search

aliyun / 3D-Local-CNN-for-Gait-Recognition

Apache License 2.0
43 stars 8 forks source link

The size of tensor a (64) must match the size of tensor b (128) at non-singleton dimension 1 #3

Open FuHui-UPC opened 2 years ago

FuHui-UPC commented 2 years ago

Traceback (most recent call last): File "main.py", line 161, in p.start() File "/home/fh/3D-Local-CNN-for-Gait-Recognition/solvers/solver.py", line 55, in start return mode() File "/home/fh/3D-Local-CNN-for-Gait-Recognition/solvers/baseline.py", line 95, in train feature = self.model(seq) File "/home/fh/miniconda3/envs/gait/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, kwargs) File "/home/fh/miniconda3/envs/gait/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 165, in forward return self.module(*inputs[0], *kwargs[0]) File "/home/fh/miniconda3/envs/gait/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(input, kwargs) File "/home/fh/3D-Local-CNN-for-Gait-Recognition/models/localcnn3d.py", line 302, in forward gl = self.local(feat4_5d, feat6_5d) File "/home/fh/miniconda3/envs/gait/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, kwargs) File "/home/fh/3D-Local-CNN-for-Gait-Recognition/models/localcnn3d.py", line 166, in forward head = self.head(x, param_x.detach()) File "/home/fh/miniconda3/envs/gait/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, *kwargs) File "/home/fh/3D-Local-CNN-for-Gait-Recognition/models/localcnn3d.py", line 121, in forward sampled_feature = self.sampler(x, loc_params) File "/home/fh/miniconda3/envs/gait/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(input, kwargs) File "/home/fh/3D-Local-CNN-for-Gait-Recognition/models/sample.py", line 233, in forward glimpse = torch.matmul(Fyv, torch.matmul(x, Fxt)) RuntimeError: The size of tensor a (64) must match the size of tensor b (128) at non-singleton dimension 1

I met some errors when I run "python main.py --config=configs/3DLocalCNN_CASIA.yaml". Could you help me?

X-ray0214 commented 2 years ago

Have you ever solved the problem? I met the same error now.

FuHui-UPC commented 2 years ago

Have you ever solved the problem? I met the same error now.

No. It must be the error of the provided source code.

Yangyc07 commented 2 years ago

请问你解决该问题了吗，数据预处理的程序好像运行不了

FuHui-UPC commented 2 years ago

请问你解决该问题了吗，数据预处理的程序好像运行不了

没有解决，联系作者也没有回复，数据预处理好像没有问题吧

Yangyc07 commented 2 years ago

这个预处理和gaitset不同，请问怎么运行pretrement文件预处理

HUAFOR commented 2 years ago

我也是遇到了这个问题！作者可以回复一下吗？

zhang123-sys commented 2 years ago

一定cuda10.2？cuda11.1可以吗？

hxi667 commented 1 year ago

我也是遇到了这个问题！作者可以回复一下吗？

你是因为多个GPU吧，我也遇到了这种问题。但是只用一张GPU的话就没问题