keras实现简单CNN人脸关键点检测-CSDN博客

用keras实现人脸关键点检测

改良版：http://www.cnblogs.com/ansang/p/8583122.html

第一步：准备好需要的库

tensorflow 1.4.0
h5py 2.7.0
hdf5 1.8.15.1
Keras 2.0.8
opencv-python 3.3.0
numpy 1.13.3+mkl

第二步：准备数据集：

如图：里面包含着标签和数据

第三步：将图片和标签转成numpy array格式：

 1 def __data_label__(path):
 2     f = open(path+"lable.txt", "r")
 3     i = 0
 4     datalist = []
 5     labellist = []
 6     for line in f.readlines():
 7 
 8         i+=1
 9         a = line.replace("\n", "")
10         b = a.split(",")
11         labellist.append(b[1:])
12         imgname = path + b[0]
13         image = load_img(imgname, target_size=(218, 178))
14         datalist.append(img_to_array(image))
15 
16     img_data = np.array(datalist)
17     img_data = img_data.astype('float32')
18     img_data /= 255
19     label = np.array(labellist)
20     # print(img_data)
21     return img_data,label

第四步：搭建网络：

这里使用非常简单的网络

 1 def __CNN__():
 2     model = Sequential()#218*178*3
 3     model.add(Conv2D(32, (3, 3), input_shape=(218, 178, 3)))
 4     model.add(Activation('relu'))
 5     model.add(MaxPooling2D(pool_size=(2, 2)))
 6 
 7     model.add(Conv2D(32, (3, 3)))
 8     model.add(Activation('relu'))
 9     model.add(MaxPooling2D(pool_size=(2, 2)))
10 
11     model.add(Conv2D(64, (3, 3)))
12     model.add(Activation('relu'))
13     model.add(MaxPooling2D(pool_size=(2, 2)))
14 
15     model.add(Flatten())
16     model.add(Dense(64))
17     model.add(Activation('relu'))
18     model.add(Dropout(0.5))
19     model.add(Dense(10))
20     model.add(Activation('softmax'))
21     model.summary()
22     return model

_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 216, 176, 32) 896
_________________________________________________________________
activation_1 (Activation) (None, 216, 176, 32) 0
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 108, 88, 32) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 106, 86, 32) 9248
_________________________________________________________________
activation_2 (Activation) (None, 106, 86, 32) 0
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 53, 43, 32) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 51, 41, 64) 18496
_________________________________________________________________
activation_3 (Activation) (None, 51, 41, 64) 0
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 25, 20, 64) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 32000) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 2048064
_________________________________________________________________
activation_4 (Activation) (None, 64) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 10) 650
_________________________________________________________________
activation_5 (Activation) (None, 10) 0
=================================================================
Total params: 2,077,354
Trainable params: 2,077,354
Non-trainable params: 0
_________________________________________________________________

第五步：训练保存和预测：

 1 def train(model, testdata, testlabel, traindata, trainlabel):
 2     
 3     
 4     # model.compile里的参数loss就是损失函数(目标函数)
 5     model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
 6     # 开始训练， show_accuracy在每次迭代后显示正确率 。  batch_size是每次带入训练的样本数目 ， nb_epoch 是迭代次数
 7     model.fit(traindata, trainlabel, batch_size=16, epochs=20,
 8               validation_data=(testdata, testlabel))
 9     # 设置测试评估参数，用测试集样本
10     model.evaluate(testdata, testlabel, batch_size=16, verbose=1,)
11 
12 def save(model, file_path=FILE_PATH):
13     print('Model Saved.')
14     model.save_weights(file_path)
15 
16 # def load(model, file_path=FILE_PATH):
17 #     print('Model Loaded.')
18 #     model.load_weights(file_path)
19 
20 def predict(model,image):
21 
22     img = image.resize((1, 218, 178, 3))
23     img = image.astype('float32')
24     img /= 255
25 
26     #归一化
27     result = model.predict(img)
28     result = result*1000+10
29 
30     print(result)
31     return result

第六步：主模块：

 1 ############
 2 # 主模块
 3 ############
 4 if __name__ == '__main__':
 5     model = __CNN__()
 6     testdata, testlabel = __data_label__(testpath)
 7     traindata, trainlabel = __data_label__(trainpath)
 8     # print(testlabel)
 9     # train(model,testdata, testlabel, traindata, trainlabel)
10     # model.save(FILE_PATH)
11     model.load_weights(FILE_PATH)
12     img = []
13     path = "D:/pycode/facial-keypoints-master/data/train/000096.jpg"
14     # path = "D:/pycode/Abel_Aguilar_0001.jpg"
15     image = load_img(path)
16     img.append(img_to_array(image))
17     img_data = np.array(img)
18     rects = predict(model,img_data)
19     img = cv2.imread(path)
20     for x, y, w, h, a,b,c,d,e,f in rects:
21         point(x,y)
22         point(w, h)
23         point(a,b)
24         point(c,d)
25         point(e,f)
26 
27     cv2.imshow('img', img)
28     cv2.waitKey(0)
29     cv2.destroyAllWindows()

训练的时候把train函数的注释取消

预测的时候把train函数注释掉。

下面上全代码：

  1 from tensorflow.contrib.keras.api.keras.preprocessing.image import ImageDataGenerator,img_to_array
  2 from keras.models import Sequential
  3 from keras.layers.core import Dense, Dropout, Activation, Flatten
  4 from keras.layers.advanced_activations import PReLU
  5 from keras.layers.convolutional import Conv2D, MaxPooling2D, ZeroPadding2D
  6 from keras.optimizers import SGD, Adadelta, Adagrad
  7 from keras.preprocessing.image import load_img, img_to_array
  8 from keras.utils import np_utils, generic_utils
  9 import numpy as np
 10 import cv2
 11 
 12 
 13 FILE_PATH = 'face_landmark.h5'
 14 trainpath = 'D:/pycode/facial-keypoints-master/data/train/'
 15 testpath = 'D:/pycode/facial-keypoints-master/data/test/'
 16 
 17 def __data_label__(path):
 18     f = open(path+"lable.txt", "r")
 19     i = 0
 20     datalist = []
 21     labellist = []
 22     for line in f.readlines():
 23 
 24         i+=1
 25         a = line.replace("\n", "")
 26         b = a.split(",")
 27         labellist.append(b[1:])
 28         imgname = path + b[0]
 29         image = load_img(imgname, target_size=(218, 178))
 30         datalist.append(img_to_array(image))
 31 
 32     img_data = np.array(datalist)
 33     img_data = img_data.astype('float32')
 34     img_data /= 255
 35     label = np.array(labellist)
 36     # print(img_data)
 37     return img_data,label
 38 
 39 ###############
 40 # 开始建立CNN模型
 41 ###############
 42 
 43 # 生成一个model
 44 
 45 def __CNN__():
 46     model = Sequential()#218*178*3
 47     model.add(Conv2D(32, (3, 3), input_shape=(218, 178, 3)))
 48     model.add(Activation('relu'))
 49     model.add(MaxPooling2D(pool_size=(2, 2)))
 50 
 51     model.add(Conv2D(32, (3, 3)))
 52     model.add(Activation('relu'))
 53     model.add(MaxPooling2D(pool_size=(2, 2)))
 54 
 55     model.add(Conv2D(64, (3, 3)))
 56     model.add(Activation('relu'))
 57     model.add(MaxPooling2D(pool_size=(2, 2)))
 58 
 59     model.add(Flatten())
 60     model.add(Dense(64))
 61     model.add(Activation('relu'))
 62     model.add(Dropout(0.5))
 63     model.add(Dense(10))
 64      65     model.summary()
 66     return model
 67 
 68 def train(model, testdata, testlabel, traindata, trainlabel):
 69     
 70     
 71     # model.compile里的参数loss就是损失函数(目标函数)
 72     model.compile(loss='categorical_crossentropy', optimizer='adam')
 73     # 开始训练， show_accuracy在每次迭代后显示正确率 。  batch_size是每次带入训练的样本数目 ， nb_epoch 是迭代次数
 74     model.fit(traindata, trainlabel, batch_size=16, epochs=20,
 75               validation_data=(testdata, testlabel))
 76     # 设置测试评估参数，用测试集样本
 77     model.evaluate(testdata, testlabel, batch_size=16, verbose=1,)
 78 
 79 def save(model, file_path=FILE_PATH):
 80     print('Model Saved.')
 81     model.save_weights(file_path)
 82 
 83 # def load(model, file_path=FILE_PATH):
 84 #     print('Model Loaded.')
 85 #     model.load_weights(file_path)
 86 
 87 def predict(model,image):
 88     
 89     img = image.resize((1, 218, 178, 3))
 90     img = image.astype('float32')
 91     img /= 255
 92 
 93     #归一化
 94     result = model.predict(img)
 95     result = result*1000+10
 96 
 97     print(result)
 98     return result
 99 def point(x, y):
100     cv2.circle(img, (x, y), 1, (0, 0, 255), 10)
101 
102 ############
103 # 主模块
104 ############
105 if __name__ == '__main__':
106     model = __CNN__()
107     testdata, testlabel = __data_label__(testpath)
108     traindata, trainlabel = __data_label__(trainpath)
109     # print(testlabel)
110     # train(model,testdata, testlabel, traindata, trainlabel)
111     # model.save(FILE_PATH)
112     model.load_weights(FILE_PATH)
113     img = []
114     path = "D:/pycode/facial-keypoints-master/data/train/000096.jpg"
115     # path = "D:/pycode/Abel_Aguilar_0001.jpg"
116     image = load_img(path)
117     img.append(img_to_array(image))
118     img_data = np.array(img)
119     rects = predict(model,img_data)
120     img = cv2.imread(path)
121     for x, y, w, h, a,b,c,d,e,f in rects:
122         point(x,y)
123         point(w, h)
124         point(a,b)
125         point(c,d)
126         point(e,f)
127 
128     cv2.imshow('img', img)
129     cv2.waitKey(0)
130     cv2.destroyAllWindows()

结果如下：

未来计划：

用tensorflow-cpu跑的，数据量很少，网络很简单，提升数据量和网络深度应该还能有较大的改善空间。

而且目前网络只能预测大小为（218，178）像素的图片，将适用性提升是未来的目标。

改进方案：

将图片全部resize成方形，边长不够的加黑边补齐。

 1 # 按照指定图像大小调整尺寸
 2 def resize_image(image, height=IMAGE_SIZE, width=IMAGE_SIZE):
 3     top, bottom, left, right = (0, 0, 0, 0)
 4 
 5     # 获取图像尺寸
 6     h, w, _ = image.shape
 7 
 8     # 对于长宽不相等的图片，找到最长的一边
 9     longest_edge = max(h, w)
10 
11     # 计算短边需要增加多上像素宽度使其与长边等长
12     if h < longest_edge:
13         dh = longest_edge - h
14         top = dh // 2
15         bottom = dh - top
16     elif w < longest_edge:
17         dw = longest_edge - w
18         left = dw // 2
19         right = dw - left
20     else:
21         pass
22 
23         # RGB颜色
24     BLACK = [0, 0, 0]
25 
26     # 给图像增加边界，是图片长、宽等长，cv2.BORDER_CONSTANT指定边界颜色由value指定
27     constant = cv2.copyMakeBorder(image, top, bottom, left, right, cv2.BORDER_CONSTANT, value=BLACK)
28 
29     # 调整图像大小并返回
30     return cv2.resize(constant, (height, width))