Jim Zhou

Same problem， Is there any official issue to solve this problem?

Same problem caused with commands: python main.py --cfg configs/epipolar/keypoint_h36m_zresidual_fixed.yaml DOTRAIN False DOTEST True VIS.VIDEO True DATASETS.H36M.TEST_SAMPLE 2

I found a probable solution to this problem. As this problem is caused by the format of pth, we can simple use the checkpoint instead of checkpoint.pop('model')

Another problem occurs when loading the model `pose_resnet_4.5_pixels_human36m.pth.` `RuntimeError: Error(s) in loading state_dict for Modelbuilder: size mismatch for reference.module.final_layer.weight: copying a param with shape torch.Size([33, 256, 1, 1]) from checkpoint,...

鎗这个字没有被转为枪

I apologize for not expressing myself clearly. I mean the download links for model file in https://github.com/JiangWenPL/multiperson/blob/master/mmdetection/MODEL_ZOO.md becomes invalid

I met this problem too. But I solved it by shorten my senetences and it works. This error is probably caused by using long sentence whose hash is longer than...

Same problem, any solutions?

Thanks for answer, i use the eft labels provided in Pymaf to train the pymafx. I want to make sure that the models' performance on 3dpw is only traind on...

Hi, so the train have two stage. 1.train on 2d dataset 2.train on whole dataset. After these training, the model is evaluated on 3dpw?