def get_train_augmentors(self, input_shape, output_shape, view=False):
shape_augs = [
imgaug.Affine(
shear=5, # in degree
scale=(0.8, 1.2),
rotate_max_deg=179,
translate_frac=(0.01, 0.01),
interp=cv2.INTER_NEAREST,
border=cv2.BORDER_CONSTANT),
imgaug.Flip(vert=True),
imgaug.Flip(horiz=True),
imgaug.CenterCrop(input_shape),
]
input_augs = self.input_augs
label_augs = []
if self.model_type == 'unet' or self.model_type == 'micronet':
label_augs =[GenInstanceUnetMap(crop_shape=output_shape)]
if self.model_type == 'dcan':
label_augs =[GenInstanceContourMap(crop_shape=output_shape)]
if self.model_type == 'dist':
label_augs = [GenInstanceDistance(crop_shape=output_shape, inst_norm=False)]
if self.model_type == 'np_hv' or self.model_type == 'np_hv_opt':
label_augs = [GenInstanceHV(crop_shape=output_shape)]
if self.model_type == 'np_dist':
label_augs = [GenInstanceDistance(crop_shape=output_shape, inst_norm=True)]
if not self.type_classification:
label_augs.append(BinarizeLabel())
if not view:
label_augs.append(imgaug.CenterCrop(output_shape))
return shape_augs, input_augs, label_augs
def train_dataloader(self):
# REQUIRED
ds_train = PretrainedSNEMI(folder=self.hparams.data_path,
train_or_valid='train',
size=40000,
# resize=int(self.hparams.shape),
debug=DEBUG
)
ag_train = [
imgaug.RotationAndCropValid(max_deg=180, interp=cv2.INTER_NEAREST),
imgaug.Flip(horiz=True, vert=False),
imgaug.Flip(horiz=False, vert=True),
imgaug.Transpose(),
imgaug.GoogleNetRandomCropAndResize(crop_area_fraction=(0.2, 0.5),
aspect_ratio_range=(0.5, 2.0),
interp=cv2.INTER_NEAREST,
target_shape=self.hparams.shape),
imgaug.ToFloat32(),
]
ds_train.reset_state()
# ds_train = AugmentImageComponent(ds_train, ag_train, 0)
ds_train = AugmentImageComponent(ds_train, [imgaug.Albumentations(AB.RandomBrightnessContrast())], (0))
ds_train = AugmentImageComponents(ds_train, ag_train, (0, 1))
ds_train = MapData(ds_train, lambda dp: [dp[0], 255.0*(dp[1]>0)*(1-skimage.segmentation.find_boundaries(dp[1], mode='inner'))])
ds_train = BatchData(ds_train, self.hparams.batch)
ds_train = PrintData(ds_train)
ds_train = MapData(ds_train, lambda dp: [torch.tensor(dp[0][:,np.newaxis,:,:]), torch.tensor(dp[1][:,np.newaxis,:,:]).float()])
ds_train = MultiProcessRunner(ds_train, num_proc=32, num_prefetch=8)
return ds_train
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 get_train_augmentors(self, input_shape, output_shape, view=False):
print(input_shape, output_shape)
shape_augs = [
imgaug.Affine(
shear=5, # in degree
scale=(0.8, 1.2),
rotate_max_deg=179,
translate_frac=(0.01, 0.01),
interp=cv2.INTER_NEAREST,
border=cv2.BORDER_CONSTANT),
imgaug.Flip(vert=True),
imgaug.Flip(horiz=True),
imgaug.CenterCrop(input_shape),
]
input_augs = [
imgaug.RandomApplyAug(
imgaug.RandomChooseAug([
GaussianBlur(),
MedianBlur(),
imgaug.GaussianNoise(),
]), 0.5),
# standard color augmentation
imgaug.RandomOrderAug([
imgaug.Hue((-8, 8), rgb=True),
imgaug.Saturation(0.2, rgb=True),
imgaug.Brightness(26, clip=True),
imgaug.Contrast((0.75, 1.25), clip=True),
]),
imgaug.ToUint8(),
]
label_augs = []
if self.model_type == 'unet' or self.model_type == 'micronet':
label_augs = [GenInstanceUnetMap(crop_shape=output_shape)]
if self.model_type == 'dcan':
label_augs = [GenInstanceContourMap(crop_shape=output_shape)]
if self.model_type == 'dist':
label_augs = [
GenInstanceDistance(crop_shape=output_shape, inst_norm=False)
]
if self.model_type == 'np_hv':
label_augs = [GenInstanceHV(crop_shape=output_shape)]
if self.model_type == 'np_dist':
label_augs = [
GenInstanceDistance(crop_shape=output_shape, inst_norm=True)
]
if not self.type_classification:
label_augs.append(BinarizeLabel())
if not view:
label_augs.append(imgaug.CenterCrop(output_shape))
return shape_augs, input_augs, label_augs
def get_augmentations(is_train):
if is_train:
augmentors = [
GoogleNetResize(crop_area_fraction=0.76,
target_shape=224), # TODO : 76% or 49%?
imgaug.RandomOrderAug([
imgaug.BrightnessScale((0.6, 1.4), clip=True),
imgaug.Contrast((0.6, 1.4), clip=True),
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:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((224, 224)),
]
return augmentors
def fbresnet_augmentor(isTrain, target_shape=224):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
if isTrain:
augmentors = [
GoogleNetResize(crop_area_fraction=0.32,
target_shape=target_shape),
# GoogleNetResize(target_shape=target_shape),
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:
augmentors = [
imgaug.ResizeShortestEdge(int(256 / 224 * target_shape),
cv2.INTER_CUBIC),
imgaug.CenterCrop((target_shape, target_shape)),
]
return augmentors
def get_tp_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
interpolation = cv2.INTER_CUBIC
# linear seems to have more stable performance.
# but we keep cubic for compatibility with old models
if isTrain:
augmentors = [
imgaug.GoogleNetRandomCropAndResize(interp=interpolation),
# 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), rgb=False, 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:
augmentors = [
imgaug.ResizeShortestEdge(256, interp=interpolation),
imgaug.CenterCrop((224, 224)),
]
return augmentors
def fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
if isTrain:
augmentors = [
GoogleNetResize(),
imgaug.RandomOrderAug( # Remove these augs if your CPU is not fast enough
[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:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((224, 224)),
]
return augmentors
def fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
if isTrain:
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:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((DEFAULT_IMAGE_SHAPE, DEFAULT_IMAGE_SHAPE)),
]
return augmentors
def fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
if isTrain:
"""
Sec 5.1:
We use scale and aspect ratio data augmentation [35] as
in [12]. The network input image is a 224×224 pixel random
crop from an augmented image or its horizontal flip.
"""
augmentors = [
GoogleNetResize(),
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:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((224, 224)),
]
return augmentors
def fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255]. # 残差网络增强图像
"""
if isTrain: # 如果训练数据的话
augmentors = [
GoogleNetResize(), # 定义好了crop_area_fraction等参数
imgaug.
RandomOrderAug( # GPU不行的话就把这部分删除Remove these augs if your CPU is not fast enough #imgaug是一个图像增强库
[
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: # 如果不是训练数据的话
augmentors = [
imgaug.ResizeShortestEdge(
256, cv2.INTER_CUBIC), # 在保持纵横比的同时，将最短边的大小调整为某个数字。
imgaug.CenterCrop((224, 224)), # 在中间裁剪图像
]
return augmentors
def fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
if isTrain:
augmentors = [
GoogleNetResize(),
imgaug.RandomOrderAug([
JohnAug(),
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:
round2pow2 = lambda x: 2**(x - 1).bit_length()
augmentors = [
imgaug.ResizeShortestEdge(round2pow2(IMAGE_SIZE), cv2.INTER_CUBIC),
imgaug.CenterCrop((IMAGE_SIZE, IMAGE_SIZE)),
]
return augmentors
def fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images.
"""
if isTrain:
augmentors = [
GoogleNetResize(),
imgaug.RandomOrderAug([
imgaug.Brightness(30, clip=False),
imgaug.Contrast((0.8, 1.2), clip=False),
imgaug.Saturation(0.4, rgb=False),
# rgb-bgr conversion
imgaug.Lighting(0.1,
eigval=[0.2175, 0.0188, 0.0045][::-1],
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.Clip(),
imgaug.Flip(horiz=True),
]
else:
augmentors = [
imgaug.ResizeShortestEdge(256, cv2.INTER_CUBIC),
imgaug.CenterCrop((224, 224)),
]
return augmentors
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_train_augmentors(self, view=False):
shape_augs = [
imgaug.Affine(
shear=5, # in degree
scale=(0.8, 1.2),
rotate_max_deg=179,
translate_frac=(0.01, 0.01),
interp=cv2.INTER_NEAREST,
border=cv2.BORDER_CONSTANT),
imgaug.Flip(vert=True),
imgaug.Flip(horiz=True),
imgaug.CenterCrop(self.train_input_shape),
]
input_augs = [
imgaug.RandomApplyAug(
imgaug.RandomChooseAug([
GaussianBlur(),
MedianBlur(),
imgaug.GaussianNoise(),
]), 0.5),
# standard color augmentation
imgaug.RandomOrderAug([
imgaug.Hue((-8, 8), rgb=True),
imgaug.Saturation(0.2, rgb=True),
imgaug.Brightness(26, clip=True),
imgaug.Contrast((0.75, 1.25), clip=True),
]),
imgaug.ToUint8(),
]
# default to 'xy'
if self.model_mode != 'np+dst':
label_augs = [GenInstanceXY(self.train_mask_shape)]
else:
label_augs = [GenInstanceDistance(self.train_mask_shape)]
label_augs.append(BinarizeLabel())
if not view:
label_augs.append(imgaug.CenterCrop(self.train_mask_shape))
return shape_augs, input_augs, label_augs
def small_augmentor():
augmentors = [
GoogleNetResize(),
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),
]
return augmentors
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 fbresnet_augmentor(isTrain):
"""
Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
"""
interpolation = cv2.INTER_LINEAR
if isTrain:
"""
Sec 5.1:
We use scale and aspect ratio data augmentation [35] as
in [12]. The network input image is a 224×224 pixel random
crop from an augmented image or its horizontal flip.
"""
augmentors = [
imgaug.GoogleNetRandomCropAndResize(interp=interpolation),
# 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), rgb=False, 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:
augmentors = [
imgaug.ResizeShortestEdge(256, interp=interpolation),
imgaug.CenterCrop((224, 224)),
]
return augmentors
def get_train_augmentors(self, input_shape, output_shape, view=False):
print(input_shape, output_shape)
if self.model_mode == "class_rotmnist":
shape_augs = [
imgaug.Affine(rotate_max_deg=359,
interp=cv2.INTER_NEAREST,
border=cv2.BORDER_CONSTANT),
]
input_augs = []
else:
shape_augs = [
imgaug.Affine(
rotate_max_deg=359,
translate_frac=(0.01, 0.01),
interp=cv2.INTER_NEAREST,
border=cv2.BORDER_REFLECT,
),
imgaug.Flip(vert=True),
imgaug.Flip(horiz=True),
imgaug.CenterCrop(input_shape),
]
input_augs = [
imgaug.RandomApplyAug(
imgaug.RandomChooseAug([
GaussianBlur(),
MedianBlur(),
imgaug.GaussianNoise(),
]),
0.5,
),
# Standard colour augmentation
imgaug.RandomOrderAug([
imgaug.Hue((-8, 8), rgb=True),
imgaug.Saturation(0.2, rgb=True),
imgaug.Brightness(26, clip=True),
imgaug.Contrast((0.75, 1.25), clip=True),
]),
imgaug.ToUint8(),
]
if self.model_mode == "seg_gland":
label_augs = []
label_augs = [GenInstanceContourMap(mode=self.model_mode)]
label_augs.append(BinarizeLabel())
if not view:
label_augs.append(imgaug.CenterCrop(output_shape))
else:
label_augs.append(imgaug.CenterCrop(input_shape))
return shape_augs, input_augs, label_augs
elif self.model_mode == "seg_nuc":
label_augs = []
label_augs = [GenInstanceMarkerMap()]
label_augs.append(BinarizeLabel())
if not view:
label_augs.append(imgaug.CenterCrop(output_shape))
else:
label_augs.append(imgaug.CenterCrop(input_shape))
return shape_augs, input_augs, label_augs
else:
return shape_augs, input_augs
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
]
