Pytorch_Realtime_Multi-Person_Pose_Estimation
Pytorch_Realtime_Multi-Person_Pose_Estimation copied to clipboard
I think there are bugs in train_pose.py
Hi,
I ran train.sh, but I had some errors. I think there are bugs.
Should I add "input = input.cuda()" to around line 138 in train_pose.py and change line 63 "params_dict = dict(model.module.named_parameters())" in train_pose.py to "params_dict = dict(model.named_parameters())" .
If you use one gpu to train and change line 49 "model = torch.nn.DataParallel(model, device_ids=args.gpu).cuda()" to "model = model.cuda()", you're right. Because of torch.nn.DataParallel, it will change "model" to "model.module" and it's the reason that when run test, I will use k[7:] to get the key. If you use the one gpu, you also need to change the test script
Thank you for your replying.
Yes, I use one gpu to train. Should I change other codes ?
No, I think. If you find something error, please let me know. Thank you.
Thank you !
@tugumi911 you are right! if one gpu is used, "input = input.cuda()" and "params_dict = dict(model.named_parameters())" should be modified! thanks
If we want to use only one GPU, there is another way can achieve it.
- Remove the line "os.environ['CUDA_VISIBLE_DEVICES'] = '2,3'" in the train_pose.py.
- Modify the value of --gpu in train.sh to 0.