def load_dataset(subset: Subset) -> batches.BatchGenerator:
dataset = PetsDataset('../data/cifar-10-batches-py', subset)
op = ops.chain([
ops.hwc2chw(),
ops.add(-127.5),
ops.mul(1 / 127.5),
ops.type_cast(np.float32)
])
return batches.BatchGenerator(dataset, 128, True, op)
def load_dataset(subset: Subset, augment=False) -> batches.BatchGenerator:
dataset = PetsDataset('../data/cifar-10-batches-py', subset)
ops_list = []
if augment:
ops_list += [ops.hflip(), ops.rcrop(32, 12, 'constant')]
ops_list += [
ops.mul(1 / 255),
ops.type_cast(np.float32),
# Imagenet:
# ops.normalize( mean=np.array([0.485, 0.456, 0.406]),
# std=np.array([0.229, 0.224, 0.225])),
# Cifar-10:
ops.normalize(mean=np.array([0.41477802, 0.45935813, 0.49693552]),
std=np.array([0.25241926, 0.24699265, 0.25279155])),
ops.hwc2chw()
]
op = ops.chain(ops_list)
return batches.BatchGenerator(dataset, 128, True, op)
import numpy as np
from dlvc.dataset import Subset
from dlvc.datasets.pets import PetsDataset
from dlvc import ops, batches
dataset = PetsDataset('../data/cifar-10-batches-py', Subset.TRAINING)
op = ops.chain([ops.mul(1 / 255), ops.type_cast(np.float32)])
batch_generator = batches.BatchGenerator(dataset, 7959, True, op)
training_images = []
for batch in batch_generator:
training_images.append(batch.data)
training_images = np.array(training_images, dtype=np.float32)
training_images = training_images.reshape(training_images.shape[1:])
train_mean = np.mean(training_images, axis=(0, 1, 2))
train_std = np.std(training_images, axis=(0, 1, 2))
print(train_mean, train_std)
def load_dataset(subset: Subset) -> batches.BatchGenerator:
dataset = PetsDataset('../data/cifar-10-batches-py', subset)
op = ops.chain([ops.vectorize(), ops.type_cast(np.float32)])
return batches.BatchGenerator(dataset, len(dataset), True, op)
test_sample = dataset[1]
print(f'Index of test sample: {test_sample.idx}')
print(f'Label of test sample: {test_sample.label}')
#cv2.imshow('Sample Image', test_sample.data)
#cv2.waitKey(0)
#cv2.destroyAllWindows()
op = ops.chain([
ops.vectorize(),
ops.type_cast(np.float32)
])
#The number of training batches is 1 if the batch size is set to the number of samples in the dataset
generator = batches.BatchGenerator(dataset, len(dataset), True, op)
print(len(generator))
#The number of training batches is 16 if the batch size is set to 500
generator = batches.BatchGenerator(dataset, 500, True, op)
print(len(generator))
#The data and label shapes are (500, 3072) and (500,), respectively, unless for the last batch
#The data type is always np.float32 and the label type is integral (one of the np.int and np.uint variants)
#generator = batches.BatchGenerator(dataset, 20, False, op)
for i in iter(generator):
pass
# print(i.idx.shape)
# print(i.data)
# print(i.data.dtype)
# print(i.label.shape)