def data_import():
X_train, y_train = mnist_reader.load_mnist('../../data/mnist', kind='train')
X_test, y_test = mnist_reader.load_mnist('../../data/mnist', kind='t10k')
X_valid = X_test[0:5000]
y_valid = y_test[0:5000]
X_test = X_test[5000:10000]
y_test = y_test[5000:10000]
print(y_test.shape)
# convert the targets to one hot
y_valid = convertTarget(y_valid)
y_test = convertTarget(y_test)
y_train = convertTarget(y_train)
return X_train, y_train, X_valid, y_valid, X_test, y_test
def _read_data_test(data_path):
"""Reads CIFAR-10 format data. Always returns NHWC format.
Returns:
images: np tensor of size [N, H, W, C]
labels: np tensor of size [N]
"""
images, labels = [], []
X_test, y_test = mnist_reader.load_mnist(data_path, kind='t10k')
#X_test, y_test = mnist_reader.load_mnist('data/fashion', kind='t10k')
#data = pickle.load(finp,encoding='bytes')
print(X_test)
batch_images = X_test.astype(np.float32) / 255.0
batch_labels = np.array(y_test, dtype=np.int32)
images.append(batch_images)
labels.append(batch_labels)
images = np.concatenate(images, axis=0)
labels = np.concatenate(labels, axis=0)
images = np.reshape(images, [-1, 1, 28, 28])
images = np.transpose(images, [0, 2, 3, 1])
return images, labels