def get_data(datadir,
size=IMAGE_SIZE,
isTrain=True,
zmin=-1,
zmax=1,
batch=BATCH,
shuffle_read=False):
if isTrain:
augs = [
imgaug.ResizeShortestEdge(int(size * 1.143)),
imgaug.RandomCrop(size),
imgaug.Flip(horiz=True),
]
else:
augs = [
imgaug.ResizeShortestEdge(int(size * 1.143)),
imgaug.CenterCrop(size)
]
def get_images(dir):
files = glob.glob(os.path.join(dir, "*.jpg"))
if shuffle_read:
import random
random.shuffle(files)
else:
files = sorted(files)
image_df = ImageFromFile(files, channel=3, shuffle=isTrain)
image_df = AugmentImageComponent(image_df, augs)
random_df = RandomZData([size, size, 3], zmin, zmax)
return JoinData([random_df, image_df])
names = ['train'] if isTrain else ['test']
df = get_images(*[os.path.join(datadir, n) for n in names])
df = BatchData(df, batch)
return df
def get_data(image_ids, batch_size=1, is_train=False, shape=510):
ds = ImageAndMaskFromFile(image_ids, channel=3, shuffle=True)
if is_train:
number_of_prefetch = 8
augs_with_label = [
imgaug.RandomCrop(shape),
imgaug.Flip(horiz=True, prob=0.5),
imgaug.Flip(vert=True, prob=0.5)
]
augs_no_label = [
imgaug.RandomOrderAug(
[imgaug.Brightness(delta=20),
imgaug.Contrast((0.6, 1.4))])
]
# augmentors = [
# GoogleNetResize(),
# # It's OK to remove the following augs if your CPU is not fast enough.
# # Removing brightness/contrast/saturation does not have a significant effect on accuracy.
# # Removing lighting leads to a tiny drop in accuracy.
# imgaug.RandomOrderAug(
# [imgaug.BrightnessScale((0.6, 1.4), clip=False),
# imgaug.Contrast((0.6, 1.4), clip=False),
# imgaug.Saturation(0.4, rgb=False),
# # rgb-bgr conversion for the constants copied from fb.resnet.torch
# imgaug.Lighting(0.1,—
# eigval=np.asarray(
# [0.2175, 0.0188, 0.0045][::-1]) * 255.0,
# eigvec=np.array(
# [[-0.5675, 0.7192, 0.4009],
# [-0.5808, -0.0045, -0.8140],
# [-0.5836, -0.6948, 0.4203]],
# dtype='float32')[::-1, ::-1]
# )]),
# imgaug.Flip(horiz=True),
# ]
else:
number_of_prefetch = 1
augs_with_label = [imgaug.CenterCrop(shape)]
augs_no_label = []
ds = AugmentImageComponents(ds, augs_with_label, (0, 1))
ds = AugmentImageComponents(ds, augs_no_label, [0])
ds = BatchData(ds, batch_size)
ds = PrefetchData(ds, 30, 1) #number_of_prefetch)
return ds
def normal_augmentor(isTrain):
"""
Normal augmentor with random crop and flip only, for BGR images in range [0,255].
"""
if isTrain:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.RandomCrop((DEFAULT_IMAGE_SHAPE, DEFAULT_IMAGE_SHAPE)),
imgaug.Flip(horiz=True),
]
else:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((DEFAULT_IMAGE_SHAPE, DEFAULT_IMAGE_SHAPE)),
]
return augmentors
def get_data(phase):
is_train = phase == "train"
ds = dataset.Cifar10(phase)
pp_mean = ds.get_per_pixel_mean(("train", ))
if is_train:
augmentors = [
imgaug.CenterPaste((40, 40)),
imgaug.RandomCrop((32, 32)),
imgaug.Flip(horiz=True),
imgaug.MapImage(lambda x: x - pp_mean),
]
else:
augmentors = [imgaug.MapImage(lambda x: x - pp_mean)]
ds = AugmentImageComponent(ds, augmentors)
ds = BatchData(ds, BATCH_SIZE, remainder=not is_train)
return ds
def get_data(datadir, size=IMAGESIZE, isTrain=True):
if isTrain:
augs = [
imgaug.RandomCrop(size),
imgaug.Flip(horiz=True),
]
else:
augs = [imgaug.CenterCrop(size)]
def get_images(dir):
files = sorted(glob.glob(os.path.join(dir, "*.jpg")))
df = ImageFromFile(files, channel=3, shuffle=isTrain)
random_df = RandomZData([size, size, 3], -1, 1)
return JoinData([random_df, AugmentImageComponent(df, augs)])
names = ['train'] if isTrain else ['test']
df = get_images(*[os.path.join(datadir, n) for n in names])
df = BatchData(df, BATCH if isTrain else TEST_BATCH)
return df
def fbresnet_augmentor(is_training, option):
if is_training:
augmentors = [
imgaug.ToFloat32(),
imgaug.Resize((option.final_size + 32, option.final_size + 32)),
imgaug.RandomCrop((option.final_size, option.final_size))
]
flip = [imgaug.Flip(horiz=True), imgaug.ToUint8()]
augmentors.extend(flip)
else:
augmentors = [
imgaug.ToFloat32(),
imgaug.Resize((option.final_size + 32, option.final_size + 32)),
imgaug.CenterCrop((option.final_size, option.final_size)),
imgaug.ToUint8()
]
return augmentors
def get_ilsvrc_data_alexnet(is_train, image_size, batchsize, directory):
if is_train:
if not directory.startswith('/'):
ds = ILSVRCTTenthTrain(directory)
else:
ds = ILSVRC12(directory, 'train')
augs = [
imgaug.RandomApplyAug(imgaug.RandomResize((0.9, 1.2), (0.9, 1.2)),
0.7),
imgaug.RandomApplyAug(imgaug.RotationAndCropValid(15), 0.7),
imgaug.RandomApplyAug(
imgaug.RandomChooseAug([
imgaug.SaltPepperNoise(white_prob=0.01, black_prob=0.01),
imgaug.RandomOrderAug([
imgaug.BrightnessScale((0.8, 1.2), clip=False),
imgaug.Contrast((0.8, 1.2), clip=False),
# imgaug.Saturation(0.4, rgb=True),
]),
]),
0.7),
imgaug.Flip(horiz=True),
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.RandomCrop((224, 224)),
]
ds = AugmentImageComponent(ds, augs)
ds = PrefetchData(ds, 1000, multiprocessing.cpu_count())
ds = BatchData(ds, batchsize)
ds = PrefetchData(ds, 10, 4)
else:
if not directory.startswith('/'):
ds = ILSVRCTenthValid(directory)
else:
ds = ILSVRC12(directory, 'val')
ds = AugmentImageComponent(ds, [
imgaug.ResizeShortestEdge(224, cv2.INTER_CUBIC),
imgaug.CenterCrop((224, 224)),
])
ds = PrefetchData(ds, 100, multiprocessing.cpu_count())
ds = BatchData(ds, batchsize)
return ds
def _augment(self, img, _):
h, w = img.shape[:2]
area = h * w
for _ in range(10):
targetArea = self.rng.uniform(self.crop_area_fraction, 1.0) * area
aspectR = self.rng.uniform(self.aspect_ratio_low,
self.aspect_ratio_high)
ww = int(np.sqrt(targetArea * aspectR) + 0.5)
hh = int(np.sqrt(targetArea / aspectR) + 0.5)
if self.rng.uniform() < 0.5:
ww, hh = hh, ww
if hh <= h and ww <= w:
x1 = 0 if w == ww else self.rng.randint(0, w - ww)
y1 = 0 if h == hh else self.rng.randint(0, h - hh)
out = img[y1:y1 + hh, x1:x1 + ww]
out = cv2.resize(out, (self.target_shape, self.target_shape),
interpolation=cv2.INTER_CUBIC)
return out
out = imgaug.ResizeShortestEdge(self.target_shape,
interp=cv2.INTER_CUBIC).augment(img)
out = imgaug.RandomCrop(self.target_shape).augment(
out) # TODO : Random Crop?
return out
def fbresnet_augmentor(isTrain, crop_method, color_augmentation):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
execution_lst = []
if isTrain:
augmentors = [
# 1. crop_method
# a) GoogleNetResize
GoogleNetResize(),
# b) ShortestEdgeResize
imgaug.ResizeShortestEdge(256),
# c) GlobalWarp
imgaug.Resize(226), # NOTE: for CAM generation
imgaug.RandomCrop((224, 224)),
# d) CAMCrop
# (when CAMCrop is set, the output from the original DataFlow has already been cropped)
# 2. color_augmentation
imgaug.RandomOrderAug([
imgaug.BrightnessScale((0.6, 1.4), clip=False),
imgaug.Contrast((0.6, 1.4), clip=False),
imgaug.Saturation(0.4, rgb=False),
# rgb-bgr conversion for the constants copied from fb.resnet.torch
imgaug.Lighting(
0.1,
eigval=np.asarray([0.2175, 0.0188, 0.0045][::-1]) * 255.0,
eigvec=np.array([[-0.5675, 0.7192, 0.4009],
[-0.5808, -0.0045, -0.8140],
[-0.5836, -0.6948, 0.4203]],
dtype='float32')[::-1, ::-1])
]),
imgaug.Flip(horiz=True),
]
#
if crop_method == 'GoogleNetResize':
print(
'--> perform GoogleNetResize cropping method during the training pipeline'
)
execution_lst.extend([0])
elif crop_method == 'ShortestEdgeResize':
print(
'--> perform ShortestEdgeResize cropping method during the training pipeline'
)
execution_lst.extend([1, 3])
elif crop_method == 'GlobalWarp':
print(
'--> perform GlobalWarp cropping method during the training pipeline'
)
execution_lst.extend([2, 3])
elif crop_method == 'CAMCrop':
# enable CAMCrop @ 20171124
print(
'*** Perform CAMCrop to better the training dynamics and the results ***'
)
if color_augmentation:
print(
'--> perform color augmentation during the training pipeline')
execution_lst.extend([4])
else:
print(
'--> discard the color jittering process during the training pipeline'
)
# perform mirror reflection augmentation anyway
execution_lst.extend([5])
else:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((224, 224)),
imgaug.RandomCrop((224, 224)),
]
if crop_method == 'RandomCrop':
execution_lst.extend([0, 2])
elif crop_method == 'CenterCrop':
execution_lst.extend([0, 1])
return [
item_ for id_, item_ in enumerate(augmentors) if id_ in execution_lst
]