Unclear about the model used for MNIST and FashionMNIST

brjathu / deepcaps

Official Implementation of "DeepCaps: Going Deeper with Capsule Networks" paper (CVPR 2019).

MIT License

151 stars 48 forks source link

Unclear about the model used for MNIST and FashionMNIST #1

Closed sairaamVenkatraman closed 5 years ago

sairaamVenkatraman commented 5 years ago

Hi. Thank you for uploading your code. Could you please clarify the architecture you used for MNIST and FashionMNIST. Is it the same as the one used for CIFAR-10 and SVHN? Thank you

brjathu commented 5 years ago

Hi, Thanks for the question. Yes, the architecture is same except the fact that the decoder will generate 28*28 gray scale images now. I have updated the code with new model, please check.

sairaamVenkatraman commented 5 years ago

Thanks a lot! You guys are amazing!