AssertionError: expected 4D input (got 3D input)

[sgs66]

Describe the bug
I'm running the example code in: 02_example_sig53_classifier.py, I encountered the following problem:

Environment Info
Python 3.9

Stacktra

Sanity Checking DataLoader 0: 0%| | 0/2 [00:00<?, ?it/s]Traceback (most recent call last):
File "/mnt/HDD1/sgs/torchsig-main/examples/02_example_sig53_classifier.py", line 230, in
trainer.fit(example_model)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 520, in fit
call._call_and_handle_interrupt(
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 44, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 559, in _fit_impl
self._run(model, ckpt_path=ckpt_path)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 935, in _run
results = self._run_stage()
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 976, in _run_stage
self._run_sanity_check()
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1005, in _run_sanity_check
val_loop.run()
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/loops/utilities.py", line 177, in _decorator
return loop_run(self, *args, **kwargs)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/loops/evaluation_loop.py", line 115, in run
self._evaluation_step(batch, batch_idx, dataloader_idx)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/loops/evaluation_loop.py", line 375, in _evaluation_step
output = call._call_strategy_hook(trainer, hook_name, *step_kwargs.values())
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 288, in _call_strategy_hook
output = fn(*args, **kwargs)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 378, in validation_step
return self.model.validation_step(*args, **kwargs)
File "/mnt/HDD1/sgs/torchsig-main/examples/02_example_sig53_classifier.py", line 194, in validation_step
loss = F.cross_entropy(self(x.float()), y)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/HDD1/sgs/torchsig-main/examples/02_example_sig53_classifier.py", line 168, in forward
return self.mdl(x.float())
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/timm/models/efficientnet.py", line 557, in forward
x = self.forward_features(x)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/timm/models/efficientnet.py", line 541, in forward_features
x = self.bn1(x)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/timm/models/layers/norm_act.py", line 67, in forward
_assert(x.ndim == 4, f'expected 4D input (got {x.ndim}D input)')
File "/home/sgs/.conda/envs/yolov5test/lib/python3.9/site-packages/torch/init.py", line 833, in _assert
assert condition, message
AssertionError: expected 4D input (got 3D input)

[gvanhoy]

Cannot reproduce from 0.3.1 :(.

What does pip show output?

I believe the model instantiated in the example script (efficientnet) should be expecting a 3D input. The project requirements call for timm==0.5.4, a different version of that may cause this error.

[sgs66]

Thank you. I solved the problem