def LoadData(DATASET_NAME):
"""
This function is called in the main.py file
returns:
; dataset object
"""
# handling for MNIST or CIFAR Superpixels
if DATASET_NAME == 'MNIST' or DATASET_NAME == 'CIFAR10':
return SuperPixDataset(DATASET_NAME)
# handling for (ZINC) molecule dataset
if DATASET_NAME == 'ZINC':
return MoleculeDataset(DATASET_NAME)
# handling for the TU Datasets
TU_DATASETS = ['ENZYMES', 'DD', 'PROTEINS_full']
if DATASET_NAME in TU_DATASETS:
return TUsDataset(DATASET_NAME)
# handling for SBM datasets
SBM_DATASETS = ['SBM_CLUSTER', 'SBM_PATTERN']
if DATASET_NAME in SBM_DATASETS:
return SBMsDataset(DATASET_NAME)
# handling for TSP dataset
if DATASET_NAME == 'TSP':
return TSPDataset(DATASET_NAME)
# handling for COLLAB dataset
if DATASET_NAME == 'OGBL-COLLAB':
return COLLABDataset(DATASET_NAME)
# handling for the CSL (Circular Skip Links) Dataset
if DATASET_NAME == 'CSL':
return CSLDataset(DATASET_NAME)
def LoadData(DATASET_NAME):
"""
This function is called in the main.py file
returns:
; dataset object
"""
# handling for MNIST or CIFAR Superpixels
if DATASET_NAME == 'MNIST' or DATASET_NAME == 'CIFAR10':
return SuperPixDataset(DATASET_NAME)
# handling for SBM datasets
SBM_DATASETS = ['SBM_CLUSTER', 'SBM_PATTERN']
if DATASET_NAME in SBM_DATASETS:
return SBMsDataset(DATASET_NAME)
def LoadData(DATASET_NAME):
"""
This function is called in the main.py file
returns:
; dataset object
"""
# handling for (ZINC) molecule dataset
if DATASET_NAME == 'ZINC' or DATASET_NAME == 'ZINC-full':
return MoleculeDataset(DATASET_NAME)
# handling for SBM datasets
SBM_DATASETS = ['SBM_CLUSTER', 'SBM_PATTERN']
if DATASET_NAME in SBM_DATASETS:
return SBMsDataset(DATASET_NAME)
def load_data(args):
if args.data in ['ZINC']:
return MoleculeDataset(args.data)
elif args.data in ['QM9']:
return QM9Dataset(args.data, args.extra)
elif args.data in ['TSP']:
return TSPDataset(args.data)
elif args.data in ['MNIST', 'CIFAR10']:
return SuperPixDataset(args.data)
elif args.data in ['SBM_CLUSTER', 'SBM_PATTERN']:
return SBMsDataset(args.data)
elif args.data in ['Cora']:
return CoraDataset(args.data)
else:
raise Exception('Unknown dataset!')
def LoadData(DATASET_NAME):
"""
This function is called in the main.py file
returns:
; dataset object
"""
toxic_reps = [
'PBT_Repn1', 'PBT_Repn2', 'PBT_Repn3', 'PBT_Repn4', 'PBT_Rep1',
'PBT_Rep2', 'PBT_Rep3', 'PBT_Rep4', 'CMR_Rep1', 'CMR_Rep2', 'CMR_Rep3',
'CMR_Rep4'
]
# handling for (TOX) molecule dataset
if DATASET_NAME in toxic_reps:
return TOXDataset(DATASET_NAME)
# handling for MNIST or CIFAR Superpixels
if DATASET_NAME == 'MNIST' or DATASET_NAME == 'CIFAR10':
return SuperPixDataset(DATASET_NAME)
# handling for (ZINC) molecule dataset
if DATASET_NAME == 'ZINC':
return MoleculeDataset(DATASET_NAME)
# handling for the TU Datasets
TU_DATASETS = ['COLLAB', 'ENZYMES', 'DD', 'PROTEINS_full']
if DATASET_NAME in TU_DATASETS:
return TUsDataset(DATASET_NAME)
# handling for SBM datasets
SBM_DATASETS = ['SBM_CLUSTER', 'SBM_PATTERN']
if DATASET_NAME in SBM_DATASETS:
return SBMsDataset(DATASET_NAME)
# handling for TSP dataset
if DATASET_NAME == 'TSP':
return TSPDataset(DATASET_NAME)
# handling for the CITATIONGRAPHS Datasets
CITATIONGRAPHS_DATASETS = ['CORA', 'CITESEER', 'PUBMED']
if DATASET_NAME in CITATIONGRAPHS_DATASETS:
return CitationGraphsDataset(DATASET_NAME)
def LoadData(DATASET_NAME):
"""
This function is called in the main.py file
returns:
; dataset object
"""
# handling for MNIST or CIFAR Superpixels
if DATASET_NAME == 'MNIST' or DATASET_NAME == 'CIFAR10':
return SuperPixDataset(DATASET_NAME)
# handling for (ZINC) molecule dataset
if DATASET_NAME == 'ZINC':
return MoleculeDataset(DATASET_NAME)
# handling for SBM datasets
SBM_DATASETS = ['SBM_CLUSTER', 'SBM_PATTERN']
if DATASET_NAME in SBM_DATASETS:
return SBMsDataset(DATASET_NAME)
# handling for the SGS (Synthetic Graph Spectrum) Dataset
SGS_DATASETS = ['SGS_HIGH_PASS', 'SGS_BAND_PASS', 'SGS_LOW_PASS']
if DATASET_NAME in SGS_DATASETS:
return SGSDataset(DATASET_NAME)
def main():
"""
USER CONTROLS
"""
parser = argparse.ArgumentParser()
parser.add_argument(
'--config',
help=
"Please give a config.json file with training/model/data/param details"
)
parser.add_argument('--gpu_id', help="Please give a value for gpu id")
parser.add_argument('--model', help="Please give a value for model name")
parser.add_argument('--dataset',
help="Please give a value for dataset name")
parser.add_argument('--seed', help="Please give a value for seed")
parser.add_argument('--epochs', help="Please give a value for epochs")
parser.add_argument('--batch_size',
help="Please give a value for batch_size")
parser.add_argument('--init_lr', help="Please give a value for init_lr")
parser.add_argument('--lr_reduce_factor',
help="Please give a value for lr_reduce_factor")
parser.add_argument('--lr_schedule_patience',
help="Please give a value for lr_schedule_patience")
parser.add_argument('--min_lr', help="Please give a value for min_lr")
parser.add_argument('--weight_decay',
help="Please give a value for weight_decay")
parser.add_argument('--print_epoch_interval',
help="Please give a value for print_epoch_interval")
parser.add_argument('--L', help="Please give a value for L")
parser.add_argument('--hidden_dim',
help="Please give a value for hidden_dim")
parser.add_argument('--out_dim', help="Please give a value for out_dim")
parser.add_argument('--residual', help="Please give a value for residual")
parser.add_argument('--edge_feat',
help="Please give a value for edge_feat")
parser.add_argument('--readout', help="Please give a value for readout")
parser.add_argument('--in_feat_dropout',
help="Please give a value for in_feat_dropout")
parser.add_argument('--dropout', help="Please give a value for dropout")
parser.add_argument('--graph_norm',
help="Please give a value for graph_norm")
parser.add_argument('--layer_norm',
help="Please give a value for layer_norm")
parser.add_argument('--batch_norm',
help="Please give a value for batch_norm")
parser.add_argument('--max_time', help="Please give a value for max_time")
parser.add_argument('--type_net', default='simple', help='Type of net')
parser.add_argument('--lap_norm',
default='none',
help='Laplacian normalisation')
# eig params
parser.add_argument('--aggregators', type=str, help='Aggregators to use.')
parser.add_argument('--scalers', type=str, help='Scalers to use.')
parser.add_argument('--towers', type=int, default=5, help='Towers to use.')
parser.add_argument('--divide_input_first',
type=bool,
help='Whether to divide the input in first layer.')
parser.add_argument('--divide_input_last',
type=bool,
help='Whether to divide the input in last layers.')
parser.add_argument('--edge_dim',
type=int,
help='Size of edge embeddings.')
parser.add_argument('--pretrans_layers', type=int, help='pretrans_layers.')
parser.add_argument('--posttrans_layers',
type=int,
help='posttrans_layers.')
parser.add_argument('--pos_enc_dim',
default=0,
type=int,
help='Positional encoding dimension')
args = parser.parse_args()
with open(args.config) as f:
config = json.load(f)
# device
if args.gpu_id is not None:
config['gpu']['id'] = int(args.gpu_id)
config['gpu']['use'] = True
device = gpu_setup(config['gpu']['use'], config['gpu']['id'])
# dataset
if args.dataset is not None:
DATASET_NAME = args.dataset
else:
DATASET_NAME = config['dataset']
dataset = SBMsDataset(DATASET_NAME,
pos_enc_dim=int(args.pos_enc_dim),
norm=args.lap_norm)
# parameters
params = config['params']
if args.seed is not None:
params['seed'] = int(args.seed)
if args.epochs is not None:
params['epochs'] = int(args.epochs)
if args.batch_size is not None:
params['batch_size'] = int(args.batch_size)
if args.init_lr is not None:
params['init_lr'] = float(args.init_lr)
if args.lr_reduce_factor is not None:
params['lr_reduce_factor'] = float(args.lr_reduce_factor)
if args.lr_schedule_patience is not None:
params['lr_schedule_patience'] = int(args.lr_schedule_patience)
if args.min_lr is not None:
params['min_lr'] = float(args.min_lr)
if args.weight_decay is not None:
params['weight_decay'] = float(args.weight_decay)
if args.print_epoch_interval is not None:
params['print_epoch_interval'] = int(args.print_epoch_interval)
if args.max_time is not None:
params['max_time'] = float(args.max_time)
# network parameters
net_params = config['net_params']
net_params['device'] = device
net_params['gpu_id'] = config['gpu']['id']
net_params['batch_size'] = params['batch_size']
if args.L is not None:
net_params['L'] = int(args.L)
if args.hidden_dim is not None:
net_params['hidden_dim'] = int(args.hidden_dim)
if args.out_dim is not None:
net_params['out_dim'] = int(args.out_dim)
if args.residual is not None:
net_params['residual'] = True if args.residual == 'True' else False
if args.edge_feat is not None:
net_params['edge_feat'] = True if args.edge_feat == 'True' else False
if args.readout is not None:
net_params['readout'] = args.readout
if args.in_feat_dropout is not None:
net_params['in_feat_dropout'] = float(args.in_feat_dropout)
if args.dropout is not None:
net_params['dropout'] = float(args.dropout)
if args.graph_norm is not None:
net_params['graph_norm'] = True if args.graph_norm == 'True' else False
if args.layer_norm is not None:
net_params['layer_norm'] = True if args.layer_norm == 'True' else False
if args.batch_norm is not None:
net_params['batch_norm'] = True if args.batch_norm == 'True' else False
if args.aggregators is not None:
net_params['aggregators'] = args.aggregators
if args.scalers is not None:
net_params['scalers'] = args.scalers
if args.towers is not None:
net_params['towers'] = args.towers
if args.divide_input_first is not None:
net_params['divide_input_first'] = args.divide_input_first
if args.divide_input_last is not None:
net_params['divide_input_last'] = args.divide_input_last
if args.edge_dim is not None:
net_params['edge_dim'] = args.edge_dim
if args.pretrans_layers is not None:
net_params['pretrans_layers'] = args.pretrans_layers
if args.posttrans_layers is not None:
net_params['posttrans_layers'] = args.posttrans_layers
if args.type_net is not None:
net_params['type_net'] = args.type_net
if args.pos_enc_dim is not None:
net_params['pos_enc_dim'] = args.pos_enc_dim
# SBM
net_params['in_dim'] = torch.unique(dataset.train[0][0].ndata['feat'],
dim=0).size(
0) # node_dim (feat is an integer)
net_params['n_classes'] = torch.unique(dataset.train[0][1], dim=0).size(0)
# calculate logarithmic average degree for scalers
D = torch.cat([
torch.sparse.sum(g.adjacency_matrix(transpose=True),
dim=-1).to_dense() for g in dataset.train.graph_lists
])
net_params['avg_d'] = dict(lin=torch.mean(D),
log=torch.mean(torch.log(D + 1)))
net_params['total_param'] = view_model_param(net_params)
train_val_pipeline(dataset, params, net_params)
def main():
"""
USER CONTROLS
"""
parser = argparse.ArgumentParser()
parser.add_argument('--config', help="Please give a config.json file with training/model/data/param details")
parser.add_argument('--gpu_id', help="Please give a value for gpu id")
parser.add_argument('--model', help="Please give a value for model name")
parser.add_argument('--dataset', help="Please give a value for dataset name")
parser.add_argument('--out_dir', help="Please give a value for out_dir")
parser.add_argument('--seed', help="Please give a value for seed")
parser.add_argument('--epochs', help="Please give a value for epochs")
parser.add_argument('--batch_size', help="Please give a value for batch_size")
parser.add_argument('--init_lr', help="Please give a value for init_lr")
parser.add_argument('--lr_reduce_factor', help="Please give a value for lr_reduce_factor")
parser.add_argument('--lr_schedule_patience', help="Please give a value for lr_schedule_patience")
parser.add_argument('--min_lr', help="Please give a value for min_lr")
parser.add_argument('--weight_decay', help="Please give a value for weight_decay")
parser.add_argument('--print_epoch_interval', help="Please give a value for print_epoch_interval")
parser.add_argument('--L', help="Please give a value for L")
parser.add_argument('--hidden_dim', help="Please give a value for hidden_dim")
parser.add_argument('--out_dim', help="Please give a value for out_dim")
parser.add_argument('--residual', help="Please give a value for residual")
parser.add_argument('--JK', default='last', help='Jumping Knowledge')
parser.add_argument('--edge_feat', help="Please give a value for edge_feat")
parser.add_argument('--readout', help="Please give a value for readout")
parser.add_argument('--kernel', help="Please give a value for kernel")
parser.add_argument('--n_heads', help="Please give a value for n_heads")
parser.add_argument('--gated', help="Please give a value for gated")
parser.add_argument('--in_feat_dropout', help="Please give a value for in_feat_dropout")
parser.add_argument('--dropout', help="Please give a value for dropout")
parser.add_argument('--graph_norm', help="Please give a value for graph_norm")
parser.add_argument('--layer_norm', help="Please give a value for layer_norm")
parser.add_argument('--batch_norm', help="Please give a value for batch_norm")
parser.add_argument('--sage_aggregator', help="Please give a value for sage_aggregator")
parser.add_argument('--data_mode', help="Please give a value for data_mode")
parser.add_argument('--num_pool', help="Please give a value for num_pool")
parser.add_argument('--gnn_per_block', help="Please give a value for gnn_per_block")
parser.add_argument('--embedding_dim', help="Please give a value for embedding_dim")
parser.add_argument('--pool_ratio', help="Please give a value for pool_ratio")
parser.add_argument('--linkpred', help="Please give a value for linkpred")
parser.add_argument('--cat', help="Please give a value for cat")
parser.add_argument('--self_loop', help="Please give a value for self_loop")
parser.add_argument('--max_time', help="Please give a value for max_time")
parser.add_argument('--pos_enc_dim', help="Please give a value for pos_enc_dim")
parser.add_argument('--pos_enc', help="Please give a value for pos_enc")
parser.add_argument('--type_net', default='simple', help='Type of net')
parser.add_argument('--lap_norm', default='none', help='Laplacian normalisation')
# hydra params
parser.add_argument('--hydra', action='store_true', default=False, help='Run in Hydra environment.')
parser.add_argument('--hydra_checkpoint_every', type=int, default=100, help='Save checkpoints to hydra every.')
parser.add_argument('--hydra_eta_every', type=int, default=100, help='Update ETA to hydra every.')
parser.add_argument('--hydra_progress_bar_every', type=float, default=1,
help='Update progress hydra every (seconds).')
# eig params
parser.add_argument('--aggregators', type=str, help='Aggregators to use.')
parser.add_argument('--scalers', type=str, help='Scalers to use.')
parser.add_argument('--NN_eig', action='store_true', default=False, help='NN eig aggr.')
parser.add_argument('--towers', type=int, default=5, help='Towers to use.')
parser.add_argument('--divide_input_first', type=bool, help='Whether to divide the input in first layer.')
parser.add_argument('--divide_input_last', type=bool, help='Whether to divide the input in last layers.')
parser.add_argument('--gru', type=bool, help='Whether to use gru.')
parser.add_argument('--edge_dim', type=int, help='Size of edge embeddings.')
parser.add_argument('--pretrans_layers', type=int, help='pretrans_layers.')
parser.add_argument('--posttrans_layers', type=int, help='posttrans_layers.')
parser.add_argument('--not_pre', action='store_true', default=False, help='Not applying pre-transformation')
args = parser.parse_args()
# hydra load
if args.hydra:
print('I am passing here 1')
if not hydra.is_available():
print('hydra: not available')
args.hydra = False
with open(args.config) as f:
config = json.load(f)
# device
if args.gpu_id is not None:
config['gpu']['id'] = int(args.gpu_id)
config['gpu']['use'] = True
device = gpu_setup(config['gpu']['use'], config['gpu']['id'], verbose=hydra.is_first_execution())
# model, dataset, out_dir
if args.model is not None:
MODEL_NAME = args.model
else:
MODEL_NAME = config['model']
if args.dataset is not None:
DATASET_NAME = args.dataset
else:
DATASET_NAME = config['dataset']
dataset = SBMsDataset(DATASET_NAME, norm=args.lap_norm, pos_enc_dim=int(args.pos_enc_dim), verbose=hydra.is_first_execution())
if args.out_dir is not None:
out_dir = args.out_dir
else:
out_dir = config['out_dir']
# parameters
params = config['params']
if args.seed is not None:
params['seed'] = int(args.seed)
if args.epochs is not None:
params['epochs'] = int(args.epochs)
if args.batch_size is not None:
params['batch_size'] = int(args.batch_size)
if args.init_lr is not None:
params['init_lr'] = float(args.init_lr)
if args.lr_reduce_factor is not None:
params['lr_reduce_factor'] = float(args.lr_reduce_factor)
if args.lr_schedule_patience is not None:
params['lr_schedule_patience'] = int(args.lr_schedule_patience)
if args.min_lr is not None:
params['min_lr'] = float(args.min_lr)
if args.weight_decay is not None:
params['weight_decay'] = float(args.weight_decay)
if args.print_epoch_interval is not None:
params['print_epoch_interval'] = int(args.print_epoch_interval)
if args.max_time is not None:
params['max_time'] = float(args.max_time)
#hydra parameters
params['hydra'] = args.hydra
params['hydra_checkpoint_every'] = args.hydra_checkpoint_every
params['hydra_eta_every'] = args.hydra_eta_every
params['hydra_progress_bar_every'] = args.hydra_progress_bar_every
# network parameters
net_params = config['net_params']
net_params['device'] = device
net_params['gpu_id'] = config['gpu']['id']
net_params['batch_size'] = params['batch_size']
if args.L is not None:
net_params['L'] = int(args.L)
if args.hidden_dim is not None:
net_params['hidden_dim'] = int(args.hidden_dim)
if args.out_dim is not None:
net_params['out_dim'] = int(args.out_dim)
if args.residual is not None:
net_params['residual'] = True if args.residual == 'True' else False
if args.JK is not None:
net_params['JK'] = args.JK
if args.edge_feat is not None:
net_params['edge_feat'] = True if args.edge_feat == 'True' else False
if args.readout is not None:
net_params['readout'] = args.readout
if args.kernel is not None:
net_params['kernel'] = int(args.kernel)
if args.n_heads is not None:
net_params['n_heads'] = int(args.n_heads)
if args.gated is not None:
net_params['gated'] = True if args.gated == 'True' else False
if args.in_feat_dropout is not None:
net_params['in_feat_dropout'] = float(args.in_feat_dropout)
if args.dropout is not None:
net_params['dropout'] = float(args.dropout)
if args.graph_norm is not None:
net_params['graph_norm'] = True if args.graph_norm == 'True' else False
if args.layer_norm is not None:
net_params['layer_norm'] = True if args.layer_norm == 'True' else False
if args.batch_norm is not None:
net_params['batch_norm'] = True if args.batch_norm == 'True' else False
if args.sage_aggregator is not None:
net_params['sage_aggregator'] = args.sage_aggregator
if args.data_mode is not None:
net_params['data_mode'] = args.data_mode
if args.num_pool is not None:
net_params['num_pool'] = int(args.num_pool)
if args.gnn_per_block is not None:
net_params['gnn_per_block'] = int(args.gnn_per_block)
if args.embedding_dim is not None:
net_params['embedding_dim'] = int(args.embedding_dim)
if args.pool_ratio is not None:
net_params['pool_ratio'] = float(args.pool_ratio)
if args.linkpred is not None:
net_params['linkpred'] = True if args.linkpred == 'True' else False
if args.cat is not None:
net_params['cat'] = True if args.cat == 'True' else False
if args.self_loop is not None:
net_params['self_loop'] = True if args.self_loop == 'True' else False
if args.pos_enc is not None:
net_params['pos_enc'] = True if args.pos_enc == 'True' else False
if args.pos_enc_dim is not None:
net_params['pos_enc_dim'] = int(args.pos_enc_dim)
if args.aggregators is not None:
net_params['aggregators'] = args.aggregators
if args.scalers is not None:
net_params['scalers'] = args.scalers
if args.towers is not None:
net_params['towers'] = args.towers
if args.divide_input_first is not None:
net_params['divide_input_first'] = args.divide_input_first
if args.divide_input_last is not None:
net_params['divide_input_last'] = args.divide_input_last
if args.NN_eig is not None:
net_params['NN_eig'] = args.NN_eig
if args.gru is not None:
net_params['gru'] = args.gru
if args.edge_dim is not None:
net_params['edge_dim'] = args.edge_dim
if args.pretrans_layers is not None:
net_params['pretrans_layers'] = args.pretrans_layers
if args.posttrans_layers is not None:
net_params['posttrans_layers'] = args.posttrans_layers
if args.not_pre is not None:
net_params['not_pre'] = args.not_pre
if args.type_net is not None:
net_params['type_net'] = args.type_net
# SBM
net_params['in_dim'] = torch.unique(dataset.train[0][0].ndata['feat'], dim=0).size(0) # node_dim (feat is an integer)
net_params['n_classes'] = torch.unique(dataset.train[0][1], dim=0).size(0)
D = torch.cat([torch.sparse.sum(g.adjacency_matrix(transpose=True), dim=-1).to_dense() for g in
dataset.train.graph_lists])
net_params['avg_d'] = dict(lin=torch.mean(D),
exp=torch.mean(torch.exp(torch.div(1, D)) - 1),
log=torch.mean(torch.log(D + 1)))
root_log_dir = out_dir + 'logs/' + MODEL_NAME + "_" + DATASET_NAME + "_GPU" + str(
config['gpu']['id']) + "_" + time.strftime('%Hh%Mm%Ss_on_%b_%d_%Y')
root_ckpt_dir = out_dir + 'checkpoints/' + MODEL_NAME + "_" + DATASET_NAME + "_GPU" + str(
config['gpu']['id']) + "_" + time.strftime('%Hh%Mm%Ss_on_%b_%d_%Y')
write_file_name = out_dir + 'results/result_' + MODEL_NAME + "_" + DATASET_NAME + "_GPU" + str(
config['gpu']['id']) + "_" + time.strftime('%Hh%Mm%Ss_on_%b_%d_%Y')
write_config_file = out_dir + 'configs/config_' + MODEL_NAME + "_" + DATASET_NAME + "_GPU" + str(
config['gpu']['id']) + "_" + time.strftime('%Hh%Mm%Ss_on_%b_%d_%Y')
dirs = root_log_dir, root_ckpt_dir, write_file_name, write_config_file
if not os.path.exists(out_dir + 'results'):
os.makedirs(out_dir + 'results')
if not os.path.exists(out_dir + 'configs'):
os.makedirs(out_dir + 'configs')
net_params['total_param'] = view_model_param(net_params, verbose=hydra.is_first_execution())
train_val_pipeline(MODEL_NAME, dataset, params, net_params, dirs)