Skip to content

question about train FVC  #21

Description

@WenBingo

when i run the main.py , it trackback blow:

Traceback (most recent call last):
File "E:\Code_of_shenbin\code_of_reconfiguration\Video\FVC\main.py", line 290, in
global_step = train(epoch, global_step)
File "E:\Code_of_shenbin\code_of_reconfiguration\Video\FVC\main.py", line 190, in train
seqout["rd_loss"].backward()
File "D:\Anaconda\envs\pytorch\lib\site-packages\torch_tensor.py", line 487, in backward
torch.autograd.backward(
File "D:\Anaconda\envs\pytorch\lib\site-packages\torch\autograd_init_.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
File "D:\Anaconda\envs\pytorch\lib\site-packages\torch\autograd\function.py", line 274, in apply
return user_fn(self, *args)
File "D:\Anaconda\envs\pytorch\lib\site-packages\torch\autograd\function.py", line 522, in wrapper
outputs = fn(ctx, *args)
File "E:\Code_of_shenbin\code_of_reconfiguration\Video\FVC\subnet\dcn\deform_conv.py", line 73, in backward
deform_conv_cuda.deform_conv_backward_parameters_cuda(
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

and when i run the /dcn/setup.py it traceback :

usage: setup.py [global_opts] cmd1 [cmd1_opts] [cmd2 [cmd2_opts] ...]
or: setup.py --help [cmd1 cmd2 ...]
or: setup.py --help-commands
or: setup.py cmd --help

error: no commands supplied

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions