Closed philnguyenresson closed 2 years ago
Hi @philnguyenresson,
I think there are many flavors of the data processing for the inception network. It very much depends on the model you have. For example Pytorch implementation uses channel-wise normalization. Also, this is just an example. You should adjust it to the data processing applied during the training of your models.
Sure, I will make modifications as I need them for my own code. I'm just talking about the model given in the example "inception_v3_2016_08_28_frozen", which I believe was trained with [-1,1] normalization
The inception_ensemble example uses channel-wise mean/std normalization, whereas I believe the source inception model just rescales to [-1,1] see here