def outofsample_extensions(method='linear-regression'):
# Load the data and init seeds
train_data, train_labels, test_data, test_labels = load_mnist(dataset_path='data')
np.random.seed(1)
sklearn.utils.check_random_state(1)
n_train_samples = 5000
# Learn a new space using Isomap
isomap = Isomap(n_components=10, n_neighbors=20)
train_data_isomap = np.float32(isomap.fit_transform(train_data[:n_train_samples, :]))
if method == 'linear-regression':
# Use linear regression to provide baseline out-of-sample extensions
proj = LinearRegression()
proj.fit(np.float64(train_data[:n_train_samples, :]), np.float64(train_data_isomap))
acc = evaluate_svm(proj.predict(train_data[:n_train_samples, :]), train_labels[:n_train_samples],
proj.predict(test_data), test_labels)
elif method == 'c-ISOMAP-10d' or method == 'c-ISOMAP-20d':
# Use the SEF to provide out-of-sample extensions
if method == 'c-ISOMAP-10d':
proj = LinearSEF(train_data.shape[1], output_dimensionality=10)
proj.cuda()
else:
proj = LinearSEF(train_data.shape[1], output_dimensionality=20)
proj.cuda()
loss = proj.fit(data=train_data[:n_train_samples, :], target_data=train_data_isomap, target='copy',
epochs=50, batch_size=128, verbose=True, learning_rate=0.001, regularizer_weight=1)
acc = evaluate_svm(proj.transform(train_data[:n_train_samples, :]), train_labels[:n_train_samples],
proj.transform(test_data), test_labels)
print("Method: ", method, " Test accuracy: ", 100 * acc, " %")
def outofsample_extensions(method=None, dataset=None):
np.random.seed(1)
sklearn.utils.check_random_state(1)
dataset_path = 'data'
train_data, train_labels, test_data, test_labels = dataset_loader(dataset_path, dataset, seed=1)
# Learn a new space using Isomap
isomap = Isomap(n_components=10, n_neighbors=20)
train_data_isomap = np.float32(isomap.fit_transform(train_data))
if method == 'linear-regression':
from sklearn.preprocessing import StandardScaler
std = StandardScaler()
train_data = std.fit_transform(train_data)
test_data = std.transform(test_data)
# Use linear regression to provide baseline out-of-sample extensions
proj = LinearRegression()
proj.fit(np.float64(train_data), np.float64(train_data_isomap))
acc = evaluate_svm(proj.predict(train_data), train_labels,
proj.predict(test_data), test_labels)
elif method == 'c-ISOMAP-10d' or method == 'c-ISOMAP-20d':
# Use the SEF to provide out-of-sample extensions
if method == 'c-ISOMAP-10d':
proj = LinearSEF(train_data.shape[1], output_dimensionality=10)
proj.cuda()
else:
proj = LinearSEF(train_data.shape[1], output_dimensionality=20)
proj.cuda()
loss = proj.fit(data=train_data, target_data=train_data_isomap, target='copy',
epochs=50, batch_size=1024, verbose=False, learning_rate=0.001, regularizer_weight=1)
acc = evaluate_svm(proj.transform(train_data), train_labels,
proj.transform(test_data), test_labels)
print("Method: ", method, " Test accuracy: ", 100 * acc, " %")
def run(args):
if args.use_gpu:
try:
output = subprocess.check_output("free-gpu", shell=True)
output = int(output.decode('utf-8'))
gpu = output
print("claiming gpu {}".format(gpu))
torch.cuda.set_device(int(gpu))
a = torch.tensor([1]).cuda()
device = int(gpu)
except (IndexError, subprocess.CalledProcessError) as e:
device = None
else:
device = None
print(f"device is : {device}")
train_loader = DataLoader("../../data/raw/xkcd_colordata",
"../../data/raw",
"train",
device=device)
dev_generator = DataLoader("../../data/raw/xkcd_colordata",
"../../data/raw/",
"dev",
device=device)
model = LinearRegression(128, 3)
if device is not None:
model = model.cuda(device)
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(), lr=args.lr)
for i in range(args.n_epochs):
for batch in train_loader:
X, Y = prepare_batch(batch, device)
optimizer.zero_grad()
Y_pred = model.forward(X)
loss = criterion(Y_pred, Y)
loss.backward()
optimizer.step()
print(f"epoch: {i}, loss: {loss.data[0]}")
torch.save(model, "../../models/baseline/{args.lr}_linear_{i}")