Python imgaug.Lighting方法代碼示例

本文整理匯總了Python中tensorpack.imgaug.Lighting方法的典型用法代碼示例。如果您正苦於以下問題：Python imgaug.Lighting方法的具體用法？Python imgaug.Lighting怎麽用？Python imgaug.Lighting使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類tensorpack.imgaug的用法示例。

在下文中一共展示了imgaug.Lighting方法的6個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: fbresnet_augmentor

# 需要導入模塊: from tensorpack import imgaug [as 別名]
# 或者: from tensorpack.imgaug import Lighting [as 別名]
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

開發者ID:huawei-noah，項目名稱:ghostnet，代碼行數:34，代碼來源:imagenet_utils.py

示例2: fbresnet_augmentor

# 需要導入模塊: from tensorpack import imgaug [as 別名]
# 或者: from tensorpack.imgaug import Lighting [as 別名]
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

開發者ID:tensorpack，項目名稱:benchmarks，代碼行數:41，代碼來源:imagenet_utils.py

示例3: fbresnet_augmentor

# 需要導入模塊: from tensorpack import imgaug [as 別名]
# 或者: from tensorpack.imgaug import Lighting [as 別名]
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

開發者ID:qinenergy，項目名稱:webvision-2.0-benchmarks，代碼行數:31，代碼來源:imagenet_utils.py

示例4: fbresnet_augmentor

# 需要導入模塊: from tensorpack import imgaug [as 別名]
# 或者: from tensorpack.imgaug import Lighting [as 別名]
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

開發者ID:microsoft，項目名稱:LQ-Nets，代碼行數:34，代碼來源:imagenet_utils.py

示例5: fbresnet_augmentor

# 需要導入模塊: from tensorpack import imgaug [as 別名]
# 或者: from tensorpack.imgaug import Lighting [as 別名]
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
#####################################################################################################
#####################################################################################################

開發者ID:BayesWatch，項目名稱:sequential-imagenet-dataloader，代碼行數:33，代碼來源:data.py

示例6: get_augmentations

# 需要導入模塊: from tensorpack import imgaug [as 別名]
# 或者: from tensorpack.imgaug import Lighting [as 別名]
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

開發者ID:ildoonet，項目名稱:tf-mobilenet-v2，代碼行數:28，代碼來源:data_helper.py

注：本文中的tensorpack.imgaug.Lighting方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。