Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

The result of Epoch 299. Top1 #5

Closed
aihcyllop opened this issue Feb 21, 2022 · 1 comment
Closed

The result of Epoch 299. Top1 #5

aihcyllop opened this issue Feb 21, 2022 · 1 comment

Comments

@aihcyllop
Copy link

When I run the following command, I got the result:

  • INFO - train - Epoch 299. Top1: 65.9493. Top5: 88.9249 result.
    I want to ask what other parameters can be adjusted to achieve better result, thank you!
    Or did I write something wrong? Thank you!

=======
command

--word-vec-path C:/Users/Aihcyllop/Desktop/semco-main/numberbatch-en-19.08_128D.dict.pkl --dataset-name cifar100 --train-split-pickle splits/cifar100_labelled_data_25_seed123.pkl --model_backbone=wres --wres-k=2 --no_amp

=======
result

2022-02-19 07:11:57,178 - INFO - train - Epoch 299. Top1: 65.9493. Top5: 88.9249. Top1_emb: 65.2811. Top5_emb: 82.3998. Top1_comb: 65.5660. best_metric: 66.1557 in epoch282
2022-02-19 07:11:57,180 - INFO - train - Break epoch is reached

@islam-nassar
Copy link
Owner

Hi,

If you look at the results in our paper, this is the best result you can get with the current configuration (2500 labelled samples, mu=3). If you want to get the 68.01%, you need to use mu=7

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants