Python imgaug.ResizeShortestEdge方法代码示例

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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.CenterCrop(self.target_shape).augment(out)
        return out 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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((224, 224)),
        ]
    return augmentors 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
def fbresnet_augmentor(isTrain):
    """
    Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
    """
    if isTrain:
        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 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
def fbresnet_augmentor(isTrain):
    """
    Augmentor used in fb.resnet.torch, for BGR images in range [0,255].
    """
    if isTrain:
        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
#####################################################################################################
##################################################################################################### 

# 需要导入模块: from tensorpack import imgaug [as 别名]
# 或者: from tensorpack.imgaug import ResizeShortestEdge [as 别名]
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