Bo Zhang
The author wrote following words in paper: Additionally, we found that it was important to put very little or no weight decay (l2 regularization) on the depthwise filters since their...
HOW to prune the zero-weight in the conv layers after train the model using block_group_lasso or breadth_decay_mult? I found the sparsity rate in each conv layer apparently increased. Like 36%...
Thank you very much for your contribution. The author says in the original paper that "update the discriminators using a history of generated images rather than the ones produced by...