Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

Fix CosineEmbeddingLoss in when symbol API is used #17308

Merged
merged 2 commits into from
Jan 15, 2020
Merged

Fix CosineEmbeddingLoss in when symbol API is used #17308

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8502f79
Fix CosineEmbeddingLoss in when symbol API is used
dithyrambe Jan 14, 2020
ef3091c
Update CONTRIBUTORS.md
dithyrambe Jan 14, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CONTRIBUTORS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,6 +247,7 @@ List of Contributors
* [Disi A](https://github.com/adis300)
* [Vandana Kannan](https://github.com/vandanavk)
* [Guanxin Qiao](https://github.com/guanxinq)
* [dithyrambe](https://github.com/dithyrambe)

Label Bot
---------
Expand Down
6 changes: 3 additions & 3 deletions python/mxnet/gluon/loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -922,9 +922,9 @@ def hybrid_forward(self, F, input1, input2, label, sample_weight=None):

def _cosine_similarity(self, F, x, y, axis=-1):
# Calculates the cosine similarity between 2 vectors
x_norm = F.norm(x, axis=axis).reshape(-1, 1)
y_norm = F.norm(y, axis=axis).reshape(-1, 1)
x_dot_y = F.sum(x * y, axis=axis).reshape(-1, 1)
x_norm = F.norm(x, axis=axis).reshape((-1, 1))
y_norm = F.norm(y, axis=axis).reshape((-1, 1))
x_dot_y = F.sum(x * y, axis=axis).reshape((-1, 1))
if F is ndarray:
eps_arr = F.array([1e-12])
else:
Expand Down