YOLOv3, YOLOv4, YOLOv5, YOLOX的PyTorch实现。（持续更新中......）

1. Make sure that you have installed PyTorch 1.10.0 and torchvision 0.11.1 or higher.
2. Run the following to install dependencies.

pip install -r requirements.txt

3. Install pycocotools.
4. Download COCO2017 and VOC2012, and then extract them under data folder, make them look like this:

|-- data
    |-- coco
    |   |-- annotations
    |   |   |-- instances_train2017.json
    |   |   `-- instances_val2017.json
    |   `-- images
    |       |-- train2017
    |       |   |-- ... 
    |       `-- val2017
    |           |-- ... 
    |-- VOCdevkit
    `-- |-- Annotations
        |-- ImageSets
        |-- JPEGImages
        |-- SegmentationClass
        |-- SegmentationObject

5. Modify the configuration file under the experiments folder according to your needs.
6. Change the CONFIG parameter in setup.py, and then run setup.py to start training or detect multiple pictures at once.

1. YoloV3 on VOC
   

1. 训练和测试代码

• Yolo_v3
• Yolo_v4
• Yolo_v5
• Yolo_X
• CenterNet

2. 发布在COCO数据集上训练好的模型

• Yolo_v3
• Yolo_v4
• Yolo_v5
• Yolo_X
• CenterNet

• https://github.com/hunglc007/tensorflow-yolov4-tflite
• https://github.com/amdegroot/ssd.pytorch code for processing COCO dataset
• https://github.com/ultralytics/yolov5
• https://github.com/calmisential/YOLOv4_PyTorch
• https://github.com/calmisential/CenterNet_TensorFlow2
• https://github.com/xingyizhou/CenterNet