mks0601/Hand4Whole_RELEASE

I have googled it, but it has not been solved yet. I have the following problem, please help me

Opened this issue · 6 comments

I only used MSCOCO for train.
Trying the 1st: 1st: pre-train Hand4Whole and run
python train.py --gpu 0-3 --lr 1e-4 --continue
Getting the following error

Traceback (most recent call last): File "train.py", line 82, in <module> main() File "train.py", line 53, in main loss = trainer.model(inputs, targets, meta_info, 'train') File "/home/wansiqi1/.custom/pyrender78/envs/train/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/home/wansiqi1/.custom/pyrender78/envs/train/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 168, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/wansiqi1/.custom/pyrender78/envs/train/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 178, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/wansiqi1/.custom/pyrender78/envs/train/lib/python3.8/site-packages/torch/nn/parallel/parallel_apply.py", line 86, in parallel_apply output.reraise() File "/home/wansiqi1/.custom/pyrender78/envs/train/lib/python3.8/site-packages/torch/_utils.py", line 461, in reraise raise exception KeyError: Caught KeyError in replica 0 on device 0.

Anyone else seen this? Thanks!

what is pyrender78?

It is the name I used to customize the image on the cloud server.
I find that I get no error when I use dataset Human36M+MSCOCO+MPII, but I get this error when I use only one of them.

How did you set trainset_3d and trainset_2d in config.py?

trainset_3d = []
trainset_2d = ['MSCOCO']

Screenshot 2023-02-04 at 12 47 57 AM

I have just downloaded current repo and ran without any problem.

trainset_3d = [] trainset_2d = ['MSCOCO']

It is the name I used to customize the image on the cloud server. I find that I get no error when I use dataset Human36M+MSCOCO+MPII, but I get this error when I use only one of them.

Hello, do you know what's causing this problem