GraphCMR icon indicating copy to clipboard operation
GraphCMR copied to clipboard

Published 20 hours ago • verified publisher icon nkolot

Running ‘demo.py' can't get good results

Open moondabaojian opened this issue 4 years ago • 2 comments

Hello, I use the smplx template for training and only train the graphcnn module. In the process of training, I get good output results, but when I load checkpoint to run demo, I can't get good results most of the time. Do you have any suggestions In addition, will the parameters of resnet50 network be updated? Even if the pretrained model is used, will it affect the output of demo Thank you!

moondabaojian avatar Jun 02 '20 11:06 moondabaojian

Hello, I have problem on training the network, I can't get good results even in the process of training. I only use Human3.6M, COCO and LSP dataset for training. Would you mind helping me?My email address is [email protected]

LSY1111 avatar Mar 29 '22 07:03 LSY1111

Hello, @LSY1111 . I tried to contact you by email, but did not receive a reply. I hope we can communicate our problems to solve them.

Hao-hui avatar Apr 09 '22 14:04 Hao-hui