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
Currently my PyTorch model has the following inputs:
A tensor with size (B, 1, 300) where B is the batch size
A list of pack_padded_sequence objects, each of which has size (T, B, 300) where T is the maximum length among the batch and B is the batch size.
When I tried to convert the model from Pytorch to TensorRT, I got the error: AttributeError: 'list' object has no attribute 'clone'
I also tried to retrieve each pack_padded_sequence object from the list and pass them one by one into the model, but got: AttributeError: 'list' object has no attribute 'clone'.
Is it possible to support list or pack_padded_sequence as model input?
The text was updated successfully, but these errors were encountered:
Currently my PyTorch model has the following inputs:
When I tried to convert the model from Pytorch to TensorRT, I got the error:
AttributeError: 'list' object has no attribute 'clone'
I also tried to retrieve each pack_padded_sequence object from the list and pass them one by one into the model, but got:
AttributeError: 'list' object has no attribute 'clone'
.Is it possible to support list or pack_padded_sequence as model input?
The text was updated successfully, but these errors were encountered: