search

scheckmedia / keras-shufflenet

ShuffleNet Implementation using Keras Functional Framework 2.0
MIT License
77 stars 40 forks source link

BN after first Conv2D #6

Closed afzalxo closed 5 years ago

afzalxo commented 5 years ago

Hey! There is supposed to be a batch-norm between the first Conv2D and the 3x3 max-pool in stage1. The pre-trained weight file that I'm using (ShuffleNetV1-1x-g=8.npz) contains these parameters (gamma, beta, mean and variance for BN for conv1). Could you please confirm if there is a BN in your pretrained model? I can't check since the link to your model is dead.

Thanks

scheckmedia commented 5 years ago

Hey, this implementation uses no batch norm for the stage 1, you can check the model graph. You are right the link is dead but the weight file is located in the weight folder of the repository.

afzalxo commented 5 years ago

Got it... Thanks!