TensorFlow 实现MLP

#coding=utf-8import numpy as npfrom numpy.random import RandomStateimport tensorflow as tfw1=tf.Variable(tf.random_normal([2,3],stddev=1,seed=1))b1=tf.Variable(tf.constant(0.1, shape=[2]))w2=tf.Variable(tf.random_normal([3,1],stddev=1,seed=1))b2=tf.Variable(tf.constant(0.1, shape=[1]))x=tf.placeholder(dtype=tf.float32, shape=(None,2), name='x-input')#y_=tf.placeholder(dtype=tf.float32, shape=(None,1), name='y-output')#print(tf.shape(x))a=tf.matmul(x+b1,w1)a_out=tf.nn.relu(a)y=tf.matmul(a_out+b2,w2)dataset_size=128rdm=RandomState(1)X=rdm.rand(dataset_size, 2)# print(X)Y=[[int(x1+x2>1)] for (x1,x2) in X]# print(Y)cross_entropy=-tf.reduce_mean(y_*tf.log(tf.clip_by_value(y,1e-10,1.0)))train_step=tf.train.AdamOptimizer(0.01).minimize(cross_entropy)init_op=tf.global_variables_initializer()sess=tf.Session()sess.run(init_op)print('w1 w2:')print(sess.run(w1))print(sess.run(w2))print('b1 b2:')print(sess.run(b1))print(sess.run(b2))for i in range(10):    result=sess.run(train_step,feed_dict={x:X[0:128],y_:Y[0:128]})    loss=sess.run(cross_entropy,feed_dict={x:X[0:128],y_:Y[0:128]})    print(loss)print('w1 w2:')print(sess.run(w1))print(sess.run(w2))print('b1 b2:')print(sess.run(b1))print(sess.run(b2))sess.close()