Evaluation batch

[celestialxevermore]

Dear Author, I feel always thankful for your reply.

Q1. Here is another quetion, In the training code, is there any difference in performance if I change the batch_size_eval 16 to the number bigger than 16 such as 64 or 96?

Q2. Plus, I wonder about the 'num_thread_reader' value. does it concerned with GPU memory? or model Performance?

Thx :)

Sincerely,