Added dataset and training data
This commit is contained in:
@@ -0,0 +1,254 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ee6d3405-39e3-4109-84e0-f1ba6c7df74b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%matplotlib inline\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"import random\n",
|
||||
"import cv2\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"from ultralytics import YOLO\n",
|
||||
"\n",
|
||||
"# --- CONFIGURATION ---\n",
|
||||
"DATASET_DIR = os.path.abspath(\"dataset\") # Absolute path to your dataset folder\n",
|
||||
"# VIDEO_PATH = \"Screen_Recording_20260710_101822_Hades' Star.mp4\" # Path to your test video\n",
|
||||
"VIDEO_PATH = \"Screen_Recording_20260710_142109_Hades' Star.mp4\"\n",
|
||||
"\n",
|
||||
"# The exact list from your label.py script\n",
|
||||
"CLASS_NAMES = [\n",
|
||||
" \"guardian\",\n",
|
||||
" \"interceptor\",\n",
|
||||
" \"sentinel\",\n",
|
||||
" \"rocket\",\n",
|
||||
" \"bomber\",\n",
|
||||
" \"background\",\n",
|
||||
" \"asteroid\",\n",
|
||||
"]\n",
|
||||
"# ---------------------"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "0245800c-f39d-479d-8093-a8573223d975",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"-> Created dataset.yaml successfully.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# === STEP 1: CREATE THE YOLO CONFIGURATION FILE ===\n",
|
||||
"yaml_content = f\"\"\"\n",
|
||||
"path: {DATASET_DIR}\n",
|
||||
"train: images # path relative to 'path'\n",
|
||||
"val: images # for a quick test, we will validate on the same images\n",
|
||||
"\n",
|
||||
"names:\n",
|
||||
"\"\"\"\n",
|
||||
"for idx, name in enumerate(CLASS_NAMES):\n",
|
||||
" yaml_content += f\" {idx}: {name}\\n\"\n",
|
||||
"\n",
|
||||
"yaml_path = \"dataset.yaml\"\n",
|
||||
"with open(yaml_path, \"w\") as f:\n",
|
||||
" f.write(yaml_content.strip())\n",
|
||||
"\n",
|
||||
"print(f\"-> Created {yaml_path} successfully.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a3e69197-7565-4464-8381-ffc871818819",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"-> Initializing YOLO training...\n",
|
||||
"Ultralytics 8.4.92 🚀 Python-3.13.14 torch-2.13.0+cu130 CPU (Intel Core i5-8365U 1.60GHz)\n",
|
||||
"\u001b[34m\u001b[1mengine/trainer: \u001b[0magnostic_nms=False, amp=True, angle=1.0, 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, cls_pw=0.0, cls_remap=True, compile=False, conf=None, copy_paste=0.0, copy_paste_mode=flip, cos_lr=False, cutmix=0.0, data=dataset.yaml, degrees=0.0, deterministic=True, device=, dfl=1.5, dis=6.0, distill_model=None, dnn=False, dropout=0.0, dynamic=False, embed=None, end2end=None, epochs=75, erasing=0.4, exist_ok=False, fliplr=0.5, flipud=0.0, format=torchscript, fraction=1.0, freeze=None, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, imgsz=640, 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=0.0, name=train-3, 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, quantize=None, rect=False, resume=False, retina_masks=False, rle=1.0, save=True, save_conf=False, save_crop=False, save_dir=/home/nathan/school/CSE_450/final/runs/detect/train-3, 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=tracktrack.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=7\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 752677 ultralytics.nn.modules.head.Detect [7, 16, None, [64, 128, 256]] \n",
|
||||
"Model summary: 130 layers, 3,012,213 parameters, 3,012,197 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: 0.0±0.0 ms, read: 2882.6±931.7 MB/s, size: 170.8 KB)\n",
|
||||
"\u001b[K\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/nathan/school/CSE_450/final/dataset/labels... 200 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 200/200 2.2Kit/s 0.1s\n",
|
||||
"\u001b[34m\u001b[1mtrain: \u001b[0m/home/nathan/school/CSE_450/final/dataset/images/Screen_Recording_20260710_110910_Hades' Star_frame_1832.jpg: 1 duplicate labels removed\n",
|
||||
"\u001b[34m\u001b[1mtrain: \u001b[0m/home/nathan/school/CSE_450/final/dataset/images/Screen_Recording_20260710_142109_Hades' Star_frame_500.jpg: 1 duplicate labels removed\n",
|
||||
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /home/nathan/school/CSE_450/final/dataset/labels.cache\n",
|
||||
"\u001b[34m\u001b[1mval: \u001b[0mFast image access ✅ (ping: 0.0±0.0 ms, read: 3815.1±715.0 MB/s, size: 139.5 KB)\n",
|
||||
"\u001b[K\u001b[34m\u001b[1mval: \u001b[0mScanning /home/nathan/school/CSE_450/final/dataset/labels.cache... 200 images, 0 backgrounds, 0 corrupt: 100% ━━━━━━━━━━━━ 200/200 52.4Mit/s 0.0s\n",
|
||||
"\u001b[34m\u001b[1mtrain: \u001b[0m/home/nathan/school/CSE_450/final/dataset/images/Screen_Recording_20260710_110910_Hades' Star_frame_1832.jpg: 1 duplicate labels removed\n",
|
||||
"\u001b[34m\u001b[1mtrain: \u001b[0m/home/nathan/school/CSE_450/final/dataset/images/Screen_Recording_20260710_142109_Hades' Star_frame_500.jpg: 1 duplicate labels removed\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=0.000909, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)\n",
|
||||
"Plotting labels to /home/nathan/school/CSE_450/final/runs/detect/train-3/labels.jpg... \n",
|
||||
"Image sizes 640 train, 640 val\n",
|
||||
"Using 0 dataloader workers\n",
|
||||
"Logging results to \u001b[1m/home/nathan/school/CSE_450/final/runs/detect/train-3\u001b[0m\n",
|
||||
"Starting training for 75 epochs...\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 1/75 0G 2.958 5.133 1.861 24 640: 100% ━━━━━━━━━━━━ 13/13 5.7s/it 1:144.4ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 1.9s/it 13.3s2.4s\n",
|
||||
" all 200 688 0 0 0 0\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 2/75 0G 2.32 4.479 1.373 62 640: 100% ━━━━━━━━━━━━ 13/13 6.4s/it 1:234.8ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 2.4s/it 16.7s3.1ss\n",
|
||||
" all 200 688 0.000766 0.0548 0.000265 5.24e-05\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 3/75 0G 2.113 3.946 1.244 59 640: 100% ━━━━━━━━━━━━ 13/13 6.7s/it 1:276.1ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 2.8s/it 19.8s3.5ss\n",
|
||||
" all 200 688 0.0023 0.121 0.00597 0.00267\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 4/75 0G 2.018 3.399 1.21 45 640: 100% ━━━━━━━━━━━━ 13/13 6.2s/it 1:215.4ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 3.0s/it 21.0s4.0ss\n",
|
||||
" all 200 688 0.0103 0.753 0.0839 0.0235\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 5/75 0G 1.965 3.118 1.224 71 640: 100% ━━━━━━━━━━━━ 13/13 6.7s/it 1:274.7ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 2.4s/it 16.5s3.0s\n",
|
||||
" all 200 688 0.493 0.128 0.12 0.0565\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 6/75 0G 1.819 2.967 1.173 74 640: 100% ━━━━━━━━━━━━ 13/13 7.0s/it 1:315.4ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 2.9s/it 20.0s3.6ss\n",
|
||||
" all 200 688 0.171 0.101 0.149 0.0428\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 7/75 0G 1.865 2.806 1.192 49 640: 100% ━━━━━━━━━━━━ 13/13 6.3s/it 1:225.3ss\n",
|
||||
"\u001b[K Class Images Instances Box(P R mAP50 mAP50-95): 100% ━━━━━━━━━━━━ 7/7 3.4s/it 23.8s4.4ss\n",
|
||||
" all 200 688 0.359 0.237 0.224 0.108\n",
|
||||
"\n",
|
||||
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n",
|
||||
"\u001b[K 8/75 0G 1.783 2.766 1.169 124 640: 76% ━━━━━━━━━─── 10/13 9.0s/it 1:36<27.1s"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# === STEP 2: TRAIN A NANO YOLO MODEL ===\n",
|
||||
"print(\"\\n-> Initializing YOLO training...\")\n",
|
||||
"# 'yolov8n.pt' is the Nano model.\n",
|
||||
"model = YOLO(\"yolov8n.pt\")\n",
|
||||
"\n",
|
||||
"# Train the model on your 130 annotations\n",
|
||||
"model.train(data=yaml_path, epochs=75, imgsz=640, verbose=True)\n",
|
||||
"print(\"\\n-> Training complete!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "138e1424-8ecd-4b76-a487-345bcb3b69f1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = YOLO(\"runs/detect/train/weights/best.pt\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "693c7e66-9c2f-427f-b2a0-311c4e5e8a38",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# === STEP 3: EXTRACT A RANDOM FRAME AND TEST DETECTION ===\n",
|
||||
"print(\"\\n-> Running full-frame inference test...\")\n",
|
||||
"\n",
|
||||
"# Grab a random frame from your video file\n",
|
||||
"cap = cv2.VideoCapture(VIDEO_PATH)\n",
|
||||
"if not cap.isOpened():\n",
|
||||
" print(f\"Error: Could not open video {VIDEO_PATH}\")\n",
|
||||
"else:\n",
|
||||
" total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))\n",
|
||||
" random_idx = random.randint(0, total_frames - 1)\n",
|
||||
" cap.set(cv2.CAP_PROP_POS_FRAMES, random_idx)\n",
|
||||
" ret, frame = cap.read()\n",
|
||||
" cap.release()\n",
|
||||
"\n",
|
||||
" if ret:\n",
|
||||
" # Run our freshly trained model on the single, complete video frame!\n",
|
||||
" results = model.predict(source=frame, conf=0.10, imgsz=640)\n",
|
||||
"\n",
|
||||
" # Ultralytics built-in renderer\n",
|
||||
" annotated_frame = results[0].plot()\n",
|
||||
"\n",
|
||||
" plt.figure(figsize=(24, 16))\n",
|
||||
"\n",
|
||||
" # Display the result directly inside your Jupyter Notebook\n",
|
||||
" # plt.figure(figsize=(12, 8))\n",
|
||||
" # Convert BGR (OpenCV format) to RGB (Matplotlib format)\n",
|
||||
" plt.imshow(cv2.cvtColor(annotated_frame, cv2.COLOR_BGR2RGB))\n",
|
||||
" plt.title(f\"YOLO Object Detection Test (Frame: {random_idx})\", fontsize=14)\n",
|
||||
" plt.axis(\"off\")\n",
|
||||
" plt.show()\n",
|
||||
" else:\n",
|
||||
" print(\"Error: Could not read a random frame from the video.\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"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": "3.13.14"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Reference in New Issue
Block a user