Commit d8011e30 authored by lucas_miranda's avatar lucas_miranda
Browse files

Implemented weight saving callback in model_training.py

parent ed3b7821
......@@ -319,7 +319,7 @@ for i in range(len(checkpoints) + 1):
encs.append(
reducer.fit_transform(predictions[i], np.argmax(clusters[i - 1], axis=1))
)
print("ENCS:",encs)
# As projection direction is difficult to predict in LDA,
# axes are flipped to maintain subsequent representations
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment