Sandeep Tammu

I am sorry but I will no longer be maintaining this project, especially when it comes to Python 3 support. Please have a look at the other implementation of the...

I think transpose was used because PyTorch expects the batch_size in the second dimension, it's been a while since I have coded this. But, I have checked all the dimensions...

I am not quite sure if there is an issue, it's been a long time. I believe I'm also doing a transpose while creating the mini-batch itself, so we have...

In hindsight, I would have used a single optimiser using something like this. optim.Adam(list(model1.parameters()) + list(model2.parameters()) At that time, I was new to PyTorch and didn't know this. You can...

Hi, I'm sorry that I don't understand what you are asking for. You will have to initialise both the forward and the backward states initially to start the training process....

Yeah, np.max should be used ideally. I used mean because it is consuming too much of GPU memory. Now, I think you should ideally sort samples with their lengths so...

I am afraid not.