facebookresearch / facebookresearch/SlowFast

RuntimeError on new dataset

Open
#295 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.4k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

I am trying to train the ucf-101 dataset on slowfast network, and i used the SLOWFAST_8x8_R50_stepwise_multigrid.yaml file, but something wired happend when I run the run_net.py, does anyone know how to solve the problem?

`File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 20, in _wrap
fn(i, *args)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/slowfast/utils/multiprocessing.py", line 60, in run
ret = func(cfg)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/tools/train_net.py", line 384, in train
misc.log_model_info(model, cfg, use_train_input=True)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/slowfast/utils/misc.py", line 173, in log_model_info
get_model_stats(model, cfg, "flop", use_train_input)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/slowfast/utils/misc.py", line 151, in get_model_stats
count_dict, *_ = model_stats_fun(model, inputs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/fvcore/nn/flop_count.py", line 57, in flop_count
total_flop_counter, skipped_ops = get_jit_model_analysis(
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/fvcore/nn/jit_handles.py", line 99, in get_jit_model_analysis
trace, _ = torch.jit._get_trace_graph(model, inputs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/jit/__init__.py", line 338, in _get_trace_graph
outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/jit/__init__.py", line 421, in forward
graph, out = torch._C._create_graph_by_tracing(
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/jit/__init__.py", line 412, in wrapper
outs.append(self.inner(*trace_inputs))
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 720, in _call_impl
result = self._slow_forward(*input, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 704, in _slow_forward
result = self.forward(*input, **kwargs)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/slowfast/models/video_model_builder.py", line 389, in forward
x = self.s1(x)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 720, in _call_impl
result = self._slow_forward(*input, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 704, in _slow_forward
result = self.forward(*input, **kwargs)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/slowfast/models/stem_helper.py", line 114, in forward
x[pathway] = m(x[pathway])
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 720, in _call_impl
result = self._slow_forward(*input, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 704, in _slow_forward
result = self.forward(*input, **kwargs)
File "/home/dvc614/home/dvc614/Documents/Mei/Facebook_slowfast/slowfast/models/stem_helper.py", line 190, in forward
x = self.conv(x)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 720, in _call_impl
result = self._slow_forward(*input, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/module.py", line 704, in _slow_forward
result = self.forward(*input, **kwargs)
File "/home/dvc614/.virtualenvs/mei/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 566, in forward
return F.conv3d(input, self.weight, self.bias, self.stride,
RuntimeError: Calculated padded input size per channel: (0 x 164 x 164). Kernel size: (1 x 7 x 7). Kernel size can't be greater than actual input size`

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.