j96w / gentp Goto Github PK

Hi
The script command mentioned in the README does not work.
python gentp/scripts/pretrain_rep.py

Traceback (most recent call last): File "gentp/scripts/pretrain_rep.py", line 128, in <module> main() File "gentp/scripts/pretrain_rep.py", line 119, in main pretrain(model, data_pre_train, optimizer, True) File "gentp/scripts/pretrain_rep.py", line 35, in pretrain output_syb, output_view, output_seg = model.forward_pre(rgb, seg, syb) File "/home/zyh/projects/GenTP/gentp/lib/model.py", line 577, in forward_pre feat, _ = self.encoder(rgb, seg) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zyh/projects/GenTP/gentp/lib/model.py", line 164, in forward x_img, x_early_img = self.img_encoder(x_img) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torchvision/models/resnet.py", line 249, in forward return self._forward_impl(x) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torchvision/models/resnet.py", line 232, in _forward_impl x = self.conv1(x) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 443, in forward return self._conv_forward(input, self.weight, self.bias) File "/home/zyh/anaconda3/envs/skill_learning/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 439, in _conv_forward return F.conv2d(input, weight, bias, self.stride, RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[160, 6, 128, 128] to have 3 channels, but got 6 channels instead

Is the version of torchvision package I pip install wrong? Any help will be useful.

Thanks & Regards.
Ergo