原文鏈接

#!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Thu Mar 15 21:49:08 2018@author: luogan """import tensorflow as tf from sklearn.datasets import load_digits import numpy as np digits = load_digits() X_data = digits.data.astype(np.float32) Y_data = digits.target.astype(np.float32).reshape(-1,1) print (X_data.shape) print (Y_data.shape)from sklearn.preprocessing import MinMaxScalerscaler = MinMaxScaler() X_data = scaler.fit_transform(X_data) from sklearn.preprocessing import OneHotEncoder Y = OneHotEncoder().fit_transform(Y_data).todense() #one-hot編碼 X = X_data.reshape(-1,8,8,1)batch_size = 8 # 使用MBGD算法，設定batch_size為8def generatebatch(X,Y,n_examples, batch_size):for batch_i in range(n_examples // batch_size):start = batch_i*batch_sizeend = start + batch_sizebatch_xs = X[start:end]batch_ys = Y[start:end]yield batch_xs, batch_ys # 生成每一個batchtf.reset_default_graph() # 輸入層 tf_X = tf.placeholder(tf.float32,[None,8,8,1]) tf_Y = tf.placeholder(tf.float32,[None,10])# 卷積層+激活層 conv_filter_w1 = tf.Variable(tf.random_normal([3, 3, 1, 10])) conv_filter_b1 = tf.Variable(tf.random_normal([10])) relu_feature_maps1 = tf.nn.relu(\tf.nn.conv2d(tf_X, conv_filter_w1,strides=[1, 1, 1, 1], padding='SAME') + conv_filter_b1)# 池化層 max_pool1 = tf.nn.max_pool(relu_feature_maps1,ksize=[1,3,3,1],strides=[1,2,2,1],padding='SAME')print (max_pool1)conv_filter_w2 = tf.Variable(tf.random_normal([3, 3, 10, 5])) conv_filter_b2 = tf.Variable(tf.random_normal([5])) conv_out2 = tf.nn.conv2d(relu_feature_maps1, conv_filter_w2,strides=[1, 2, 2, 1], padding='SAME') + conv_filter_b2 print (conv_out2)batch_mean, batch_var = tf.nn.moments(conv_out2, [0, 1, 2], keep_dims=True) shift = tf.Variable(tf.zeros([5])) scale = tf.Variable(tf.ones([5])) epsilon = 1e-3 BN_out = tf.nn.batch_normalization(conv_out2, batch_mean, batch_var, shift, scale, epsilon) print (BN_out) relu_BN_maps2 = tf.nn.relu(BN_out)max_pool2 = tf.nn.max_pool(relu_BN_maps2,ksize=[1,3,3,1],strides=[1,2,2,1],padding='SAME')print (max_pool2) max_pool2_flat = tf.reshape(max_pool2, [-1, 2*2*5])# 全連接層 fc_w1 = tf.Variable(tf.random_normal([2*2*5,50])) fc_b1 = tf.Variable(tf.random_normal([50])) fc_out1 = tf.nn.relu(tf.matmul(max_pool2_flat, fc_w1) + fc_b1)# 輸出層 out_w1 = tf.Variable(tf.random_normal([50,10])) out_b1 = tf.Variable(tf.random_normal([10])) pred = tf.nn.softmax(tf.matmul(fc_out1,out_w1)+out_b1)loss = -tf.reduce_mean(tf_Y*tf.log(tf.clip_by_value(pred,1e-11,1.0)))train_step = tf.train.AdamOptimizer(1e-3).minimize(loss)y_pred = tf.arg_max(pred,1) bool_pred = tf.equal(tf.arg_max(tf_Y,1),y_pred) accuracy = tf.reduce_mean(tf.cast(bool_pred,tf.float32)) # 準確率with tf.Session() as sess:sess.run(tf.global_variables_initializer())for epoch in range(1000): # 迭代1000個周期for batch_xs,batch_ys in generatebatch(X,Y,Y.shape[0],batch_size): # 每個周期進行MBGD算法sess.run(train_step,feed_dict={tf_X:batch_xs,tf_Y:batch_ys})if(epoch%100==0):res = sess.run(accuracy,feed_dict={tf_X:X,tf_Y:Y})print (epoch,res)res_ypred = y_pred.eval(feed_dict={tf_X:X,tf_Y:Y}).flatten() # 只能預測一批樣本，不能預測一個樣本print (res_ypred) from sklearn.metrics import accuracy_scoreprint accuracy_score(Y_data,res_ypred.reshape(-1,1))

總結

以上是生活随笔為你收集整理的CNN 卷积神经网络TensorFlow简单实现的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。