MatDeepLearn_dev/configs/config.yml at 610f4652f20afd2c7b74a441cec89f4abdb1acff · Fung-Lab/MatDeepLearn_dev · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
trainer: property

task:
  run_mode: "train"
  identifier: "my_train_job"
  parallel: False
  use_wandb: True
  wandb_entity: "fung-lab"
  wandb_project: "cgcnn_vn"

  seed: 12345678
  # Defaults to run directory if not specified
  save_dir:
  continue_job: False
  load_training_state: False
  # Path to the checkpoint file
  checkpoint_dir:
  write_output: True

model:
  name: CGCNN
  save_model: True
  model_path: "cgcnn.pth"
  edge_steps: 50
  self_loop: True
  # model attributes
  # model attributes
  dim1: 100
  dim2: 150
  pre_fc_count: 1
  gc_count: 4
  post_fc_count: 3
  pool: "global_mean_pool"
  pool_order: "early"
  batch_norm: True
  batch_track_stats: True
  act: "relu"
  dropout_rate: 0.0

optim:
  max_epochs: 40
  max_epochs: 250
  max_checkpoint_epochs: 0
  max_checkpoint_epochs: 0
  lr: 0.002
  # Either custom or from torch.nn.functional library. If from torch, loss_type is TorchLossWrapper
  # Either custom or from torch.nn.functional library. If from torch, loss_type is TorchLossWrapper
  loss:
    loss_type: "TorchLossWrapper"
    loss_args: {"loss_fn": "l1_loss"}

  batch_size: 64
  optimizer:
    optimizer_type: "AdamW"
    optimizer_args: {}
  scheduler:
    scheduler_type: "ReduceLROnPlateau"
    scheduler_args: {"mode":"min", "factor":0.8, "patience":10, "min_lr":0.00001, "threshold":0.0002}
  #Training print out frequency (print per n number of epochs)
  verbosity: 5

dataset:
  name: "test_data"
  processed: False
  # Path to data files - this can either be in the form of a string denoting a single path or a dictionary of {train: train_path, val: val_path, test: test_path, predict: predict_path}
  src: data/test_data/data_graph_scalar.json
  # Path to target file within data_path - this can either be in the form of a string denoting a single path or a dictionary of {train: train_path, val: val_path, test: test_path} or left blank when the dataset is a single json file
  # Example: target_path: "data/raw_graph_scalar/targets.csv"
  target_path:
  # Path to save processed data.pt file
  pt_path: "data/"
  # Either "node" or "graph"
  prediction_level: "graph"

  transforms:
    - name: GetY
      args:
        # index specifies the index of a target vector to predict, which is useful when there are multiple property labels for a single dataset
        # For example, an index: 0 (default) will use the first entry in the target vector
        # if all values are to be predicted simultaneously, then specify index: -1
        index: -1
      otf: True # Optional parameter, default is False
  all_neighbors : True
  # one of mdl (minimum image convention), ocp (all neighbors included)
  edge_calc_method: "mdl"
  # Format of data files (limit to those supported by ASE: https://wiki.fysik.dtu.dk/ase/ase/io/io.html)
  data_format: "json"
  # Method of obtaining atom dictionary: available: (onehot)
  node_representation: "onehot"
  additional_attributes: []
  # Print out processing info
  # Print out processing info
  verbose: True
  use_virtual_nodes: False
  # graph specific settings
  preprocess_params:
    cutoff_radius : 8.0
    n_neighbors : 250
    num_offsets: 1
    edge_steps : 50
  # Ratios for train/val/test split out of a total of less than 1
  train_ratio: 0.85
  val_ratio: 0.05
  test_ratio: 0.10