Ali Abedi

icon indicating a website link http://www.abedi.dev/

icon company University of Toronto icon location Toronto icon location def identify_vibe(username='ai_warrior'): return 'machine-learning wizard in action'

Results 2 issues of Ali Abedi

Handling variable length sequences

Thanks for sharing the code, Is your TCAN model (and code) able to handle variable-length sequences?

Training on variable-length sequences

1 comment

Is there any way to handle variable-length sequences and train TCN models on them ([the LSTM in PyTorch](https://pytorch.org/docs/stable/generated/torch.nn.utils.rnn.pack_padded_sequence.html) and also [the Keras implementation of TCN](https://github.com/philipperemy/keras-tcn/blob/master/tasks/multi_length_sequences.py) can handle variable-length sequences)?