When running the train of my custom data, this happens. I'm investing on what is it causing it. Still can't find the cause.
Any help would be apreciated. Thank you
Traceback (most recent call last):
File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/pytorch/PVN3D/pvn3d/train/train_blm_pvn3d.py", line 547, in <module>
best_loss=best_loss
File "/home/pytorch/PVN3D/pvn3d/train/train_blm_pvn3d.py", line 376, in train
_, loss, res = self.model_fn(self.model, batch)
File "/home/pytorch/PVN3D/pvn3d/train/train_blm_pvn3d.py", line 196, in model_fn
pred_kp_of, kp_targ_ofst, labels,
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/torch/nn/parallel/data_parallel.py", line 153, in forward
return self.module(*inputs[0], **kwargs[0])
File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/home/pytorch/PVN3D/pvn3d/lib/loss.py", line 86, in forward
sigma=1.0, normalize=True, reduce=False
File "/home/pytorch/PVN3D/pvn3d/lib/loss.py", line 58, in of_l1_loss
kp_targ_ofst = kp_targ_ofst.view(bs, n_pts, n_kpts, 3)
RuntimeError: shape '[2, 12288, 8, 3]' is invalid for input of size 7372800
I put different keypoints for better visualization of my data. By setting them back to self.n_keypoints = 8 in common.py I was able to solve the problem
When running the train of my custom data, this happens. I'm investing on what is it causing it. Still can't find the cause. Any help would be apreciated. Thank you