Files
foundry/configs/datasets/val/base.yaml
Nathaniel Corley 5a492032d5 refactor: new modelhub (#109)
* Initial commit of chiral changes

Initial checkin of chiral feature code

Add chiral metric

* Update the way chiral features are incorporated into the model

Move initialization to new func

use default pytorch reset parameters

fix initialization for chirals

config

rename argument of confidence head

fix initialization for chirals

* refactor: src nest, rename rf2aa to modelhub

* refactor: initial commit without projects

* Initial commit of chiral changes

* Initial checkin of chiral feature code

* Add chiral metric

* Remove option for double residual connection.  Add kq_norm oiptions to base (20250125) config.

* Restoring flag

* config

* rename argument of confidence head

* Update the way chiral features are incorporated into the model

* config

* rename argument of confidence head

* Update the way chiral features are incorporated into the model

* Initial commit of chiral changes

Initial checkin of chiral feature code

Add chiral metric

* Update the way chiral features are incorporated into the model

Move initialization to new func

use default pytorch reset parameters

fix initialization for chirals

config

rename argument of confidence head

fix initialization for chirals

* refactor: new modelhub

---------

Co-authored-by: fdimaio <dimaio@uw.edu>
Co-authored-by: HaotianZhangAI4Science <haotianzhang@zju.edu.cn>
2025-04-08 13:33:17 -07:00

26 lines
1.0 KiB
YAML

dataset:
_target_: datahub.datasets.datasets.StructuralDatasetWrapper
save_failed_examples_to_dir: ${paths.data.failed_examples_dir}
cif_parser_args:
cache_dir: null
load_from_cache: False
save_to_cache: False
dataset:
_target_: datahub.datasets.datasets.PandasDataset
# we will use the example_id as the unique column
id_column: example_id
# return all keys (do not subset)
return_key: null
transform:
# common Transform pipeline components for all PDB datasets
_target_: ${datasets.pipeline_target}
is_inference: True
protein_msa_dirs: ${paths.data.protein_msa_dirs}
rna_msa_dirs: ${paths.data.rna_msa_dirs}
n_recycles: ${datasets.n_recycles_validation}
crop_size: null # do not crop for inference
n_msa: ${datasets.n_msa}
diffusion_batch_size: ${datasets.diffusion_batch_size_inference}
max_atoms_in_crop: null # do not crop for inference
return_atom_array: True # return atom array for inference
key_to_balance: ${datasets.key_to_balance}