Hi,
Thank you for sharing nice codes!!
It will be really helpful to me.

Could you explain how to use pretrained model to get an accuracy?
I am new to pytorch.

Are we supposing the same length for each sentence in the position encoding?

As in above, each sentence encoding is divided by the same number elen-1.

How to add an interactive module for new paragraph and question?

Thank you for your unselfish sharing and nice work.

I noticed that the test accuracy writed in log.txt is as

fp.write(f'[Run {run}, Task {task_id}, Epoch {epoch}] [Test] Accuracy : {total_acc: {5}.{4}}' + '\n')

But the total_acc is the valid accuracy while test_acc / cnt is the correct one.

Hi. I'm pretty much a newbie at neural networks. This is a question I asked on the yerevann blog site but I never got an answer. I'm using your code as something of a guide along with the yerevann code. I'm programming in Pytorch. (I also use part of the yerevann data loader. That code is properly attributed to them.) I'm trying to implement a similar DMN for the babi set. My code is here: https://github.com/radiodee1/awesome-chatbot . Here's a question I have.

I split the training and testing data into parts for training, testing, and validation. I use 1000 parts for training, 500 parts for testing and 500 parts for validation. I run into a problem. I can train successfully but when I go to the validation step I never get a score above 50% accuracy. My question to you is what part of the program would be responsible for this kind of behavior? In other words, can you tell me why I'm always getting 50% ?? Thanks for your time. I understand this blog is pretty old. I'm limiting my experiments to the first babi test. I thought I had an answer to this question and then it popped up again and I cannot get rid of it.

thanks again.