Jinkun Huang

> torch-dct的结果除以1000以后与cv2的相符合，刚试了下 这个是什么意思？

刚刚研究了下，好像误差大是因为pytorch默认的浮点数为float32？

Thanks! In addition, I found that the code you provided cannot run in a multi-gpu environment, and the parameters in the bayar_conv part will report an error in multi-gpu environments.