Files
foundry/models/rfd3/configs/datasets/train/af2db_interdomain_distillation.yaml
Jasper Butcher 5e7b739ed3 Add initial RFD3 Files and passing tests
* Add initial files

* add files

* Move projects.aa_design -> rfd3

* Make format

* Delete test files

* Add configs

* Mc

* Fixed tests

* remove test files
2025-11-11 10:07:43 -08:00

41 lines
1.0 KiB
YAML

defaults:
- pdb/base_transform_args@interdomain_distillation
- _self_
interdomain_distillation:
dataset:
_target_: atomworks.ml.datasets.datasets.StructuralDatasetWrapper
cif_parser_args:
cache_dir: null
load_from_cache: False
save_to_cache: False
dataset_parser:
_target_: atomworks.ml.datasets.parsers.GenericDFParser
pn_unit_iid_colnames:
- pn_unit_1_iid
- pn_unit_2_iid
path_colname: path
dataset:
_target_: atomworks.ml.datasets.datasets.PandasDataset
name: af2db_interdomain_distillation
data: /projects/ml/datahub/dfs/af2db_interdomain_dset.parquet
id_column: example_id
columns_to_load:
- example_id
- path
- pn_unit_1_iid
- pn_unit_2_iid
- cluster
transform:
crop_contiguous_probability: 0.0
crop_spatial_probability: 1.0
weights:
_target_: atomworks.ml.samplers.calculate_weights_by_inverse_cluster_size
cluster_column: cluster