search

heuritech / convnets-keras

MIT License
594 stars 185 forks source link

Why don't you assign regularisation to the layers? #42

Open miguelmartin75 opened 7 years ago

miguelmartin75 commented 7 years ago

I'm comparing your model to caffe's implementation of AlexNet, where they use L2 regularisation for the weights (not bias).

Just wondering, why you don't do the same?