多平台统一管理软件接口,如何实现多平台统一管理软件接口
502
2022-08-27
minist手写数据集识别(minist手写字分类)
minist手写数据集识别
import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_data # 定义神经网络模型的评估部分def compute_accuracy(test_xs, test_ys): # 使用全局变量prediction global prediction # 获得预测值y_pre y_pre = sess.run(prediction, feed_dict = { xs: test_xs, keep_prob: 1}) # 判断预测值y和真实值y_中最大数的索引是否一致,y_pre的值为1-10概率, 返回值为bool序列 correct_prediction = tf.equal(tf.argmax(y_pre, 1), tf.argmax(test_ys, 1)) # 定义准确率的计算 accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) #tf.cast将bool转换为float32 # 计算准确率 result = sess.run(accuracy) return result # 下载mnist数据mnist = input_data.read_data_sets('MNIST_data', one_hot=True) # 权重参数初始化def weight_variable(shape): initial = tf.truncated_normal(shape, stddev = 0.1) #截断的正态分布,标准差stddev return tf.Variable(initial) # 偏置参数初始化def bias_variable(shape): initial = tf.constant(0.1, shape = shape) return tf.Variable(initial) # 定义卷积层def conv2d(x, W): # stride的四个参数:[batch, height, width, channels], [batch_size, image_rows, image_cols, number_of_colors] # height, width就是图像的高度和宽度,batch和channels在卷积层中通常设为1 return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding = 'SAME') def max_pool_2x2(x): return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME') """ max_pool(x,ksize,strides,padding)参数含义 x:input ksize:filter,滤波器大小2*2 strides:步长,2*2,表示filter窗口每次水平移动2格,每次垂直移动2格 padding:填充方式,补零 conv2d(x,W,strides=[1,1,1,1],padding='SAME')参数含义与上述类似 x:input W:filter,滤波器大小 strides:步长,1*1,表示filter窗口每次水平移动1格,每次垂直移动1格 padding:填充方式,补零('SAME') """ # 输入输出数据的placeholderxs = tf.placeholder(tf.float32, [None, 784])ys = tf.placeholder(tf.float32, [None, 10])# dropout的比例keep_prob = tf.placeholder(tf.float32) # 对数据进行重新排列,形成图像x_image = tf.reshape(xs, [-1, 28, 28, 1])# -1, 28, 28, 1 print(x_image.shape) # 卷积层一# patch为5*5,in_size为1,即图像的厚度,如果是彩色,则为3,32是out_size,输出的大小-》32个卷积和(滤波器)W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])# ReLU操作,输出大小为28*28*32h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)# Pooling操作,输出大小为14*14*32h_pool1 = max_pool_2x2(h_conv1) # 卷积层二# patch为5*5,in_size为32,即图像的厚度,64是out_size,输出的大小W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])# ReLU操作,输出大小为14*14*64h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)# Pooling操作,输出大小为7*7*64h_pool2 = max_pool_2x2(h_conv2) # 全连接层一W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])# 输入数据变换h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64]) #整形成m*n,列n为7*7*64# 进行全连接操作h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) # tf.matmul# 防止过拟合,dropouth_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # 全连接层二W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])# 预测prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) # 计算losscross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction), reduction_indices=[1]))# 神经网络训练train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy) #0.0001 # 定义Sessionsess = tf.Session()init = tf.global_variables_initializer()# 执行初始化sess.run(init) # 进行训练迭代for i in range(1000): # 取出mnist数据集中的100个数据 batch_xs, batch_ys = mnist.train.next_batch(50) #100 # 执行训练过程并传入真实数据 sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob: 0.5}) if i % 100 == 0: print( compute_accuracy(mnist.test.images, mnist.test.labels) )
总结:
基本完成,ResNet解决了训练集上网络过多导致性能下降,BN层 梯度消失,转变空间保留关键信息,压缩图片,提高了准确率.重点:ResNet网络、通道注意力机制难点:参数上的调节
版权声明:本文内容由网络用户投稿,版权归原作者所有,本站不拥有其著作权,亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容,请联系我们jiasou666@gmail.com 处理,核实后本网站将在24小时内删除侵权内容。
发表评论
暂时没有评论,来抢沙发吧~