def cifar10_batches(self,
name,
downsample,
batch_size,
num,
total_num=12800):
assert name in ['train', 'test']
assert total_num % batch_size == 0 or batch_size == -1
X0, y0 = (cf10.load_training_data()
if name == 'train' else cf10.load_test_data())
X = X0[:total_num]
X_batch = X[num * batch_size:(num + 1) + batch_size]
X_batch = X_batch[:, ::downsample, ::downsample, :]
return X_batch
def cifar10_dataset_generator(dataset_name, batch_size, restrict_size=1000):
assert dataset_name in ['train', 'test']
assert batch_size > 0 or batch_size == -1 # -1 for entire dataset
X_all_unrestricted, y_all = (cf10.load_training_data() if dataset_name == 'train'
else cf10.load_test_data())
actual_restrict_size = restrict_size if dataset_name == 'train' else int(1e10)
X_all = X_all_unrestricted[:actual_restrict_size]
data_len = X_all.shape[0]
batch_size = batch_size if batch_size > 0 else data_len
X_all_padded = np.concatenate([X_all, X_all[:batch_size]], axis=0)
y_all_padded = np.concatenate([y_all, y_all[:batch_size]], axis=0)
for slice_i in range(int(math.ceil(data_len / batch_size))):
idx = slice_i * batch_size
X_batch = X_all_padded[idx:idx + batch_size]
y_batch = np.ravel(y_all_padded[idx:idx + batch_size])
yield X_batch.astype(np.uint8), y_batch.astype(np.uint8)
def cifar10_dataset(self, name, downsample, total_num):
assert name in ['train', 'test']
X, y = (cf10.load_training_data()
if name == 'train' else cf10.load_test_data())
data = X[:total_num]
return data[:, ::downsample, ::downsample, :]
