Porting to Tensorflow / Keras. Help Needed

[SarthakYadav]

Hello

I am trying to reproduce the results of this paper using Keras. I have implemented the loss function as seen in the paper, but the accuracy of the classifier never goes above 10%.
To test the loss implementation, I am using a tiny CNN trained from scratch. The model structure is as seen in the image attached. I have also tried building on top of a pre-trained VGG16, but the results are the same.

As seen from the name, the second last layer called "latent_48bit" is the latent layer with the sigmoid activation. The final layer is the softmax classifier.

Is the model architecture correct?

Also, can you help me with the loss function? I believe that's where I am going wrong.

[kevinlin311tw]

How about removing your loss function, and training with only the softmax loss function at first? 2017-07-19 23:25 GMT-07:00 Sarthak Yadav <[email protected]>:

…

Hello I am trying to reproduce the results of this paper using Keras. I have implemented the loss function as seen in the paper, but the accuracy of the classifier never goes above 10%. To test the loss implementation, I am using a tiny CNN trained from scratch. The model structure is as seen in the image attached. I have also tried building on top of a pre-trained VGG16, but the results are the same. [image: model] <https://user-images.githubusercontent.com/8536280/28368776-39529454-6cb3-11e7-9c5a-52c4c3f3b9aa.png> As seen from the name, the second last layer called "latent_48bit" is the latent layer with the sigmoid activation. The final layer is the softmax classifier. Is the model architecture correct? Also, can you help me with the loss function? I believe that's where I am going wrong. — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#18>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AJgtML6hLFWAAmX2RjZlEgriFjXQpIZzks5sPvLNgaJpZM4Odp0F> .

-- Best regards, 林可昀 Kevin Lin

[SarthakYadav]

Trains fine with Softmax!