MNIST

**简单介绍下Mnist: **
**MNIST是一个简单的视觉计算数据集，它是像下面这样手写的数字图片： **


**每张图片还额外有一个标签记录了图片上数字是几，例如上面几张图的标签就是：5、0、4、1。 **
**本次将会展现如何训练一个模型来识别这些图片，最终实现模型对图片上的数字进行预测。 **

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import argparse  #解析训练和检测数据模块
import sys

from tensorflow.examples.tutorials.mnist import input_data

import tensorflow as tf

FLAGS = None


def main(_):
  # Import data 
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)

  # Create the model
  x = tf.placeholder(tf.float32, [None, 784]) #此函数可以理解为形参，用于定义过程，在执行的时候再赋具体的值
  W = tf.Variable(tf.zeros([784, 10])) # tf.zeros表示所有的维度都为0 
  b = tf.Variable(tf.zeros([10]))
  y = tf.matmul(x, W) + b  #对应每个分类概率值。

  # Define loss and optimizer
  y_ = tf.placeholder(tf.float32, [None, 10])

  # The raw formulation of cross-entropy,
  #
  #   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
  #                                 reduction_indices=[1]))
  #
  # can be numerically unstable.
  #
  # So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
  # outputs of 'y', and then average across the batch.
  cross_entropy = tf.reduce_mean(
      tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
  train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

  sess = tf.InteractiveSession()
  tf.global_variables_initializer().run()
  # Train
  for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

  # Test trained model
  correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  print(sess.run(accuracy, feed_dict={x: mnist.test.images,
                                      y_: mnist.test.labels}))

if __name__ == '__main__':
  parser = argparse.ArgumentParser()
  parser.add_argument('--data_dir', type=str, default='/tmp/tensorflow/mnist/input_data',
                      help='Directory for storing input data')
  FLAGS, unparsed = parser.parse_known_args()
  tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)

基于Keras 搭建 MNIST识别

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

#可视化
import keras.callbacks


batch_size = 128
num_classes = 10
epochs = 2

save_dir = os.path.join(os.getcwd(), 'saved_models')
model_name = 'keras_mnist_trained_model.h5'

img_rows,img_cols = 28,28

(x_train,y_train),(x_test,y_test) = mnist.load_data()

if K.image_data_format() == "channels_first":
    x_train = x_train.reshape(x_train.shape[0],1,img_rows,img_cols)
    x_test = x_test.reshape(x_test.shape[0],1,img_rows,img_cols)
    input_shape = (1,img_rows,img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols,1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols,1)
    input_shape = ( img_rows, img_cols,1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /=255
x_test /=255


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

model = Sequential()

model.add(Conv2D(32,kernel_size=(3,3),input_shape=input_shape))
model.add(Activation('relu'))
model.add(Conv2D(64,kernel_size=(3,3)))
model.add(Activation('relu'))
model.add(Conv2D(128,kernel_size=(3,3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256))
model.add(Activation('relu'))
model.add(Dropout(0.25))
model.add(Dense(num_classes,activation='softmax'))
model.summary()

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

tb_config = keras.callbacks.TensorBoard(
    log_dir= './logs',
    write_images= 1,
    histogram_freq= 1)

cbks = [tb_config]



history=model.fit(x_train,y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          callbacks= cbks,
          validation_data=(x_test,y_test))

# Save model and weights
if not os.path.isdir(save_dir):
    os.makedirs(save_dir)
model_path = os.path.join(save_dir, model_name)
model.save(model_path)
print('Saved trained model at %s ' % model_path)





score = model.evaluate(x_test,y_test,verbose=0)

print('Test loss:',score[0])
print('Test accuracy:',score[1])

单个图片识别

from  __future__ import  print_function
from keras.datasets import mnist
from keras.models import load_model
import numpy as np


(x_train,y_train),(x_test,y_test) = mnist.load_data()


model=load_model('./saved_models/keras_mnist_trained_model.h5')

import cv2
# print(x_test[100],y_test[100])
print(x_test[100].shape)
# input_img=cv2.resize(x_test[100],(28,28))
input_img = np.reshape(x_test[100],[1,28,28,1])
print(input_img.shape)
predict_class = np.argmax(model.predict(input_img))

print(predict_class)