# Optional argument
parser.add_argument(
'--root',
nargs=1,
help='Specify the data directory.',
default=['/home/adutta/Workspace/Datasets/STDGraphs/Letter'])
parser.add_argument('--subset',
nargs=1,
help='Specify the sub dataset.',
default=['LOW'])
args = parser.parse_args()
root = args.root[0]
subset = args.subset[0]
train_classes, train_ids = read_cxl(os.path.join(root, subset,
'train.cxl'))
test_classes, test_ids = read_cxl(os.path.join(root, subset, 'test.cxl'))
valid_classes, valid_ids = read_cxl(
os.path.join(root, subset, 'validation.cxl'))
num_classes = len(list(set(train_classes + valid_classes + test_classes)))
data_train = LETTER(root, subset, train_ids, train_classes, num_classes)
data_valid = LETTER(root, subset, valid_ids, valid_classes, num_classes)
data_test = LETTER(root, subset, test_ids, test_classes, num_classes)
print(len(data_train))
print(len(data_valid))
print(len(data_test))
for i in range(len(train_ids)):
def main():
global args, best_acc1
args = parser.parse_args()
# Check if CUDA is enabled
args.cuda = not args.no_cuda and torch.cuda.is_available()
# Load data
root = args.datasetPath
subset = args.subSet
print('Prepare files')
train_classes, train_ids = read_cxl(os.path.join(root, subset,
'train.cxl'))
test_classes, test_ids = read_cxl(os.path.join(root, subset, 'test.cxl'))
valid_classes, valid_ids = read_cxl(
os.path.join(root, subset, 'validation.cxl'))
class_list = list(set(train_classes + test_classes))
num_classes = len(class_list)
data_train = datasets.LETTER(root, subset, train_ids, train_classes,
class_list)
data_valid = datasets.LETTER(root, subset, valid_ids, valid_classes,
class_list)
data_test = datasets.LETTER(root, subset, test_ids, test_classes,
class_list)
# Define model and optimizer
print('Define model')
# Select one graph
g_tuple, l = data_train[0]
g, h_t, e = g_tuple
#TODO: Need attention
print('\tStatistics')
stat_dict = {}
# stat_dict = datasets.utils.get_graph_stats(data_train, ['edge_labels'])
stat_dict['edge_labels'] = [1]
# Data Loader
train_loader = torch.utils.data.DataLoader(
data_train,
batch_size=args.batch_size,
shuffle=True,
collate_fn=datasets.utils.collate_g,
num_workers=args.prefetch,
pin_memory=True)
valid_loader = torch.utils.data.DataLoader(
data_valid,
batch_size=args.batch_size,
collate_fn=datasets.utils.collate_g,
num_workers=args.prefetch,
pin_memory=True)
test_loader = torch.utils.data.DataLoader(
data_test,
batch_size=args.batch_size,
collate_fn=datasets.utils.collate_g,
num_workers=args.prefetch,
pin_memory=True)
print('\tCreate model')
model = MpnnIntNet([len(h_t[0]), len(list(e.values())[0])], [5, 15, 15],
[10, 20, 20],
num_classes,
type='classification')
print('Optimizer')
optimizer = optim.Adam(model.parameters(), lr=args.lr)
criterion = nn.NLLLoss()
evaluation = utils.accuracy
print('Logger')
logger = Logger(args.logPath)
lr_step = (args.lr - args.lr * args.lr_decay) / (
args.epochs * args.schedule[1] - args.epochs * args.schedule[0])
# get the best checkpoint if available without training
if args.resume:
checkpoint_dir = args.resume
best_model_file = os.path.join(checkpoint_dir, 'model_best.pth')
if not os.path.isdir(best_model_file):
os.makedirs(checkpoint_dir)
if os.path.isfile(best_model_file):
print("=> loading best model '{}'".format(best_model_file))
checkpoint = torch.load(best_model_file)
args.start_epoch = checkpoint['epoch']
best_acc1 = checkpoint['best_acc1']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
print("=> loaded best model '{}' (epoch {}; accuracy {})".format(
best_model_file, checkpoint['epoch'], best_acc1))
else:
print("=> no best model found at '{}'".format(best_model_file))
print('Check cuda')
if args.cuda:
print('\t* Cuda')
model = model.cuda()
criterion = criterion.cuda()
# Epoch for loop
for epoch in range(0, args.epochs):
if epoch > args.epochs * args.schedule[
0] and epoch < args.epochs * args.schedule[1]:
args.lr -= lr_step
for param_group in optimizer.param_groups:
param_group['lr'] = args.lr
# train for one epoch
train(train_loader, model, criterion, optimizer, epoch, evaluation,
logger)
# evaluate on test set
acc1 = validate(valid_loader, model, criterion, evaluation, logger)
is_best = acc1 > best_acc1
best_acc1 = max(acc1, best_acc1)
utils.save_checkpoint(
{
'epoch': epoch + 1,
'state_dict': model.state_dict(),
'best_acc1': best_acc1,
'optimizer': optimizer.state_dict(),
},
is_best=is_best,
directory=args.resume)
# Logger step
logger.log_value('learning_rate', args.lr).step()
# get the best checkpoint and test it with test set
if args.resume:
checkpoint_dir = args.resume
best_model_file = os.path.join(checkpoint_dir, 'model_best.pth')
if not os.path.isdir(best_model_file):
os.makedirs(checkpoint_dir)
if os.path.isfile(best_model_file):
print("=> loading best model '{}'".format(best_model_file))
checkpoint = torch.load(best_model_file)
args.start_epoch = checkpoint['epoch']
best_acc1 = checkpoint['best_acc1']
model.load_state_dict(checkpoint['state_dict'])
optimizer.load_state_dict(checkpoint['optimizer'])
print("=> loaded best model '{}' (epoch {}; accuracy {})".format(
best_model_file, checkpoint['epoch'], best_acc1))
else:
print("=> no best model found at '{}'".format(best_model_file))
# For testing
validate(test_loader, model, criterion, evaluation)
if __name__ == '__main__':
# Parse optios for downloading
parser = argparse.ArgumentParser(description='GREC Object.')
# Optional argument
parser.add_argument(
'--root',
nargs=1,
help='Specify the data directory.',
default=['/home/adutta/Workspace/Datasets/Graphs/GREC'])
args = parser.parse_args()
root = args.root[0]
train_classes, train_ids = read_cxl(os.path.join(root, 'data/train.cxl'))
test_classes, test_ids = read_cxl(os.path.join(root, 'data/test.cxl'))
valid_classes, valid_ids = read_cxl(os.path.join(root, 'data/valid.cxl'))
num_classes = len(list(set(train_classes + valid_classes + test_classes)))
data_train = GREC(root, train_ids, train_classes, num_classes)
data_valid = GREC(root, valid_ids, valid_classes, num_classes)
data_test = GREC(root, test_ids, test_classes, num_classes)
print(len(data_train))
print(len(data_valid))
print(len(data_test))
for i in range(len(train_ids)):
print(data_train[i])