Abhishek Sinha

Doubly stochastic regularization coeffieicent

2

When computing the value of doubly stochastic loss, why do you use the fraction 16/196? Shouldn't it be 1 going by the paper?

In coin game the input shape is [4,grid_size,grid_size]. Shouldn't the input be transposed before passing to the model in networks.py so that the channel(4) becomes the last dimension?

Comparison with standard model

1

Any suggestions on how to compare the training time with a non-binary MLP of same complexity? i.e. maybe a set of opt flags that I need to turn off to...

Complete implementation of CW attack

4

I was trying to reproduce the results of the paper. Can you suggest how do I get the results for the CW attack ?

Flatten layer

5

How can i handle the layers of type 'Flatten' ? On running convert.py it says:- 'Error encountered: Output shape computation not implemented for type: Flatten'

experiments over tiered ImageNet dataset

1

Hi, I wanted to know if you had run baseline/baseline++ over the tiered ImageNet dataset. If so, can you share the performance results over it also?

Confusion regarding usage of pyspark.mlllib

4

In the examples you are using pyspark.ml library but what if I have to do the classification using SVM via the pyspark.mllib library . How can i implement the 'fit()'...