Closed Xu-kexin closed 1 year ago
Hi, that command should generate the cache with id 1, then when you run with --cache_creation_id 2 it will generate the second... once you have all of them you can run the command and it will start training (they are meant to be run in parallel)
Thank you!
Hello, thanks for your work. I saw in the readme you write "run --cache_creation_id 1 then --cache_creation_id 2", but when I use this command "python -m confidence.confidence_train --original_model_dir workdir/small_score_model --run_name confidence_model --inference_steps 20 --samples_per_complex 7 --batch_size 16 --n_epochs 100 --lr 3e-4 --scheduler_patience 50 --ns 24 --nv 6 --num_conv_layers 5 --dynamic_max_cross --scale_by_sigma --dropout 0.1 --all_atoms --remove_hs --c_alpha_max_neighbors 24 --receptor_radius 15 --esm_embeddings_path data/esm2_3billion_embeddings.pt --main_metric loss --main_metric_goal min --best_model_save_frequency 5 --rmsd_classification_cutoff 2 --cache_creation_id 1 --cache_ids_to_combine 1 2 3 4", it throws the exception "ith cache_id do not exist: {cache_id}') # be careful with changing this error message since it is sometimes cought in a try catch Exception: The generated ligand positions with cache_id do not exist: 2". I would like to ask about the generation of files in cacheNew/xxx/ligand_positions_idxxx.pkl? (now I saw only the one with id1). Could you give me the way to train the confidence model with cache id more than one? Thank you so much!