Commit 4033af30 authored by peastman's avatar peastman
Browse files

Use a larger default cache size for training sets

parent 9ddec96f

deepchem/splits/splitters.py

+2 −0
Original line number Diff line number Diff line
@@ -153,6 +153,8 @@ class Splitter(object): 
    else:

      valid_dataset = None

    test_dataset = dataset.select(test_inds, test_dir)

    if isinstance(train_dataset, DiskDataset):

      train_dataset.memory_cache_size = 40 * (1 << 20)  # 40 MB



    return train_dataset, valid_dataset, test_dataset

deepchem/utils/save.py

+1 −0
Original line number Diff line number Diff line
@@ -292,6 +292,7 @@ def load_dataset_from_disk(save_dir): 
  train = deepchem.data.DiskDataset(train_dir)

  valid = deepchem.data.DiskDataset(valid_dir)

  test = deepchem.data.DiskDataset(test_dir)

  train.memory_cache_size = 40 * (1 << 20)  # 40 MB

  all_dataset = (train, valid, test)

  with open(os.path.join(save_dir, "transformers.pkl"), 'rb') as f:

    transformers = pickle.load(f)

CRA Git | Maintained and supported by SUSTech CRA and CCSE