From 0fc1997718ff2e8fdb49e93f03893437f4998496 Mon Sep 17 00:00:00 2001 From: dronefreak Date: Fri, 19 Jun 2026 09:09:45 +0200 Subject: [PATCH 1/3] chore: Add node_modules to gitignore Signed-off-by: dronefreak --- .gitignore | 1 + 1 file changed, 1 insertion(+) diff --git a/.gitignore b/.gitignore index 6a6e5bf..5873fcd 100644 --- a/.gitignore +++ b/.gitignore @@ -182,3 +182,4 @@ temp/ # Cache .cache/ *.cache +node_modules From 33617243fbeed688742eb4621674b6fe68041c06 Mon Sep 17 00:00:00 2001 From: dronefreak Date: Fri, 19 Jun 2026 09:10:12 +0200 Subject: [PATCH 2/3] chore: Remove old README Signed-off-by: dronefreak --- README.md | 74 ------------------------------------------------------- 1 file changed, 74 deletions(-) delete mode 100644 README.md diff --git a/README.md b/README.md deleted file mode 100644 index 8ae1a9a..0000000 --- a/README.md +++ /dev/null @@ -1,74 +0,0 @@ ---- - -## 🚀 YOLO v8+ Support (NEW) - -The toolkit now includes **full support for YOLO v8, v9, and v10** models alongside the existing torchvision models. This modernizes the toolkit for state-of-the-art object detection. - -### Quick Start with YOLO - -```python -from visdrone_toolkit.utils import get_model -from visdrone_toolkit.dataset import VisDroneDataset -from visdrone_toolkit.trainer import UnifiedTrainer - -# Load YOLO model (same interface for all models!) -model = get_model("yolov8n", num_classes=12, pretrained=True) - -# Load dataset -dataset = VisDroneDataset( - image_dir="path/to/images", - annotation_dir="path/to/annotations" -) - -# Train (automatic format conversion, automatic adapter selection) -trainer = UnifiedTrainer(model=model, device="cuda:0") -trainer.train(dataset, dataset, epochs=100, batch_size=16) -``` - -### Available Models - -**YOLO v8 (5 variants):** - -- `yolov8n` - Nano (fastest, smallest) -- `yolov8s` - Small -- `yolov8m` - Medium -- `yolov8l` - Large -- `yolov8x` - XLarge (highest accuracy) - -**YOLO v9 (2 variants):** - -- `yolov9c` - Compact -- `yolov9m` - Medium - -**YOLO v10 (5 variants):** - -- `yolov10n` - Nano -- `yolov10s` - Small -- `yolov10m` - Medium -- `yolov10l` - Large -- `yolov10x` - XLarge - -**Torchvision (still supported):** - -- `fasterrcnn_resnet50_fpn` -- `fasterrcnn_mobilenetv3_large_320_fpn` -- `fcos_resnet50_fpn` -- `retinanet_resnet50_fpn` - -### Architecture Improvements - -1. **Unified Training Interface** - Single `UnifiedTrainer` class works with all models -2. **Format Conversion** - Automatic COCO ↔ YOLO coordinate conversion -3. **Model Registry** - Dynamic registration, extensible for custom models -4. **Adapter Pattern** - Framework-specific training logic abstracted away -5. **100% Backward Compatible** - All existing code continues to work - -### Performance - -| Model | Speed | Accuracy | Memory | -| ---------- | ------- | -------- | ------ | -| YOLOv8n | 280 FPS | 86.5 mAP | 1.5 GB | -| YOLOv8m | 90 FPS | 90.1 mAP | 4.0 GB | -| FasterRCNN | 45 FPS | 88.3 mAP | 3.5 GB | - -For detailed documentation, see [YOLO_DETR_IMPLEMENTATION.md](YOLO_DETR_IMPLEMENTATION.md). From ddc2ec06ca60d7d2633c516411d89c0a5bcdf51f Mon Sep 17 00:00:00 2001 From: dronefreak Date: Fri, 19 Jun 2026 09:21:56 +0200 Subject: [PATCH 3/3] feat: Add link to HF model zoo Signed-off-by: dronefreak --- .github/README.md | 58 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 43 insertions(+), 15 deletions(-) diff --git a/.github/README.md b/.github/README.md index 5b41811..b231231 100644 --- a/.github/README.md +++ b/.github/README.md @@ -51,10 +51,53 @@ data/ python scripts/train.py --available-models # list all 33 models ``` +### Pretrained VisDrone Models + +Pretrained VisDrone checkpoints for all supported YOLO architectures are available through the Hugging Face collection: + + + +The collection includes model cards, benchmark results, evaluation visualizations, and ready-to-use weights for YOLOv8, YOLOv9, YOLOv10, YOLO11, and YOLO26 model families. + +| Family | Available Models | +| ------- | ---------------- | +| YOLOv8 | n, s, m, x | +| YOLOv9 | c, m, e | +| YOLOv10 | n, l, x | +| YOLO11 | n, l, x | +| YOLO26 | n, l, x | + +Individual model repositories can be accessed directly from the Hugging Face collection page. + --- ## Usage +### Pre-trained Models + +```bash +pip install ultralytics huggingface_hub +``` + +```python +from huggingface_hub import hf_hub_download +from ultralytics import YOLO + +weights = hf_hub_download( + repo_id="dronefreak/yolov8m-visdrone", + filename="best.pt" +) + +model = YOLO(weights) + +results = model.predict( + source="image.jpg", + conf=0.25 +) + +results[0].show() +``` + ### Train ```bash @@ -169,21 +212,6 @@ model = get_model("fasterrcnn_resnet50", num_classes=12, pretrained=True) --- -## Performance - -Faster R-CNN ResNet50, VisDrone2019-DET-val (200 epochs, RTX 4070 Super): - -| Metric | Score | -| --------- | ------------------- | -| F1 | 66.7% | -| Precision | 71.0% | -| Recall | 62.9% | -| Speed | 18 FPS (55ms/image) | - -YOLO v8n after 1 epoch (untrained baseline): mAP@0.5 = 0.119, mAP@0.5:0.95 = 0.062. - ---- - ## Development ```bash