cnn-text-classification-pytorch icon indicating copy to clipboard operation
cnn-text-classification-pytorch copied to clipboard
verified publisher icon Shawn1993

Performance on MR dataset

Open nick11roberts opened this issue 5 years ago • 2 comments

Hi there, I see that the best reported accuracy for this repo for the MR dataset is 77.5% using CNN-rand-static. When I run this, using ./main.py -device=0 -static, I get much lower numbers (~70%). Two questions:

  1. What training settings are you using to get 77.5%?
  2. How are you evaluating on the MR dataset to get 77.5%?

Thanks!

nick11roberts avatar Sep 19 '20 22:09 nick11roberts

same problem.

A11en0 avatar Jun 03 '21 12:06 A11en0

Hi there, I see that the best reported accuracy for this repo for the MR dataset is 77.5% using CNN-rand-static. When I run this, using ./main.py -device=0 -static, I get much lower numbers (~70%). Two questions:

  1. What training settings are you using to get 77.5%?
  2. How are you evaluating on the MR dataset to get 77.5%?

Thanks!

How did you handle the problem?

A11en0 avatar Jun 03 '21 12:06 A11en0