thom966
commented
2 years ago This is because batch norm expects more than 1 batch size. Change your batch size in the .yaml file.
Open zzzzzz-ddddd opened 2 years ago
thom966
commented
2 years ago This is because batch norm expects more than 1 batch size. Change your batch size in the .yaml file.
When I run train.py file reported an error, and then modified the drop in the dataloader_ Last is true Running again is the same error. Do not know why? Thank you for your answers.（python=3.8 pytorch=1.4.0 cudatoolkit=10.2） give the result as follows
epochs: 0%| | 0/10 [00:01<?, ?it/s] Traceback (most recent call last): File "train.py", line 203, in
main()
File "train.py", line 157, in main
train_model(
File "/home/ubuntu/zdq/CaDDN/tools/train_utils/train_utils.py", line 86, in train_model
accumulated_iter = train_one_epoch(
File "/home/ubuntu/zdq/CaDDN/tools/train_utils/train_utils.py", line 38, in train_one_epoch
loss, tb_dict, disp_dict = model_func(model, batch)
File "/home/ubuntu/zdq/CaDDN/pcdet/models/init.py", line 39, in model_func
ret_dict, tb_dict, disp_dict = model(batch_dict)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, kwargs)
File "/home/ubuntu/zdq/CaDDN/pcdet/models/detectors/caddn.py", line 11, in forward
batch_dict = cur_module(batch_dict)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, *kwargs)
File "/home/ubuntu/zdq/CaDDN/pcdet/models/backbones_3d/ffe/depth_ffe.py", line 51, in forward
ddn_result = self.ddn(images)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(input, kwargs)
File "/home/ubuntu/zdq/CaDDN/pcdet/models/backbones_3d/ffe/ddn/ddn_template.py", line 114, in forward
x = self.model.classifier(x)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, kwargs)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, *kwargs)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torchvision/models/segmentation/deeplabv3.py", line 92, in forward
res.append(conv(x))
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(input, kwargs)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torchvision/models/segmentation/deeplabv3.py", line 61, in forward
x = mod(x)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 104, in forward
return F.batch_norm(
File "/home/ubuntu/anaconda3/envs/caddn/lib/python3.8/site-packages/torch/nn/functional.py", line 1666, in batch_norm
raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])