WZY_^

别用mvcc2.0版本，就装1.7.2就行，mmpose装0.16.0 然后会有一个报错说版本不在范围，跳转进去改个范围值就好了，剩下的就是一堆警告，注释掉就没问题了

By the way, the params of model calculated by torchsummary is inconsistent with the paper： ``` embedding_size = 2048, width_mult=1 : Total params: 3.50M ``` In your paper, the params...

After review the other issues, i find the difference between above config.py and yours is: ``` output_shape: (input_shape[0]//8, input_shape[1]//8) --> (input_shape[0]//4, input_shape[1]//4) depth_dim = 32 --> 64 ``` And in...

@SangbumChoi I have finished the training on 2 GTX 1080Ti about 30 hours. After changing the config, the GPU memory occupancy is so big, so i change the bacth_size to...

@SonNguyen2510 Sorry, I didn't reproduce the result of the paper. My result is above, which has a gap with the paper. After several modifications，I think my config is consistent with...

@SonNguyen2510 Sorry, I don't know. :( You can refer this issue: https://github.com/SangbumChoi/MobileHumanPose/issues/30 It seems that the author just uploaded random pth files.