本文整理汇总了Python中tensorflow.keras.preprocessing.image.ImageDataGenerator方法的典型用法代码示例。如果您正苦于以下问题：Python image.ImageDataGenerator方法的具体用法？Python image.ImageDataGenerator怎么用？Python image.ImageDataGenerator使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.keras.preprocessing.image的用法示例。
在下文中一共展示了image.ImageDataGenerator方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: cocohpe_val_transform
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cocohpe_val_transform(ds_metainfo,
data_format="channels_last"):
"""
Create image transform sequence for validation subset.
Parameters:
----------
ds_metainfo : DatasetMetaInfo
Pascal VOC2012 dataset metainfo.
data_format : str, default 'channels_last'
The ordering of the dimensions in tensors.
Returns
-------
ImageDataGenerator
Image transform sequence.
"""
data_generator = CocoHpeImageDataGenerator(
preprocessing_function=(lambda img: ds_metainfo.val_transform2(ds_metainfo=ds_metainfo)(img)),
data_format=data_format)
return data_generator 示例2: cifar10_val_transform
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cifar10_val_transform(ds_metainfo,
data_format="channels_last"):
"""
Create image transform sequence for validation subset.
Parameters:
----------
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
data_format : str, default 'channels_last'
The ordering of the dimensions in tensors.
Returns
-------
ImageDataGenerator
Image transform sequence.
"""
data_generator = ImageDataGenerator(
preprocessing_function=(lambda img: img_normalization(
img=img,
mean_rgb=ds_metainfo.mean_rgb,
std_rgb=ds_metainfo.std_rgb)),
data_format=data_format)
return data_generator 示例3: imagenet_val_transform
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def imagenet_val_transform(ds_metainfo,
data_format="channels_last"):
"""
Create image transform sequence for validation subset.
Parameters:
----------
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
data_format : str, default 'channels_last'
The ordering of the dimensions in tensors.
Returns
-------
ImageDataGenerator
Image transform sequence.
"""
data_generator = ImageDataGenerator(
preprocessing_function=(lambda img: img_normalization(
img=img,
mean_rgb=ds_metainfo.mean_rgb,
std_rgb=ds_metainfo.std_rgb)),
data_format=data_format)
return data_generator 示例4: cub200_val_transform
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cub200_val_transform(ds_metainfo,
data_format="channels_last"):
"""
Create image transform sequence for validation subset.
Parameters:
----------
ds_metainfo : DatasetMetaInfo
CUB-200-2011 dataset metainfo.
data_format : str, default 'channels_last'
The ordering of the dimensions in tensors.
Returns
-------
ImageDataGenerator
Image transform sequence.
"""
data_generator = CubImageDataGenerator(
preprocessing_function=(lambda img: img_normalization(
img=img,
mean_rgb=ds_metainfo.mean_rgb,
std_rgb=ds_metainfo.std_rgb)),
data_format=data_format)
return data_generator 示例5: __init__
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def __init__(self,
dims,
n_clusters=10,
alpha=1.0):
super(FcDEC, self).__init__()
self.dims = dims
self.input_dim = dims[0]
self.n_stacks = len(self.dims) - 1
self.n_clusters = n_clusters
self.alpha = alpha
self.pretrained = False
self.datagen = ImageDataGenerator(width_shift_range=0.1, height_shift_range=0.1, rotation_range=10)
self.autoencoder, self.encoder = autoencoder(self.dims)
# prepare FcDEC model
clustering_layer = ClusteringLayer(self.n_clusters, name='clustering')(self.encoder.output)
self.model = Model(inputs=self.encoder.input, outputs=clustering_layer) 示例6: cocohpe_val_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cocohpe_val_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for validation subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
Pascal VOC2012 dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
split = "val"
root = ds_metainfo.root_dir_path
root = os.path.join(root, split)
generator = data_generator.flow_from_directory(
directory=root,
target_size=ds_metainfo.input_image_size,
class_mode="binary",
batch_size=batch_size,
shuffle=False,
interpolation="bilinear",
dataset=ds_metainfo.dataset_class(
root=ds_metainfo.root_dir_path,
mode="val",
transform=ds_metainfo.val_transform2(
ds_metainfo=ds_metainfo)))
return generator 示例7: cocohpe_test_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cocohpe_test_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for testing subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
Pascal VOC2012 dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
split = "val"
root = ds_metainfo.root_dir_path
root = os.path.join(root, split)
generator = data_generator.flow_from_directory(
directory=root,
target_size=ds_metainfo.input_image_size,
class_mode="binary",
batch_size=batch_size,
shuffle=False,
interpolation="bilinear",
dataset=ds_metainfo.dataset_class(
root=ds_metainfo.root_dir_path,
mode="test",
transform=ds_metainfo.test_transform2(
ds_metainfo=ds_metainfo)))
return generator 示例8: cifar10_train_transform
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cifar10_train_transform(ds_metainfo,
data_format="channels_last"):
"""
Create image transform sequence for training subset.
Parameters:
----------
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
data_format : str, default 'channels_last'
The ordering of the dimensions in tensors.
Returns
-------
ImageDataGenerator
Image transform sequence.
"""
data_generator = ImageDataGenerator(
preprocessing_function=(lambda img: img_normalization(
img=img,
mean_rgb=ds_metainfo.mean_rgb,
std_rgb=ds_metainfo.std_rgb)),
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
data_format=data_format)
return data_generator 示例9: cifar10_val_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cifar10_val_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for validation subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
assert(ds_metainfo is not None)
_, (x_test, y_test) = cifar10.load_data()
generator = data_generator.flow(
x=x_test,
y=y_test,
batch_size=batch_size,
shuffle=False)
return generator 示例10: imagenet_train_transform
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def imagenet_train_transform(ds_metainfo,
data_format="channels_last"):
"""
Create image transform sequence for training subset.
Parameters:
----------
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
data_format : str, default 'channels_last'
The ordering of the dimensions in tensors.
Returns
-------
ImageDataGenerator
Image transform sequence.
"""
data_generator = ImageDataGenerator(
preprocessing_function=(lambda img: img_normalization(
img=img,
mean_rgb=ds_metainfo.mean_rgb,
std_rgb=ds_metainfo.std_rgb)),
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True,
data_format=data_format)
return data_generator 示例11: imagenet_train_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def imagenet_train_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for training subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
split = "train"
root = ds_metainfo.root_dir_path
root = os.path.join(root, split)
generator = data_generator.flow_from_directory(
directory=root,
target_size=ds_metainfo.input_image_size,
class_mode="binary",
batch_size=batch_size,
shuffle=False,
interpolation=ds_metainfo.interpolation_msg)
return generator 示例12: imagenet_val_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def imagenet_val_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for validation subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
split = "val"
root = ds_metainfo.root_dir_path
root = os.path.join(root, split)
generator = data_generator.flow_from_directory(
directory=root,
target_size=ds_metainfo.input_image_size,
class_mode="binary",
batch_size=batch_size,
shuffle=False,
interpolation=ds_metainfo.interpolation_msg)
return generator 示例13: cub200_train_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cub200_train_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for training subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
root = ds_metainfo.root_dir_path
generator = data_generator.flow_from_directory(
directory=root,
target_size=ds_metainfo.input_image_size,
class_mode="binary",
batch_size=batch_size,
shuffle=False,
interpolation=ds_metainfo.interpolation_msg,
mode="val")
return generator 示例14: cub200_val_generator
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def cub200_val_generator(data_generator,
ds_metainfo,
batch_size):
"""
Create image generator for validation subset.
Parameters:
----------
data_generator : ImageDataGenerator
Image transform sequence.
ds_metainfo : DatasetMetaInfo
ImageNet-1K dataset metainfo.
batch_size : int
Batch size.
Returns
-------
Sequential
Image transform sequence.
"""
root = ds_metainfo.root_dir_path
generator = data_generator.flow_from_directory(
directory=root,
target_size=ds_metainfo.input_image_size,
class_mode="binary",
batch_size=batch_size,
shuffle=False,
interpolation=ds_metainfo.interpolation_msg,
mode="val")
return generator 示例15: __init__
# 需要导入模块: from tensorflow.keras.preprocessing import image [as 别名]
# 或者: from tensorflow.keras.preprocessing.image import ImageDataGenerator [as 别名]
def __init__(self,
input_shape,
filters=[32, 64, 128, 10],
n_clusters=10):
self.n_clusters = n_clusters
self.input_shape = input_shape
self.datagen = ImageDataGenerator(width_shift_range=0.1, height_shift_range=0.1, rotation_range=10)
self.datagenx = ImageDataGenerator()
self.autoencoder, self.encoder = CAE(input_shape, filters)
# Define ConvIDEC model
clustering_layer = ClusteringLayer(self.n_clusters, name='clustering')(self.encoder.output)
self.model = Model(inputs=self.autoencoder.input,
outputs=clustering_layer)