AttributeError：“tensorflow”模块在Keras模型到tensorflow lite转换Python中没有属性“lite”

Question

我尝试使用以下代码将以下keras模型转换为tflite，以便在移动平台上托管。我已经安装了tensorflow version=1.12python version=3.6.7keras version=2.2.4 运行此代码时，出现以下错误。在

转换器=tf.lite.tflite转换器.from_keras_model_文件（keras_文件） AttributeError:模块“tensorflow”没有属性“lite”

这个错误的原因是什么？如何解决？在

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
import tensorflow as tf

# dimensions of our images.
img_width, img_height = 150, 150

train_data_dir = 'D:\\My Projects\\dataset\\dataset6_2clz\\train'
validation_data_dir = 'D:\\My Projects\\Dataset\\dataset6_2clz\\validation'



nb_train_samples = 75
nb_validation_samples = 50
#epochs = 50
#batch_size = 16
epochs = 5
batch_size = 4

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])



train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)


test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)


# Save tf.keras model in HDF5 format.
keras_file = "7_try.h5"
model.save('7_try.h5')


# Convert to TensorFlow Lite model.

converter = tf.lite.TFLiteConverter.from_keras_model_file(keras_file)
tflite_model = converter.convert()
open("converted_model.tflite", "wb").write(tflite_model)

Answer 1

在tensorflow 1.12中应该是 converter = tf.contrib.lite.TFLiteConverter.from_keras_model_file(keras_file)

见https://www.tensorflow.org/lite/convert/python_api#pre_tensorflow_1.12 我猜你读了下面的参考文献https://www.tensorflow.org/lite/convert/python_api，但请注意下面的注释

Note: These docs describe the converter in the TensorFlow nightly release, installed using pip install tf-nightly. For docs describing older versions reference "Converting models from TensorFlow 1.12".

此外，有关详细信息，您可以查看此提交消息https://github.com/tensorflow/tensorflow/commit/61c6c84964b4aec80aeace187aab8cb2c3e55a72