def create_data_loader(config, drop_last=True, shuffle=True):
if config.data['type'] == 'synthetic':
dataset = SyntheticDataset(config)
else:
NotImplementedError
dataloader = DataLoader(dataset=dataset, batch_size=config.training['batch_size'], shuffle=shuffle,
drop_last=drop_last, pin_memory=True, num_workers=config.system['num_workers'])
return dataloader
import warnings; warnings.simplefilter('ignore')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
random.seed(0)
# parameters
batch_size = 100
N = 500
N_input = 20
N_output = 20
sigma = 0.01
gamma = 0.01
# Load synthetic dataset
X_train_input,X_train_target,X_test_input,X_test_target,train_bkp,test_bkp = create_synthetic_dataset(N,N_input,N_output,sigma)
dataset_train = SyntheticDataset(X_train_input,X_train_target, train_bkp)
dataset_test = SyntheticDataset(X_test_input,X_test_target, test_bkp)
trainloader = DataLoader(dataset_train, batch_size=batch_size,shuffle=True, num_workers=1)
testloader = DataLoader(dataset_test, batch_size=batch_size,shuffle=False, num_workers=1)
def train_model(net,loss_type, learning_rate, epochs=1000, gamma = 0.001,
print_every=50,eval_every=50, verbose=1, Lambda=1, alpha=0.5):
optimizer = torch.optim.Adam(net.parameters(),lr=learning_rate)
criterion = torch.nn.MSELoss()
huber_loss = torch.nn.SmoothL1Loss()
for epoch in range(epochs):
for i, data in enumerate(trainloader, 0):
inputs, target, _ = data