Dr. Cai

How can I get deep information?

1

Very thank you for your good job. I have studied for several days. I think the output of this code is only the disparities and dispariteis with post-processing. Am I...

大佬好，有个问题请教，当我train uNet的时候，出现train loss nan, cost 0.000的情况，trainA和trainB是利用UWGAN生成的图像数据，超参采用的都是默认值，希望能够帮助解答，谢谢

大佬好，非常感谢你的工作分享，确实很赞（大拇哥）！ 我自己跑了一下code，发现模拟雾化的3个参数（对应r, g, b三个通道）并未参与到训练中（一直保持0.75），请问这样的话当遇到有雾化效果的水下图像的时候，会影响增强效果吧？

KeyError: 'engine'

4

博主你好： 再用你的模型时候，生成.engine时，发生了错误，提示为KeyError：'engine'，我的模型是pytorch的.pt模型

RepVGG模型使用问题

1

原版RepVGG和DBB模型中都配有convert.py进行权重的重参数化转换，请问PaddleClas中这个脚本到哪里可以找到呢？谢谢！

TResNet for TIPC

4

1. Add a new "TResNetM_train_infer_python.txt" in configs for TIPC.

Thank you for your valuable work!!! I have performed the setup.py by "python3 ./setup.py install --user" and installed depthwise_conv2d_implicit_gemm successfully. However, "depthwise_conv2d_implicit_gemm" and "_depthwise_conv2d_implicit_gemm_C" still can not be imported. I...