You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I build a neural network using ScatLayer as one layer.
when I export the model from pytorch to onnx format, error occurs.
pytorch_wavelets\utils.py", line 162, in reflect
out = np.where(normed_mod >= rng, rng_by_2 - normed_mod, normed_mod) + minx
TypeError: '>=' not supported between instances of 'numpy.ndarray' and 'Tensor'
The text was updated successfully, but these errors were encountered:
Ah bummer. Yeah I remember I had to do some funky things to get padding to work in the right way. It's several months later I know, but what command did you use to export to onnx? It might be possible to do the padding with torch tensors so the export works fine.
I build a neural network using ScatLayer as one layer.
when I export the model from pytorch to onnx format, error occurs.
pytorch_wavelets\utils.py", line 162, in reflect
out = np.where(normed_mod >= rng, rng_by_2 - normed_mod, normed_mod) + minx
TypeError: '>=' not supported between instances of 'numpy.ndarray' and 'Tensor'
The text was updated successfully, but these errors were encountered: