假设我们已经安装好了tensorflow。
一般在安装好tensorflow后,都会跑它的demo,而最常见的demo就是手写数字识别的demo,也就是mnist数据集。
然而我们仅仅是跑了它的demo而已,可能很多人会有和我一样的想法,如果拿来一张数字图片,如何应用我们训练的网络模型来识别出来,下面我们就以mnist的demo来实现它。
1.训练模型
首先我们要训练好模型,并且把模型model.ckpt保存到指定文件夹
saver = tf.train.Saver()
saver.save(sess, "model_data/model.ckpt")
2.测试模型
我们训练好模型后,将它保存在了model_data文件夹中,你会发现文件夹中出现了4个文件
然后,我们就可以对这个模型进行测试了,将待检测图片放在images文件夹下,执行
# -*- coding:utf-8 -*-
import cv2
import tensorflow as tf
import numpy as np
from sys import path
path.append('../..')
from common import extract_mnist
#初始化单个卷积核上的参数
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
#初始化单个卷积核上的偏置值
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
#输入特征x,用卷积核W进行卷积运算,strides为卷积核移动步长,
#padding表示是否需要补齐边缘像素使输出图像大小不变
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
#对x进行最大池化操作,ksize进行池化的范围,
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')
def main():
#定义会话
sess = tf.InteractiveSession()
#声明输入图片数据,类别
x = tf.placeholder('float',[None,784])
x_img = tf.reshape(x , [-1,28,28,1])
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
W_conv2 = weight_variable([5,5,32,64])
b_conv2 = bias_variable([64])
W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
saver = tf.train.Saver(write_version=tf.train.SaverDef.V1)
saver.restore(sess , 'model_data/model.ckpt')
#进行卷积操作,并添加relu激活函数
h_conv1 = tf.nn.relu(conv2d(x_img,W_conv1) + b_conv1)
#进行最大池化
h_pool1 = max_pool_2x2(h_conv1)
#同理第二层卷积层
h_conv2 = tf.nn.relu(conv2d(h_pool1,W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
#将卷积的产出展开
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
#神经网络计算,并添加relu激活函数
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1)
#输出层,使用softmax进行多分类
y_conv=tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2)
# mnist_data_set = extract_mnist.MnistDataSet('../../data/')
# x_img , y = mnist_data_set.next_train_batch(1)
im = cv2.imread('images/888.jpg',cv2.IMREAD_GRAYSCALE).astype(np.float32)
im = cv2.resize(im,(28,28),interpolation=cv2.INTER_CUBIC)
#图片预处理
#img_gray = cv2.cvtColor(im , cv2.COLOR_BGR2GRAY).astype(np.float32)
#数据从0~255转为-0.5~0.5
img_gray = (im - (255 / 2.0)) / 255
#cv2.imshow('out',img_gray)
#cv2.waitKey(0)
x_img = np.reshape(img_gray , [-1 , 784])
print x_img
output = sess.run(y_conv , feed_dict = {x:x_img})
print 'the y_con : ', '\n',output
print 'the predict is : ', np.argmax(output)
#关闭会话
sess.close()
if __name__ == '__main__':
main()
输出:
最后再贴一个cifar10的,感觉我的输入数据有点问题,因为直接读cifar10的数据测试是没问题的,但是换成自己的图片做预处理后输入结果就有问题,(参考:cv2读入的数据是BGR顺序,PIL读入的数据是RGB顺序,cifar10的数据是RGB顺序),哪位童鞋能指出来记得留言告诉我
# -*- coding:utf-8 -*-
from sys import path
import numpy as np
import tensorflow as tf
import time
import cv2
from PIL import Image
path.append('../..')
from common import extract_cifar10
from common import inspect_image
#初始化单个卷积核上的参数
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
#初始化单个卷积核上的偏置值
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
#卷积操作
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def main():
#定义会话
sess = tf.InteractiveSession()
#声明输入图片数据,类别
x = tf.placeholder('float',[None,32,32,3])
y_ = tf.placeholder('float',[None,10])
#第一层卷积层
W_conv1 = weight_variable([5, 5, 3, 64])
b_conv1 = bias_variable([64])
#进行卷积操作,并添加relu激活函数
conv1 = tf.nn.relu(conv2d(x,W_conv1) + b_conv1)
# pool1
pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1],padding='SAME', name='pool1')
# norm1
norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,name='norm1')
#第二层卷积层
W_conv2 = weight_variable([5,5,64,64])
b_conv2 = bias_variable([64])
conv2 = tf.nn.relu(conv2d(norm1,W_conv2) + b_conv2)
# norm2
norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75,name='norm2')
# pool2
pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1],strides=[1, 2, 2, 1], padding='SAME', name='pool2')
#全连接层
#权值参数
W_fc1 = weight_variable([8*8*64,384])
#偏置值
b_fc1 = bias_variable([384])
#将卷积的产出展开
pool2_flat = tf.reshape(pool2,[-1,8*8*64])
#神经网络计算,并添加relu激活函数
fc1 = tf.nn.relu(tf.matmul(pool2_flat,W_fc1) + b_fc1)
#全连接第二层
#权值参数
W_fc2 = weight_variable([384,192])
#偏置值
b_fc2 = bias_variable([192])
#神经网络计算,并添加relu激活函数
fc2 = tf.nn.relu(tf.matmul(fc1,W_fc2) + b_fc2)
#输出层,使用softmax进行多分类
W_fc2 = weight_variable([192,10])
b_fc2 = bias_variable([10])
y_conv=tf.maximum(tf.nn.softmax(tf.matmul(fc2, W_fc2) + b_fc2),1e-30)
#
saver = tf.train.Saver()
saver.restore(sess , 'model_data/model.ckpt')
#input
im = Image.open('images/dog8.jpg')
im.show()
im = im.resize((32,32))
# r , g , b = im.split()
# im = Image.merge("RGB" , (r,g,b))
print im.size , im.mode
im = np.array(im).astype(np.float32)
im = np.reshape(im , [-1,32*32*3])
im = (im - (255 / 2.0)) / 255
batch_xs = np.reshape(im , [-1,32,32,3])
#print batch_xs
#获取cifar10数据
# cifar10_data_set = extract_cifar10.Cifar10DataSet('../../data/')
# batch_xs, batch_ys = cifar10_data_set.next_train_batch(1)
# print batch_ys
output = sess.run(y_conv , feed_dict={x:batch_xs})
print output
print 'the out put is :' , np.argmax(output)
#关闭会话
sess.close()
if __name__ == '__main__':
main()