TimeDRL icon indicating copy to clipboard operation
TimeDRL copied to clipboard

[BUG] Why are my results poor?

Open ipc-robot opened this issue 1 year ago • 4 comments

I'm troubled by the model's performance. I didn't change anything, I just modified the config according to the json file. 2024-04-06 13-52-10屏幕截图 I choose the classification task and the dataset is "HAR".

ipc-robot avatar Apr 06 '24 05:04 ipc-robot

This is my result just before the pre-training stage's epoch 9. image

Remember, when utilizing the hyperparameter settings defined in exp_settings_and_results, you should execute the following command: python main.py --overwrite_args.

blacksnail789521 avatar Apr 06 '24 07:04 blacksnail789521

Yes, the fixed and tunable params would be updated. image

blacksnail789521 avatar Apr 06 '24 08:04 blacksnail789521

Now the neural network is running and looks great! Can I save the best model parameters? I passed the path to the early stopping module, but the saved one doesn't seem to be the best one, which bothers me.

ipc-robot avatar Apr 06 '24 09:04 ipc-robot

Ok, I'll try to fix it in the future, currently busy with another paper.

blacksnail789521 avatar Apr 09 '24 08:04 blacksnail789521