def get_folder_data(train_path, val_path, data_shape, batch_size, num_workers=os.cpu_count()):
train_dataset = ImageFolderDataset(train_path)
val_dataset = ImageFolderDataset(val_path)
train_transformer = gluon.data.vision.transforms.Compose([
transforms.RandomFlipLeftRight(),
transforms.RandomResizedCrop(data_shape, scale=(0.5, 1.0)),
transforms.RandomBrightness(0.5),
transforms.RandomHue(0.1),
transforms.Resize(data_shape),
transforms.ToTensor()
])
val_transformer = gluon.data.vision.transforms.Compose([
transforms.Resize(data_shape),
transforms.ToTensor()
])
train_dataloader = data.DataLoader(train_dataset.transform_first(train_transformer),
batch_size=batch_size, shuffle=True, last_batch='rollover',
num_workers=num_workers)
val_dataloader = data.DataLoader(val_dataset.transform_first(val_transformer),
batch_size=batch_size, shuffle=True, last_batch='rollover',
num_workers=num_workers)
return train_dataloader, val_dataloader
def test_transformer():
from mxnet.gluon.data.vision import transforms
transform = transforms.Compose([
transforms.Resize(300),
transforms.CenterCrop(256),
transforms.RandomResizedCrop(224),
transforms.RandomFlipLeftRight(),
transforms.RandomColorJitter(0.1, 0.1, 0.1, 0.1),
transforms.RandomBrightness(0.1),
transforms.RandomContrast(0.1),
transforms.RandomSaturation(0.1),
transforms.RandomHue(0.1),
transforms.RandomLighting(0.1),
transforms.ToTensor(),
transforms.Normalize([0, 0, 0], [1, 1, 1])])
transform(mx.nd.ones((245, 480, 3), dtype='uint8')).wait_to_read()
max_random_area = 1
min_random_area = 0.08
jitter_param = 0.4
lighting_param = 0.1
transform_train = transforms.Compose([
# transforms.RandomResizedCrop(resize,
# scale=(min_random_area, max_random_area),
# ratio=(min_aspect_ratio, max_aspect_ratio)),
# Randomly flip the image horizontally
transforms.RandomFlipLeftRight(),
transforms.RandomBrightness(brightness=jitter_param),
transforms.RandomSaturation(saturation=jitter_param),
transforms.RandomHue(hue=jitter_param),
transforms.RandomLighting(lighting_param),
# Randomly crop an area and resize it to be 32x32, then pad it to be 40x40
gcv_transforms.RandomCrop(32, pad=4),
# Transpose the image from height*width*num_channels to num_channels*height*width
# and map values from [0, 255] to [0,1]
transforms.ToTensor(),
# Normalize the image with mean and standard deviation calculated across all images
transforms.Normalize(mean_rgb, std_rgb),
])
transform_test = transforms.Compose([
img = image.imread('G:/gluon/mxnet/img/cat1.jpg')
gb.plt.imshow(img.asnumpy())
def apply(img, aug, num_rows=2, num_cols=4, scale=1.5):
Y = [aug(img) for _ in range(num_cols * num_rows)]
gb.show_images(Y, num_rows, num_cols, scale)
apply(img, transforms.RandomFlipLeftRight())
shape_aug = transforms.RandomResizedCrop((200, 200),
scale=(.1, 1),
ratio=(.5, 2))
apply(img, shape_aug)
apply(img, transforms.RandomLighting(.5))
apply(img, transforms.RandomHue(.5))
train_augs = transforms.Compose([
transforms.RandomFlipLeftRight(),
transforms.ToTensor(),
])
test_augs = transforms.Compose([
transforms.ToTensor(),
])
def load_cifar10(is_train, augs, batch_size):
return gluon.data.DataLoader(
gluon.data.vision.CIFAR10(train=is_train).transform_first(augs),
batch_size=batch_size,
shuffle=is_train,
