xtao

The mAP of SSD-Resnet is lower than SSD-VGG16.

1

Thanks for your work ! I just replace the backbone of **SSD** with 'torchvision.models.resnet', but the mAP becomes lower than the VGG-16. The results are follow: | backbone | mAP...

Thanks for your Great work! Your code helps me a lot! When I create a new camera, I find that the resulting camera works with the Central projection. Now, I...

error when convert .pt to .caffemodel

6

Hi, I follow the [article](https://mp.weixin.qq.com/s/IYwjUpV4iYBbqIsTcwgYlg) to convert yolov5s.pt to yolov5.caffemodel, but I encountered some issues. 1. The same problem as [issue #4](https://github.com/Wulingtian/yolov5_onnx2caffe/issues/4). So, I change the **onnx** to **onnx==1.8.0**, and...

为什么不在每个训练epoch中更新pseduo label ?

2

为什么不在每个训练epoch中更新pseduo label ? https://github.com/weijiawu/SyntoReal_STD/blob/02ee312504d754bf51d5149916235110d5283105/trainSyndataToICDAR15.py#L138-L143 可以改成以下这样吗？ ``` for epoch in range(args.epoch_iter): generate_pseduo(model, args.target_image, args.target_pseudo_positive, args.target_pseudo_negative, device) train(epoch, model, optimizer, train_loader_source, train_loader_target) ```