Error running with CUB

[vunh]

Hi,

I am running with CUB with the following command:
python3 main.py --dataset_root dataset --config config/5way_1shot_resnet12_cub-200.py --num_gpu 1 --mode train

And I got this error
File "main.py", line 579, in
main()
File "main.py", line 570, in main
trainer.train()
File "main.py", line 105, in train
last_layer_data, second_last_layer_data = backbone_two_stage_initialization(all_data, self.enc_module)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/utils.py", line 197, in backbone_two_stage_initialization
encoded_result = encoder(data.squeeze(1))
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/backbone.py", line 101, in forward
x = self.avgpool(x)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/pooling.py", line 595, in forward
self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override)
RuntimeError: Given input size: (512x6x6). Calculated output size: (512x0x0). Output size is too small

Could you please let me know how to fix this?

Thank you very much.

[tiber2013]

Hi,

I am running with CUB with the following command:
python3 main.py --dataset_root dataset --config config/5way_1shot_resnet12_cub-200.py --num_gpu 1 --mode train

And I got this error
File "main.py", line 579, in
main()
File "main.py", line 570, in main
trainer.train()
File "main.py", line 105, in train
last_layer_data, second_last_layer_data = backbone_two_stage_initialization(all_data, self.enc_module)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/utils.py", line 197, in backbone_two_stage_initialization
encoded_result = encoder(data.squeeze(1))
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/backbone.py", line 101, in forward
x = self.avgpool(x)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/pooling.py", line 595, in forward
self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override)
RuntimeError: Given input size: (512x6x6). Calculated output size: (512x0x0). Output size is too small

Could you please let me know how to fix this?

Thank you very much.

I meet the same question, too.

[tiber2013]

Hi,

I am running with CUB with the following command:
python3 main.py --dataset_root dataset --config config/5way_1shot_resnet12_cub-200.py --num_gpu 1 --mode train

And I got this error
File "main.py", line 579, in
main()
File "main.py", line 570, in main
trainer.train()
File "main.py", line 105, in train
last_layer_data, second_last_layer_data = backbone_two_stage_initialization(all_data, self.enc_module)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/utils.py", line 197, in backbone_two_stage_initialization
encoded_result = encoder(data.squeeze(1))
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/backbone.py", line 101, in forward
x = self.avgpool(x)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/pooling.py", line 595, in forward
self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override)
RuntimeError: Given input size: (512x6x6). Calculated output size: (512x0x0). Output size is too small

Could you please let me know how to fix this?

Thank you very much.

I fixed this by rolling back pytorch version to 1.1.0

[zilunzhang]

Hi,

I am running with CUB with the following command:
python3 main.py --dataset_root dataset --config config/5way_1shot_resnet12_cub-200.py --num_gpu 1 --mode train

And I got this error
File "main.py", line 579, in
main()
File "main.py", line 570, in main
trainer.train()
File "main.py", line 105, in train
last_layer_data, second_last_layer_data = backbone_two_stage_initialization(all_data, self.enc_module)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/utils.py", line 197, in backbone_two_stage_initialization
encoded_result = encoder(data.squeeze(1))
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data/add_disk0/vhnguyen/cvpr21/DPGN/backbone.py", line 101, in forward
x = self.avgpool(x)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/vhnguyen/anaconda2/envs/py36_torch1_7/lib/python3.6/site-packages/torch/nn/modules/pooling.py", line 595, in forward
self.padding, self.ceil_mode, self.count_include_pad, self.divisor_override)
RuntimeError: Given input size: (512x6x6). Calculated output size: (512x0x0). Output size is too small

Could you please let me know how to fix this?

Thank you very much.

Hi, we developed the model based on PyTorch 1.1.

In PyTorch 1.1, PyTorch seems to catch the exception where AvgPool2d size > remaining feature map size and fixed the exception automatically (That's the reason we didn't notice this bug).

In some other PyTorch version, PyTorch does not catch the exception.

You could solve the error by changing the PyTorch version to 1.1 or changing the size of AvgPool2d to 6.

Best,

DPGN teams