You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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!
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
When I run the following command, I got the 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
The text was updated successfully, but these errors were encountered: