New answers tagged

1 vote
Accepted

Which loss / activation function with 2 classes that do not occur often and do not sum to one?

This is multi-label classification, which means you have two binary classification problems, one for each of your classes. This is different than multi-class classification. For this use binary cross-...
  • 1,112
0 votes

flops do not change when pruning

I was able to prune the model correctly (not only change the sparsity but also change the flops and the number of parameters). I recommend using torch_pruning [https://github.com/VainF/Torch-Pruning] ...
  • 1
1 vote

Batching together similar length sequences to avoid padding and packing

You can read that this was done in "Attention is All You Need", for Transformers: "Sentence pairs were batched together by approximate sequence length.". But, with RNN you don't ...

Top 50 recent answers are included