training_time = toc - tic
tic = time.time()
testing_acc = model.predict(test_loader)
toc = time.time()
evaluating_time = toc - tic
records.append(('BaggingClassifier',
training_time,
evaluating_time,
testing_acc))
# GradientBoostingClassifier
model = GradientBoostingClassifier(estimator=LeNet5,
n_estimators=n_estimators,
output_dim=output_dim,
lr=lr,
weight_decay=weight_decay,
epochs=epochs)
tic = time.time()
model.fit(train_loader)
toc = time.time()
training_time = toc - tic
tic = time.time()
testing_acc = model.predict(test_loader)
toc = time.time()
evaluating_time = toc - tic
records.append(('GradientBoostingClassifier',
training_time,
model.fit(train_loader, epochs=epochs)
toc = time.time()
training_time = toc - tic
# Evaluating
tic = time.time()
testing_acc = model.evaluate(test_loader)
toc = time.time()
evaluating_time = toc - tic
records.append(
("BaggingClassifier", training_time, evaluating_time, testing_acc))
# GradientBoostingClassifier
model = GradientBoostingClassifier(estimator=LeNet5,
n_estimators=n_estimators,
cuda=True)
# Set the optimizer
model.set_optimizer("Adam", lr=lr, weight_decay=weight_decay)
# Training
tic = time.time()
model.fit(train_loader, epochs=epochs)
toc = time.time()
training_time = toc - tic
# Evaluating
tic = time.time()
testing_acc = model.evaluate(test_loader)
toc = time.time()
estimators = [est1, est2]
# Hyper-parameters
n_estimators = 4
output_dim = 20
lr = 1e-4
weight_decay = 5e-4
epochs = 10
resolution = 32
# Utils
batch_size = 128
data_dir = "bird_dataset/" # MODIFY THIS IF YOU WANT
records = []
torch.manual_seed(0)
model = GradientBoostingClassifier(
estimators=estimators,
cuda=False,
n_estimators=n_estimators,
output_dim=output_dim,
lr=lr,
weight_decay=weight_decay,
epochs=epochs,
)
loader = DataLoader(torchvision.datasets.FakeData(image_size=(3,32,32),transform=transforms.ToTensor()),shuffle=True,batch_size=batch_size)
model.fit(loader,loader)