Why this snippet returns 0 gradients? Pytorch RNN understanding
I’m trying to understand how slicing the output affects the gradients in a RNN. I built this simple script.
Can I use neural network to do this classification task?
I have some time sequences(sampled at 0.5s and 3kHz which means every one of them has 1,500 points) and want to do a binary classification through a neural network. Sequences are looked as photos photo1,photo3. You can easily find that curves in photo 1 have sharper change than photo 3. So I want to design a neural network to do that.