I keep getting this error whenever i try to evaluate the model
python eval_ggcnn.py --network /home/aakaash/ggcnn/ggcnn_weights_cornell/ggcnn_epoch_23_cornell --dataset cornell --dataset-path /home/aakaash/Downloads/archive --vis
/home/aakaash/myen/lib/python3.6/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
/home/aakaash/myen/lib/python3.6/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.conv.ConvTranspose2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set torch.nn.Module.dump_patches = True and use the patch tool to revert the changes.
warnings.warn(msg, SourceChangeWarning)
INFO:root:Loading Cornell Dataset...
INFO:root:Done
INFO:root:Processing 1/89
Traceback (most recent call last):
File "eval_ggcnn.py", line 78, in
lossd = net.compute_loss(xc, yc)
File "/home/aakaash/ggcnn/models/ggcnn.py", line 49, in compute_loss
pos_pred, cos_pred, sin_pred, width_pred = self(xc)
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, *kwargs)
File "/home/aakaash/ggcnn/models/ggcnn.py", line 33, in forward
x = F.relu(self.conv1(x))
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(input, **kwargs)
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 446, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
I keep getting this error whenever i try to evaluate the model python eval_ggcnn.py --network /home/aakaash/ggcnn/ggcnn_weights_cornell/ggcnn_epoch_23_cornell --dataset cornell --dataset-path /home/aakaash/Downloads/archive --vis /home/aakaash/myen/lib/python3.6/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set
lossd = net.compute_loss(xc, yc)
File "/home/aakaash/ggcnn/models/ggcnn.py", line 49, in compute_loss
pos_pred, cos_pred, sin_pred, width_pred = self(xc)
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, *kwargs)
File "/home/aakaash/ggcnn/models/ggcnn.py", line 33, in forward
x = F.relu(self.conv1(x))
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(input, **kwargs)
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 446, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/aakaash/myen/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
torch.nn.Module.dump_patches = True
and use the patch tool to revert the changes. warnings.warn(msg, SourceChangeWarning) /home/aakaash/myen/lib/python3.6/site-packages/torch/serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.conv.ConvTranspose2d' has changed. you can retrieve the original source code by accessing the object's source attribute or settorch.nn.Module.dump_patches = True
and use the patch tool to revert the changes. warnings.warn(msg, SourceChangeWarning) INFO:root:Loading Cornell Dataset... INFO:root:Done INFO:root:Processing 1/89 Traceback (most recent call last): File "eval_ggcnn.py", line 78, in