Classification分类学习

    #Classification分类学习
    import tensorflow as tfw
    import numpy as np
    #from tensorflow.examples.tutorials.mnist import input_data
    #mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
    from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
    mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

    def add_layer(inputs,in_size,out_size,activation_function = None):
    #add one more layer and return the output of this layer 
        Weights = tfw.Variable(tfw.random_normal([in_size,out_size]))
        biases = tfw.Variable(tfw.zeros([1,out_size]) + 0.1)
        Wx_plus_b = tfw.matmul(inputs,Weights) +biases
        if  activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b,)
        return outputs

    def compute_accuracy(v_xs,v_ys):
        global prediction
        #修改方法：batch_target = batch_target.astype(np.float32)
        v_xs = v_xs.astype(np.float32)
        y_pre = sess.run(prediction,feed_dict = {xs:v_xs})
        correct_prediction = tfw.equal(tfw.argmax(y_pre,1),tfw.argmax(v_ys,1))
        accuracy = tfw.reduce_mean(tfw.cast(correct_prediction,tfw.float32))
        result = sess.run(accuracy,feed_dict ={xs:v_xs,ys:v_ys})
        return result

    #define placeholder for inputs to network
    xs= tfw.placeholder(tfw.float32,[None,784])  #28*28
    ys= tfw.placeholder(tfw.float32,[None,10])  

    #add output layer
    prediction = add_layer(xs,784,10,activation_function = tfw.nn.softmax)

    #the error between prediction and real data
    cross_entropy =tfw.reduce_mean(-tfw.reduce_sum(ys*tfw.log(prediction),reduction_indices = [1]))  #loss
    train_step = tfw.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)                       

    sess =tfw.Session()
    #important step
    sess.run(tfw.initialize_all_variables())

    for i in range(1000):
        batch_xs,batch_ys = mnist.train.next_batch(100)
        #batch_target = batch_target.astype(np.float32)
        batch_xs = batch_xs.astype(np.float32)
        batch_ys = batch_ys.astype(np.float32)
        sess.run(train_step,feed_dict = {xs:batch_xs,ys:batch_ys})
        if i%50 == 0:
            print(compute_accuracy(mnist.test.images,mnist.test.labels))   

Extracting MNIST_data\train-images-idx3-ubyte.gz
Extracting MNIST_data\train-labels-idx1-ubyte.gz
Extracting MNIST_data\t10k-images-idx3-ubyte.gz
Extracting MNIST_data\t10k-labels-idx1-ubyte.gz
0.0964
0.6393
0.747
0.7878
0.8094
0.82
0.8315
0.8421
0.8449
0.8527
0.8542
0.8595
0.8581
0.8631
0.8677
0.8723
0.872
0.872
0.8774
0.8742