titu1994 / Inception-v4

Inception-v4, Inception - Resnet-v1 and v2 Architectures in Keras
MIT License
385 stars 172 forks source link

Dropout rate is inverted #5

Open cebolan opened 6 years ago

cebolan commented 6 years ago

The rate of dropout seems to be inverted in your implementation. The inception v4 paper describes the dropout layer as keeping 80% of the units, but Keras' dropout layer takes the drop rate as a parameter. If I'm not mistaken, the model is actually keeping only 20% of the units.

I'm however not 100% sure about that; Keras' implementation of dropout seems to take a different approach (which I don't fully understand), but by reading the paper and Keras' docs, I believe the mistake is there.