fengshikun

Results 9 comments of fengshikun

@wang21jun , thanks for your explanation, still i have some questions, i notice that the mask texture file under path Data/mask-data(called 0.png, 1.png...) is a 4-channel matrix. 1.Is that 0-3...

Sorry, I just checked the logs and noticed that Val inference rmsds_lt2 consistently remains zero. Additionally, the validation loss shows fluctuating and abnormal values such as: ``` Epoch 19: Validation...

I have trained for approximately 100 epochs, and the latest results for Val inference rmsds_lt2 are consistently zero, as shown below: ``` Epoch 89: Val inference rmsds_lt2 0.000 rmsds_lt5 0.000...

Below is the complete training log file for your reference. [big_score_model_resume.log](https://github.com/user-attachments/files/16244835/big_score_model_resume.log)

> Could you try --limit_complexes 100 and setting the train set to validation set? > > i.e. --split_train data/splits/timesplit_no_lig_overlap_val_aligned --split_val data/splits/timesplit_no_lig_overlap_val_aligned --limit_complexes 100 > > And see if the problem...

> Maybe related: #6 (which has been fixed). So maybe it is worth to pull again Got it, thanks for the remainder

> Maybe related: #6 (which has been fixed). So maybe it is worth to pull again I have pulled the newest version of the codebase and trained the scoring model...

> @fengshikun hi, were you able to train the model? The loss still cannot converge.