TensorFlow2教程-CNN-RNN结构用于图像处理

Tensorflow 2.0 教程持续更新 ：https://blog.csdn.net/qq_31456593/article/details/88606284

完整tensorflow2.0教程代码请看tensorflow2.0：中文教程tensorflow2_tutorials_chinese(欢迎star)

入门教程：
TensorFlow 2.0 教程- Keras 快速入门
TensorFlow 2.0 教程-keras 函数api
TensorFlow 2.0 教程-使用keras训练模型
TensorFlow 2.0 教程-用keras构建自己的网络层
TensorFlow 2.0 教程-keras模型保存和序列化

TensorFlow2教程-CNN-RNN结构用于图像处理

1.导入数据

使用cifar-10数据集

import numpy as np
from sklearn.metrics import accuracy_score
from tensorflow import keras

(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()

y_train = keras.utils.to_categorical(y_train)
y_test = keras.utils.to_categorical(y_test)

print(x_train.shape, ' ', y_train.shape)
print(x_test.shape, ' ', y_test.shape)

(50000, 32, 32, 3)   (50000, 10)
(10000, 32, 32, 3)   (10000, 10)

2.简单的cnn-rnn结构

from tensorflow.keras import layers
model = keras.Sequential()

x_shape = x_train.shape
model.add(layers.Conv2D(input_shape=(x_shape[1], x_shape[2], x_shape[3]),
                       filters=32, kernel_size=(3,3), strides=(1,1), 
                       padding='same', activation=