New answers tagged pytorch
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 ...
- 11
Top 50 recent answers are included
Related Tags
pytorch × 195deep-learning × 34
neural-networks × 33
reinforcement-learning × 31
convolutional-neural-networks × 28
tensorflow × 18
natural-language-processing × 15
transformer × 15
python × 14
objective-functions × 14
machine-learning × 12
actor-critic-methods × 10
classification × 9
recurrent-neural-networks × 9
implementation × 9
training × 8
deep-rl × 8
keras × 7
long-short-term-memory × 7
dqn × 7
generative-adversarial-networks × 7
policy-gradients × 7
terminology × 5
optimization × 5
variational-autoencoder × 5