def load_stl10_data(train_split):
# Load STL-10 data
print 'Loading STL-10 Training Data'
X_train = numpy.load('/data/stl10_matlab/train_splits/train_X_' +
str(train_split) + '.npy')
y_train = numpy.load('/data/stl10_matlab/train_splits/train_y_' +
str(train_split) + '.npy')
print 'Loading STL-10 Testing Data'
X_test = numpy.load('/data/stl10_matlab/test_X.npy')
y_test = numpy.load('/data/stl10_matlab/test_y.npy')
X_train = numpy.float32(X_train)
X_train /= 255.0
X_train *= 2.0
X_test = numpy.float32(X_test)
X_test /= 255.0
X_test *= 2.0
train_dataset = supervised_dataset.SupervisedDataset(X_train, y_train)
test_dataset = supervised_dataset.SupervisedDataset(X_test, y_test)
train_iterator = train_dataset.iterator(mode='sequential', batch_size=128)
test_iterator = test_dataset.iterator(mode='sequential', batch_size=128)
return train_iterator, test_iterator
def load_cifar10_data():
# Load CIFAR-10 data
print 'Loading CIFAR-10 Testing Data'
X_test = numpy.load('/data/cifar10/test_X.npy')
y_test = numpy.load('/data/cifar10/test_y.npy')
test_dataset = supervised_dataset.SupervisedDataset(X_test, y_test)
test_iterator = test_dataset.iterator(mode='sequential', batch_size=128)
return test_iterator
model = CNNModel('experiment', './', learning_rate=1e-2)
monitor = util.Monitor(model)
# Loading CIFAR-10 dataset
print('Loading Data')
data_path = '/data/cifar10/'
reduced_data_path = os.path.join(data_path, 'reduced', 'cifar10_100')
train_data = numpy.load(os.path.join(reduced_data_path, 'train_X_split_0.npy'))
train_labels = numpy.load(
os.path.join(reduced_data_path, 'train_y_split_0.npy'))
test_data = numpy.load('/data/cifar10/test_X.npy')
test_labels = numpy.load('/data/cifar10/test_y.npy')
train_dataset = supervised_dataset.SupervisedDataset(train_data, train_labels)
test_dataset = supervised_dataset.SupervisedDataset(test_data, test_labels)
train_iterator = train_dataset.iterator(mode='random_uniform',
batch_size=128,
num_batches=100000)
test_iterator = test_dataset.iterator(mode='random_uniform',
batch_size=128,
num_batches=100000)
normer = util.Normer2(filter_size=5, num_channels=3)
print('Training Model')
for x_batch, y_batch in train_iterator:
x_batch = x_batch.transpose(1, 2, 3, 0)
x_batch = normer.run(x_batch)
#y_batch = numpy.int64(numpy.argmax(y_batch, axis=1))
def _get_iterator(self):
dataset = supervised_dataset.SupervisedDataset(self.data_container.X,
self.data_container.y)
iterator = dataset.iterator(mode='sequential',
batch_size=self.batch_size)
return iterator
X_val /= 255.0
X_val *= 2.0
X_test = numpy.float32(X_test)
X_test /= 255.0
X_test *= 2.0
mean = numpy.average(numpy.concatenate((X_train, X_val, X_test), axis=0),
axis=(0, 2, 3))
print numpy.shape(numpy.concatenate((X_train, X_val, X_test), axis=0))
std = numpy.std(numpy.concatenate((X_train, X_val, X_test), axis=0),
axis=(0, 2, 3))
print mean
print std
train_dataset = supervised_dataset.SupervisedDataset(X_train, y_train)
val_dataset = supervised_dataset.SupervisedDataset(X_val, y_val)
train_iterator = train_dataset.iterator(mode='random_uniform',
batch_size=64,
num_batches=31000)
val_iterator = val_dataset.iterator(mode='random_uniform',
batch_size=64,
num_batches=31000)
# Create object to local contrast normalize a batch.
# Note: Every batch must be normalized before use.
normer = util.Normer3(filter_size=5, num_channels=1)
module_list = [normer]
preprocessor = util.Preprocessor(module_list)
print('Training Model')
train_data_container = supervised_data_loader.load('train', train_split)
test_data_container = supervised_data_loader.load('test', train_split)
X_train = train_data_container.X
X_train = numpy.float32(X_train)
X_train /= 255.0
X_train *= 2.0
y_train = train_data_container.y
X_test = test_data_container.X
X_test = numpy.float32(X_test)
X_test /= 255.0
X_test *= 2.0
y_test = test_data_container.y
train_dataset = supervised_dataset.SupervisedDataset(X_train, y_train)
test_dataset = supervised_dataset.SupervisedDataset(X_test, y_test)
train_iterator = train_dataset.iterator(mode='random_uniform',
batch_size=64,
num_batches=31000)
test_iterator = test_dataset.iterator(mode='random_uniform',
batch_size=64,
num_batches=31000)
# Create object to local contrast normalize a batch.
# Note: Every batch must be normalized before use.
normer = util.Normer3(filter_size=5, num_channels=1)
module_list = [normer]
preprocessor = util.Preprocessor(module_list)
print('Training Model')
