julius/prototorch_models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Revert deletion of training accuracy.

Browse Source
This commit is contained in:
Alexander Engelsberger 2021-05-06 18:02:01 +02:00
parent 1c3613019b
commit 5a2f4f6170
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
prototorch/models/glvq.py
View File

@ -52,6 +52,8 @@ class GLVQ(AbstractPrototypeModel):
# Compute training accuracy # Compute training accuracy
with torch.no_grad(): with torch.no_grad():
preds = wtac(dis, plabels) preds = wtac(dis, plabels)
self.train_acc(preds.int(), y.int())
# `.int()` because FloatTensors are assumed to be class probabilities # `.int()` because FloatTensors are assumed to be class probabilities
# Logging # Logging