=1\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 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] \n",
|
||
|
|
"Model summary: 129 layers, 3,011,043 parameters, 3,011,027 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[1mtrain: \u001b[0mFast image access (ping: 0.10.0 ms, read: 1027.1189.7 MB/s, size: 1031.3 KB)\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning C:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\labels\\train.cache... 154 images, 0 backgrounds, 0 corrupt: 100%|██████████| 154/154 [00:00<?, ?it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\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, num_output_channels=3, method='weighted_average'), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
|
||
|
|
"\u001b[34m\u001b[1mval: \u001b[0mFast image access (ping: 0.10.0 ms, read: 1372.8251.0 MB/s, size: 2917.1 KB)\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\n",
|
||
|
|
"\u001b[34m\u001b[1mval: \u001b[0mScanning C:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\labels\\val.cache... 6 images, 0 backgrounds, 0 corrupt: 100%|██████████| 6/6 [00:00<?, ?it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Plotting labels to c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\labels.jpg... \n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\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=0.002, 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 0 dataloader workers\n",
|
||
|
|
"Logging results to \u001b[1mc:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\u001b[0m\n",
|
||
|
|
"Starting training for 10 epochs...\n",
|
||
|
|
"Closing dataloader mosaic\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, num_output_channels=3, method='weighted_average'), CLAHE(p=0.01, clip_limit=(1.0, 4.0), tile_grid_size=(8, 8))\n",
|
||
|
|
"\n",
|
||
|
|
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" 1/10 0G 2.091 3.341 1.923 40 640: 100%|██████████| 10/10 [00:53<00:00, 5.34s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.54it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.0133 1 0.446 0.272\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": [
|
||
|
|
" 2/10 0G 1.509 1.644 1.308 40 640: 100%|██████████| 10/10 [00:53<00:00, 5.32s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.48it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.026 0.792 0.489 0.229\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": [
|
||
|
|
" 3/10 0G 1.343 1.322 1.159 40 640: 100%|██████████| 10/10 [00:59<00:00, 5.93s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:01<00:00, 1.02s/it]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.0133 1 0.586 0.254\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": [
|
||
|
|
" 4/10 0G 1.313 1.271 1.152 40 640: 100%|██████████| 10/10 [01:03<00:00, 6.33s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:01<00:00, 1.28s/it]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 1 0.475 0.796 0.353\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": [
|
||
|
|
" 5/10 0G 1.263 1.197 1.137 40 640: 100%|██████████| 10/10 [00:58<00:00, 5.83s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.55it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 1 0.285 0.748 0.368\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": [
|
||
|
|
" 6/10 0G 1.215 1.144 1.125 40 640: 100%|██████████| 10/10 [00:54<00:00, 5.43s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.15it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.916 0.457 0.708 0.315\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": [
|
||
|
|
" 7/10 0G 1.233 1.128 1.122 40 640: 100%|██████████| 10/10 [00:53<00:00, 5.35s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.44it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.848 0.458 0.672 0.325\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": [
|
||
|
|
" 8/10 0G 1.119 1.037 1.091 40 640: 100%|██████████| 10/10 [00:55<00:00, 5.54s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.46it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.922 0.492 0.665 0.375\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": [
|
||
|
|
" 9/10 0G 1.085 0.9943 1.08 40 640: 100%|██████████| 10/10 [00:55<00:00, 5.60s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.25it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.928 0.541 0.703 0.41\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": [
|
||
|
|
" 10/10 0G 1.032 0.9557 1.067 40 640: 100%|██████████| 10/10 [00:59<00:00, 5.95s/it]\n",
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.05it/s]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.889 0.665 0.77 0.441\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\n",
|
||
|
|
"10 epochs completed in 0.161 hours.\n",
|
||
|
|
"Optimizer stripped from c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\last.pt, 6.2MB\n",
|
||
|
|
"Optimizer stripped from c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\best.pt, 6.2MB\n",
|
||
|
|
"\n",
|
||
|
|
"Validating c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\best.pt...\n",
|
||
|
|
"Ultralytics 8.3.113 Python-3.11.4 torch-2.6.0+cpu CPU (11th Gen Intel Core(TM) i7-1165G7 2.80GHz)\n",
|
||
|
|
"Model summary (fused): 72 layers, 3,005,843 parameters, 0 gradients, 8.1 GFLOPs\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stderr",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.62it/s]\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" all 6 24 0.889 0.665 0.77 0.443\n",
|
||
|
|
"Speed: 4.4ms preprocess, 44.9ms inference, 0.0ms loss, 3.0ms postprocess per image\n",
|
||
|
|
"Results saved to \u001b[1mc:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\u001b[0m\n",
|
||
|
|
"Ultralytics 8.3.113 Python-3.11.4 torch-2.6.0+cpu CPU (11th Gen Intel Core(TM) i7-1165G7 2.80GHz)\n",
|
||
|
|
"Model summary (fused): 72 layers, 3,005,843 parameters, 0 gradients, 8.1 GFLOPs\n",
|
||
|
|
"\n",
|
||
|
|
"\u001b[34m\u001b[1mPyTorch:\u001b[0m starting from 'c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 5, 8400) (5.9 MB)\n",
|
||
|
|
"\n",
|
||
|
|
"\u001b[34m\u001b[1mTorchScript:\u001b[0m starting export with torch 2.6.0+cpu...\n",
|
||
|
|
"\u001b[34m\u001b[1mTorchScript:\u001b[0m export success 3.1s, saved as 'c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\best.torchscript' (11.9 MB)\n",
|
||
|
|
"\n",
|
||
|
|
"Export complete (3.4s)\n",
|
||
|
|
"Results saved to \u001b[1mC:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\u001b[0m\n",
|
||
|
|
"Predict: yolo predict task=detect model=c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\best.torchscript imgsz=640 \n",
|
||
|
|
"Validate: yolo val task=detect model=c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\runs\\detect\\train8\\weights\\best.torchscript imgsz=640 data=c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\datasets\\data.yaml \n",
|
||
|
|
"Visualize: https://netron.app\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"'c:\\\\Users\\\\babaw\\\\Documents\\\\Work\\\\Mana Knight Digital\\\\ds_task_recycling_project\\\\datasets\\\\runs\\\\detect\\\\train8\\\\weights\\\\best.torchscript'"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 17,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from ultralytics import YOLO\n",
|
||
|
|
"from ultralytics.utils import SETTINGS\n",
|
||
|
|
"import os\n",
|
||
|
|
"\n",
|
||
|
|
"current_directory = os.getcwd()\n",
|
||
|
|
"\n",
|
||
|
|
"# Temporarily override dataset dir\n",
|
||
|
|
"SETTINGS['datasets_dir'] = current_directory + '\\\\datasets'\n",
|
||
|
|
"SETTINGS['weights_dir'] = current_directory + '\\\\datasets\\\\weights'\n",
|
||
|
|
"SETTINGS['runs_dir'] = current_directory + '\\\\datasets\\\\runs'\n",
|
||
|
|
"\n",
|
||
|
|
"# Load a model\n",
|
||
|
|
"model = YOLO('yolov8n.pt') # Load a pretrained model (e.g., yolov8n.pt)\n",
|
||
|
|
"\n",
|
||
|
|
"# Train the model\n",
|
||
|
|
"results = model.train(data=current_directory + '\\\\datasets\\\\data.yaml', epochs=10, imgsz=640) # customize as needed\n",
|
||
|
|
"\n",
|
||
|
|
"# Save the model\n",
|
||
|
|
"model.export() # export in other formats as needed"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"### TESTING THE MODEL WITH AN IMAGE"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"\n",
|
||
|
|
"image 1/1 c:\\Users\\babaw\\Documents\\Work\\Mana Knight Digital\\ds_task_recycling_project\\training\\memory\\out15.png: 384x640 4 memorys, 90.1ms\n",
|
||
|
|
"Speed: 27.3ms preprocess, 90.1ms inference, 1.1ms postprocess per image at shape (1, 3, 384, 640)\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 640x480 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# Load the model\n",
|
||
|
|
"import cv2\n",
|
||
|
|
"import os\n",
|
||
|
|
"import matplotlib.pyplot as plt\n",
|
||
|
|
"from ultralytics import YOLO\n",
|
||
|
|
"\n",
|
||
|
|
"current_directory = os.getcwd()\n",
|
||
|
|
"model_path = current_directory + '\\\\datasets\\\\runs\\\\detect\\\\train8\\\\weights\\\\last.pt'\n",
|
||
|
|
"model = YOLO(model_path) # Load the trained model\n",
|
||
|
|
"\n",
|
||
|
|
"image_path = current_directory + '\\\\training\\\\memory\\\\out15.png'\n",
|
||
|
|
"results = model.predict(image_path)\n",
|
||
|
|
"\n",
|
||
|
|
"for r in results:\n",
|
||
|
|
" im_array = r.plot()\n",
|
||
|
|
" plt.imshow(cv2.cvtColor(im_array, cv2.COLOR_BGR2RGB))\n",
|
||
|
|
" plt.show()\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 7,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"%matplotlib inline\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": []
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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": "3.11.4"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 2
|
||
|
|
}
|