#coding:utf-8 import tensorflow as tf from PIL import Image,ImageFilter from tensorflow.examples.tutorials.mnist import input_data def imageprepare(argv): # 该函数读一张图片，处理后返回一个数组，进到网络中预测 """ This function returns the pixel values. The imput is a png file location. """ im = Image.open(argv).convert('L') width = float(im.size[0]) height = float(im.size[1]) newImage = Image.new('L', (28, 28), (255)) # creates white canvas of 28x28 pixels if width > height: # check which dimension is bigger # Width is bigger. Width becomes 20 pixels. nheight = int(round((20.0 / width * height), 0)) # resize height according to ratio width if nheight == 0: # rare case but minimum is 1 pixel nheight = 1 # resize and sharpen img = im.resize((20, nheight), Image.ANTIALIAS).filter(ImageFilter.SHARPEN) wtop = int(round(((28 - nheight) / 2), 0)) # caculate horizontal pozition newImage.paste(img, (4, wtop)) # paste resized image on white canvas else: # Height is bigger. Heigth becomes 20 pixels. nwidth = int(round((20.0 / height * width), 0)) # resize width according to ratio height if (nwidth == 0): # rare case but minimum is 1 pixel nwidth = 1 # resize and sharpen img = im.resize((nwidth, 20), Image.ANTIALIAS).filter(ImageFilter.SHARPEN) wleft = int(round(((28 - nwidth) / 2), 0)) # caculate vertical pozition newImage.paste(img, (wleft, 4)) # paste resized image on white canvas # newImage.save("sample.png") tv = list(newImage.getdata()) # get pixel values # normalize pixels to 0 and 1. 0 is pure white, 1 is pure black. tva = [(255 - x) * 1.0 / 255.0 for x in tv] return tva def weight_variable(shape): initial = tf.truncated_normal(shape,stddev=0.1) #生成一个截断的正态分布 return tf.Variable(initial) def bias_variable(shape): initial = tf.constant(0.1,shape = shape) return tf.Variable(initial) #卷基层 def conv2d(x,W): return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME') #池化层 def max_pool_2x2(x): return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME') #定义两个placeholder x = tf.placeholder(tf.float32, [None,784]) #y = tf.placeholder(tf.float32,[None,10]) #改变x的格式转为4D的向量[batch,in_height,in_width,in_channels] x_image = tf.reshape(x, [-1,28,28,1]) #初始化第一个卷基层的权值和偏置 W_conv1 = weight_variable([5,5,1,32]) #5*5的采样窗口 32个卷积核从一个平面抽取特征 32个卷积核是自定义的 b_conv1 = bias_variable([32]) #每个卷积核一个偏置值 #把x_image和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数 h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1) h_pool1 = max_pool_2x2(h_conv1) #进行max-pooling #初始化第二个卷基层的权值和偏置 W_conv2 = weight_variable([5,5,32,64]) # 5*5的采样窗口 64个卷积核从32个平面抽取特征 由于前一层操作得到了32个特征图 b_conv2 = bias_variable([64]) #每一个卷积核一个偏置值 #把h_pool1和权值向量进行卷积 再加上偏置值 然后应用于relu激活函数 h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2) #进行max-pooling #28x28的图片第一次卷积后还是28x28 第一次池化后变为14x14 #第二次卷积后 变为14x14 第二次池化后变为7x7 #通过上面操作后得到64张7x7的平面 #初始化第一个全连接层的权值 W_fc1 = weight_variable([7*7*64,1024])#上一层有7*7*64个神经元，全连接层有1024个神经元 b_fc1 = bias_variable([1024]) #1024个节点 #把第二个池化层的输出扁平化为一维 h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64]) #求第一个全连接层的输出 h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1) #keep_prob用来表示神经元的输出概率 keep_prob = tf.placeholder(tf.float32) h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob) #初始化第二个全连接层 W_fc2 = weight_variable([1024,10]) b_fc2 = bias_variable([10]) #计算输出 gailv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2) saver = tf.train.Saver() with tf.Session() as sess: sess.run(tf.global_variables_initializer()) saver.restore(sess,'/home/xxx/logs/mnistmodel-1') array = imageprepare('/home/xxx/logs/7.jpg') # 读一张包含数字的图片 prediction = tf.argmax(gailv, 1) # 预测 prediction = prediction.eval(feed_dict={x:[array],keep_prob:1.0},session=sess) print('The digits in this image is:%d' % prediction[0])
结果 手写数字图片7被预测为7
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0: Y I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:03:00.0) The digits in this image is:7