www九九热,欧美国产在线观看,99精品99

ImageDataGenerator的參數自己看文檔

									from keras.preprocessing import image

									import numpy as np

									X_train=np.ones((3,123,123,1))

									Y_train=np.array([[1],[2],[2]])

									generator=image.ImageDataGenerator(featurewise_center=False,

									  samplewise_center=False,

									  featurewise_std_normalization=False,

									  samplewise_std_normalization=False,

									  zca_whitening=False,

									  zca_epsilon=1e-6,

									  rotation_range=180,

									  width_shift_range=0.2,

									  height_shift_range=0.2,

									  shear_range=0,

									  zoom_range=0.001,

									  channel_shift_range=0,

									  fill_mode='nearest',

									  cval=0.,

									  horizontal_flip=True,

									  vertical_flip=True,

									  rescale=None,

									  preprocessing_function=None,

									  data_format='channels_last')

									a=generator.flow(X_train,Y_train,batch_size=20)#生成的是一個迭代器，可直接用于for循環

									'''

									batch_size如果小于X的第一維m，next生成的多維矩陣的第一維是為batch_size，輸出是從輸入中隨機選取batch_size個數據

									batch_size如果大于X的第一維m，next生成的多維矩陣的第一維是m，輸出是m個數據，不過順序隨機

									，輸出的X，Y是一一對對應的

									如果要直接用于tf.placeholder()，要求生成的矩陣和要與tf.placeholder相匹配

									'''

									X,Y=next(a)

									print(Y)

									X,Y=next(a)

									print(Y)

									X,Y=next(a)

									print(Y)

									X,Y=next(a)

輸出

補充知識：tensorflow 與keras 混用之坑

在使用tensorflow與keras混用是model.save 是正常的但是在load_model的時候報錯了在這里mark 一下

其中錯誤為：TypeError: tuple indices must be integers, not list

再一一番百度后無結果，上谷歌后找到了類似的問題。但是是一對鳥文不知道什么東西（翻譯后發現是俄文）。后來谷歌翻譯了一下找到了解決方法。故將原始問題文章貼上來警示一下

原訓練代碼

									from tensorflow.python.keras.preprocessing.image import ImageDataGenerator

									from tensorflow.python.keras.models import Sequential

									from tensorflow.python.keras.layers import Conv2D, MaxPooling2D, BatchNormalization

									from tensorflow.python.keras.layers import Activation, Dropout, Flatten, Dense

									#Каталог с данными для обучения

									train_dir = 'train'

									# Каталог с данными для проверки

									val_dir = 'val'

									# Каталог с данными для тестирования

									test_dir = 'val'

									# Размеры изображения

									img_width, img_height = 800, 800

									# Размерность тензора на основе изображения для входных данных в нейронную сеть

									# backend Tensorflow, channels_last

									input_shape = (img_width, img_height, 3)

									# Количество эпох

									epochs = 1

									# Размер мини-выборки

									batch_size = 4

									# Количество изображений для обучения

									nb_train_samples = 300

									# Количество изображений для проверки

									nb_validation_samples = 25

									# Количество изображений для тестирования

									nb_test_samples = 25

									model = Sequential()

									model.add(Conv2D(32, (7, 7), padding="same", input_shape=input_shape))

									model.add(BatchNormalization())

									model.add(Activation('tanh'))

									model.add(MaxPooling2D(pool_size=(10, 10)))

									model.add(Conv2D(64, (5, 5), padding="same"))

									model.add(BatchNormalization())

									model.add(Activation('tanh'))

									model.add(MaxPooling2D(pool_size=(10, 10)))

									model.add(Flatten())

									model.add(Dense(512))

									model.add(Activation('relu'))

									model.add(Dropout(0.5))

									model.add(Dense(10, activation='softmax'))

									model.compile(loss='categorical_crossentropy',

									       optimizer="Nadam",

									       metrics=['accuracy'])

									print(model.summary())

									datagen = ImageDataGenerator(rescale=1. / 255)

									train_generator = datagen.flow_from_directory(

									  train_dir,

									  target_size=(img_width, img_height),

									  batch_size=batch_size,

									  class_mode='categorical')

									val_generator = datagen.flow_from_directory(

									  val_dir,

									  target_size=(img_width, img_height),

									  batch_size=batch_size,

									  class_mode='categorical')

									test_generator = datagen.flow_from_directory(

									  test_dir,

									  target_size=(img_width, img_height),

									  batch_size=batch_size,

									  class_mode='categorical')

									model.fit_generator(

									  train_generator,

									  steps_per_epoch=nb_train_samples // batch_size,

									  epochs=epochs,

									  validation_data=val_generator,

									  validation_steps=nb_validation_samples // batch_size)

									print('Сохраняем сеть')

									model.save("grib.h5")

									print("Сохранение завершено!")

模型載入

									from tensorflow.python.keras.preprocessing.image import ImageDataGenerator

									from tensorflow.python.keras.models import Sequential

									from tensorflow.python.keras.layers import Conv2D, MaxPooling2D, BatchNormalization

									from tensorflow.python.keras.layers import Activation, Dropout, Flatten, Dense

									from keras.models import load_model

									print("Загрузка сети")

									model = load_model("grib.h5")

									print("Загрузка завершена!")

報錯

									/usr/bin/python3.5 /home/disk2/py/neroset/do.py

									/home/mama/.local/lib/python3.5/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.

									 from ._conv import register_converters as _register_converters

									Using TensorFlow backend.

									Загрузка сети

									Traceback (most recent call last):

									 File "/home/disk2/py/neroset/do.py", line 13, in <module>

									  model = load_model("grib.h5")

									 File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 243, in load_model

									  model = model_from_config(model_config, custom_objects=custom_objects)

									 File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 317, in model_from_config

									  return layer_module.deserialize(config, custom_objects=custom_objects)

									 File "/usr/local/lib/python3.5/dist-packages/keras/layers/__init__.py", line 55, in deserialize

									  printable_module_name='layer')

									 File "/usr/local/lib/python3.5/dist-packages/keras/utils/generic_utils.py", line 144, in deserialize_keras_object

									  list(custom_objects.items())))

									 File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 1350, in from_config

									  model.add(layer)

									 File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 492, in add

									  output_tensor = layer(self.outputs[0])

									 File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 590, in __call__

									  self.build(input_shapes[0])

									 File "/usr/local/lib/python3.5/dist-packages/keras/layers/normalization.py", line 92, in build

									  dim = input_shape[self.axis]

									TypeError: tuple indices must be integers or slices, not list

									Process finished with exit code 1

戰斗種族解釋

убераю BatchNormalization всё работает хорошо. Не подскажите в чём ошибка?Выяснил что сохранение keras и нормализация tensorflow не работают вместе нужно просто изменить строку импорта.（譯文：整理BatchNormalization一切正常。不要告訴我錯誤是什么？我發現保存keras和規范化tensorflow不能一起工作;只需更改導入字符串即可。)

強調文本強調文本

									keras.preprocessing.image import ImageDataGenerator

									keras.models import Sequential

									keras.layers import Conv2D, MaxPooling2D, BatchNormalization

									keras.layers import Activation, Dropout, Flatten, Dense