Daniel Mao

Hi, thanks for your excellent work! By the way, I have some question about the work: 1. why not use reconstruction loss such as L1 or L2 loss for better...

Question about the percentage of GPU usage

5

Hi, the code is successfully run on my GPU Nvidia 1060 Ti. However, it seems that the percentage of usage of GPU is low, which can be shown as the...

Hi, after reading the source code of cpm, I found that you use inverted bottleneck(which is mobilenet v2) and separable conv(which corresponding the original mobilenet v1) in the part of...

Hi, thanks for you great work and I wonder if there is plan to release the training code?

Hi, I have tried your work about the application of make up transfer.But thre test result is bad.  This is the result from the prediction folder which produced by...

Is there may be some error in hands_metadata.py

1

Hi, in line 29 of the file hands_metadata.py, there are two number 7. Is there some error? To my understanding, the first number 7 shouled be replaced by 6, which...