Abour similar_small_index

[zhongshaoyy]

When running the code, I found that the similar_small_index always includes indexes from 0 to n,such as [0,1,2,3,4,5,6,7,8] .And the similar_sum matrix always has some equal numbers in the matrix. Is this because there are some setttings to constrain the matrix?

[yyx1107]

similar_pruned_num = int(weight_torch.size()[0] * distance_rate)
...
similar_small_index = similar_sum.argsort()[: similar_pruned_num]
The distance_rate is an invariant constant, so the num of filters that should be pruned each layer is also invariant.Or you can add me QQ 1017176539 .Maybe I can help you with the issue.

[he-y]

Please read the code to find the definition of these parameters.

These pruning rates are pre-defined. Please read section 4.1. Experimental Settings of our paper for details.