Md Hasan

Results 6 comments of Md Hasan

To do this, first, save the picture(output) in a variable `im = hl.build_graph(model_name, torch.zeros([64,3,7,7]))` (your size in place of torch.zeros([64,3,7,7]) Then save it giving the path with a name of...

By using MT5Tokenizer and MT5Model, you can generate question for other language.

> @mdhasanai > > can you give an example code? Use T5Tokenizer when you preprocess the data in prepare_data.py For example, use this ```python from transformers import MT5Tokenizer, BartTokenizer, HfArgumentParser...

I also got the same problem.

I got the same problem.. and i solved it.. When you load image, make sure that the image has three color channel (RGB) because it might be gray scale. So...

I found this great tutorial to learn about Transformers. Link: (http://jalammar.github.io/illustrated-transformer/) If you decided to implement in PyTorch than this link is going to help you. (http://nlp.seas.harvard.edu/2018/04/03/attention.html)