Yonghye Kwon

넵 좋은 말씀 감사드립니다. ㅜㅜ 당분간은 구현이 어려울 거 같습니다. 최근에는 기능이 다양한 어노테이션툴들이 공개된 거 같은데 다른 툴을 이용해보시는 건 어떨까요?

fix #1 issue

@hojunjin refer to [ZCBAM](https://github.com/developer0hye/ZCBAM)

@yjh0410 Hi, yjh! Refer to https://github.com/developer0hye/Simple-PyTorch-Deformable-Convolution-v2 You can easily use DCNv2 layer with PyTorch!

Okay! Close the issue!

@danczs @amaarora Thanks for sharing your works! I really love the architecture and experiments that you guys did. I could find out how to improve the performance of transformer models...

@danczs I trained the model with the below command having set '--drop-path' to 0. ``` python -m torch.distributed.launch --nproc_per_node=4 --use_env main.py --model visformer_tiny --batch-size 256 --drop-path 0.0 --data-path /path/to/imagenet --output_dir...

@danczs Okay! Thanks!

@YashRunwal @yjh0410 I recommend you guys to read [this issue](https://github.com/ultralytics/yolov5/pull/3945) for processing gray image.

@Broad-sky Training with MSELoss for sigmoid output can make model drowning into local minima. Many other yolo re-implementation projects use BCELoss or BCEWithLogitsLoss like this project.