Keras入门课2 -- 使用CNN识别mnist手写数字

Keras入门课2：使用CNN识别mnist手写数字

本系列课程代码，欢迎star：
https://github.com/tsycnh/Keras-Tutorials

本文用一个最简单的两层CNN神经网络来对mnist数据库进行分类识别。

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

Using TensorFlow backend.
/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/importlib/_bootstrap.py:205: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
  return f(*args, **kwds)

(x_train,y_train),(x_test,y_test) = mnist.load_data() # out: np.ndarray
print(x_train.shape,y_train.shape)
print(x_test.shape,y_test.shape)

(60000, 28, 28) (60000,)
(10000, 28, 28) (10000,)

↓可视化一些图片

import matplotlib.pyplot as plt
im = plt.imshow(x_train[0],cmap='gray')
plt.show()
im2 = plt.imshow(x_train[1],cmap='gray')
plt