tensorflow识别图片数字

import tensorflow as tf from PIL import Image, ImageFilter import tensorflow as tf import matplotlib.pyplot as plt import cv2 import numpy as np def inside(r1, r2): """判断r1是否在r2里面""" x1, y1, w1, h1 = r1 x2, y2, w2, h2 = r2 if (x1 >= x2) and (y1 >= y2) and (x1 + w1 <= x2 + w2) and (y1 + h1 <= y2 + h2): return True else: return False def wrap_digit(rect): """扩大矩形范围""" x, y, w, h = rect padding = 5 hcenter = x + w / 2 vcenter = y + h / 2 if (h > w): w = h x = hcenter - (w / 2) else: h = w y = vcenter - (h / 2) return (x - padding, y - padding, w + padding, h + padding) def imageprepare(path): """ This function returns the pixel values. The imput is a png file location. """ # file_name='./images/3.png'#导入自己的图片地址 file_name = path #in terminal 'mogrify -format png *.jpg' convert jpg to png im = Image.open(file_name).convert('L') # im.save("./image/sample.png") # plt.imshow(im) # plt.show() tv = list(im.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] # print(tva) return tva # 创建两个占位符，x为输入网络的图像，y_为输入网络的图像类别,None表示此张量的第一个维度可以是任何长度的 x_ = tf.placeholder("float", shape=[None, 784]) # y_ = tf.placeholder("float", shape=[None, 10]) # 权重初始化函数 def weight_variable(shape): # 输出服从截尾正态分布的随机值 initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) # 偏置初始化函数 def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial) # 创建卷积op # x 是一个4维张量，shape为[batch,height,width,channels] # 卷积核移动步长为1。填充类型为SAME,可以不丢弃任何像素点 def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding="SAME") # 创建池化op # 采用最大池化，也就是取窗口中的最大值作为结果 # x 是一个4维张量，shape为[batch,height,width,channels] # ksize表示pool窗口大小为2x2,也就是高2，宽2 # strides，表示在height和width维度上的步长都为2 def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME") # 第1层，卷积层 # 初始化W为[5,5,1,32]的张量，表示卷积核大小为5*5，第一层网络的输入和输出神经元个数分别为1和32 W_conv1 = weight_variable([5, 5, 1, 32]) # 初始化b为[32],即输出大小 b_conv1 = bias_variable([32]) # 把输入x(二维张量,shape为[batch, 784])变成4d的x_image，x_image的shape应该是[batch,28,28,1] # -1表示自动推测这个维度的size x_image = tf.reshape(x_, [-1, 28, 28, 1]) # 把x_image和权重进行卷积，加上偏置项，然后应用ReLU激活函数，最后进行max_pooling # h_pool1的输出即为第一层网络输出，shape为[batch,14,14,1] h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) # 第2层，卷积层 # 卷积核大小依然是5*5，这层的输入和输出神经元个数为32和64 W_conv2 = weight_variable([5, 5, 32, 64]) b_conv2 = weight_variable([64]) # h_pool2即为第二层网络输出，shape为[batch,7,7,1] h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2) # 第3层, 全连接层 # 这层是拥有1024个神经元的全连接层 # W的第1维size为7*7*64，7*7是h_pool2输出的size，64是第2层输出神经元个数 W_fc1 = weight_variable([7 * 7 * 64, 1024]) b_fc1 = bias_variable([1024]) # 计算前需要把第2层的输出reshape成[batch, 7*7*64]的张量 h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) # Dropout层 # 为了减少过拟合，在输出层前加入dropout keep_prob = tf.placeholder("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) # 输出层 # 最后，添加一个softmax层 # 可以理解为另一个全连接层，只不过输出时使用softmax将网络输出值转换成了概率 W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) #tf.nn.softmax函数默认（dim=-1）是对张量最后一维的shape=(p,)向量进行softmax计算，得到一个概率向量。 y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) # 数据保存器的初始化 saver = tf.train.Saver() font = cv2.FONT_HERSHEY_SIMPLEX path = "numbers.jpg" img = cv2.imread(path, cv2.IMREAD_UNCHANGED) bw = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) #高斯模糊 bw = cv2.GaussianBlur(bw, (7, 7), 0) #简单阈值，选取一个全局阈值，然后就把整幅图像分成了非黑即白的二值图像了 ret, thbw = cv2.threshold(bw, 127, 255, cv2.THRESH_BINARY_INV) #腐蚀图像 thbw = cv2.erode(thbw, np.ones((2, 2), np.uint8), iterations=2) #cv2.findContours()函数返回两个值,一个是轮廓本身,还有一个是每条轮廓对应的属性。 image, cntrs, hier = cv2.findContours(thbw.copy(), cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE) rectangles = [] for i,c in enumerate(cntrs): #用一个最小的矩形，把找到的形状包起来 r = x, y, w, h = cv2.boundingRect(c) # 轮廓面积 a = cv2.contourArea(c) #img.shape 显示尺寸,img.shape[0] 图片宽度,img.shape[1] 图片高度,img.shape[2] 图片通道数 #img.size 显示总像素个数,img.max() 最大像素值,img.mean() 像素平均值 b = (img.shape[0] - 3) * (img.shape[1] - 3) is_inside = False for j,q in enumerate(rectangles): if inside(r, q): is_inside = True break if inside(q, r): rectangles.remove(q) pass if not is_inside: if not a == b: rectangles.append(r) with tf.Session() as sess: # 初始化变量 sess.run(tf.initialize_all_variables()) #恢复模型 路径写自己的 saver.restore(sess, r'D:\python_work\other\tensorflow\model\train_faces.model') accuracy = tf.argmax(y_conv, 1) i = 0 for r in rectangles: i = i + 1 x, y, w, h = wrap_digit(r) # TypeError: integer argument expected, got float x = int(x) y = int(y) w = int(w) h = int(h) if x < 0: x = 0 if y < 0: y = 0 cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2) roi = img[y:y + h, x:x + w] roi = cv2.resize(roi, (28,28)) cv2.imwrite("test.png",roi) result = imageprepare("test.png") predint = accuracy.eval(feed_dict={x_: [result], keep_prob: 1.0}, session=sess) # print('recognize result:',predint[0]) cv2.putText(img, "%d" % predint, (x, y - 1), font, 1, (0, 255, 0)) cv2.imshow("thbw", thbw) cv2.imshow("contours", img) cv2.imwrite("sample02.jpg", img) cv2.waitKey()