PIXOR icon indicating copy to clipboard operation
PIXOR copied to clipboard

Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

Open MaxLeo-LMZ opened this issue 2 years ago • 0 comments

run evaluate_model.py

Traceback (most recent call last): File "evaluate_model.py", line 421, in eval_dict = evaluate_model(pixor, data_loader, distance_ranges=[70, 50, 30], iou_thresholds=[0.5, 0.6, 0.7, 0.8, 0.9]).to(device) File "evaluate_model.py", line 227, in evaluate_model batch_predictions = model(batch_data) File "/home/mingzhong/anaconda3/envs/pixor-36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/mingzhong/PycharmProjects/pixor/PIXOR-pytorch/PIXOR-master/PIXOR.py", line 244, in forward x_b = self.basis_block(x) File "/home/mingzhong/anaconda3/envs/pixor-36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/mingzhong/PycharmProjects/pixor/PIXOR-pytorch/PIXOR-master/PIXOR.py", line 28, in forward x = self.conv1(x) File "/home/mingzhong/anaconda3/envs/pixor-36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/mingzhong/anaconda3/envs/pixor-36/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/mingzhong/anaconda3/envs/pixor-36/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

MaxLeo-LMZ avatar May 26 '22 08:05 MaxLeo-LMZ