Hierarchical-attention-networks-pytorch icon indicating copy to clipboard operation
Hierarchical-attention-networks-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon uvipen

Handle batch size in Hidden state initialization for train set.

Open giridharmunagala opened this issue 4 years ago • 0 comments

Batch size in the last batch is handled for Evaluation dataset but not for train. Resulting in wrong dimension for Hidden state for word attention net.

https://github.com/uvipen/Hierarchical-attention-networks-pytorch/blob/b1ea9e0b7bc294364f213e42507a6fe9d502a044/train.py#L85

giridharmunagala avatar Oct 21 '21 18:10 giridharmunagala