pytorch-pose-hg-3d
pytorch-pose-hg-3d copied to clipboard
Error Benchmark Testing
dear,
I use CPU, not GPU, not CUDA.
I use Anaconda, Spider to build main.py. I had a error:
I met the error like that
Can you help me?
Hi, CPU training is not supported in this project.
Dear,
I had GPU and I had the error below
(tensorflow-gpu) D:\Binh\pytorch-pose-hg-3d-master\pytorch-pose-hg-3d-master>python src/main.py --exp_id test --task human3d --dataset fusion_3d --load_model models/fusion_3d_var.pth --test --full_test
USE_TENSORBOARD: False
heads {'hm': 16, 'depth': 16}
'cp' 不是內部或外部命令、可執行的程式或批次檔。
=> using msra resnet 'msra_50'
=> loading pretrained model https://download.pytorch.org/models/resnet50-19c8e357.pth
loaded models/fusion_3d_var.pth, epoch 10
==> initializing 3D val data.
Loaded 3D val 19312 samples
#Images2D 0, #Images3D 19312
USE_TENSORBOARD: False
Traceback (most recent call last):
File "src/main.py", line 103, in
Hi, it seems that you haven't set up the image path correctly. You can add print('path') after https://github.com/xingyizhou/pytorch-pose-hg-3d/blob/master/src/lib/datasets/h36m.py#L55 to see if the path exists on your computer.
dear,
I fix the image path but the same error.

I download the folder like that
