用keras实现人脸关键点检测(2)
上一个代码只能实现小数据的读取与训练，在大数据训练的情况下。会造内存紧张，于是我根据keras的官方文档，对上一个代码进行了改进。
用keras实现人脸关键点检测
数据集：https://pan.baidu.com/s/1cnAxJJmN9nQUVYj8w0WocA
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：
我对每一张图像进行了剪裁，使图像的大小为178*178的正方形。
并且对于原有的lable进行了优化
第三步：将图片和标签转成numpy array格式：
参数
1 trainpath = 'E:/pycode/facial-keypoints-master/data/50000train/' 2 testpath = 'E:/pycode/facial-keypoints-master/data/50000test/' 3 imgsize = 178 4 train_samples =40000 5 test_samples = 200 6 batch_size = 32
1 def __data_label__(path): 2 f = open(path + "lable-40.txt", "r") 3 j = 0 4 i = -1 5 datalist = [] 6 labellist = [] 7 while True: 8 9 for line in f.readlines(): 10 i += 1 11 j += 1 12 a = line.replace("\n", "") 13 b = a.split(",") 14 lable = b[1:] 15 # print(b[1:]) 16 #对标签进行归一化（不归一化也行） 17 # for num in b[1:]: 18 # lab = int(num) / 255.0 19 # labellist.append(lab) 20 # lab = labellist[i * 10:j * 10] 21 imgname = path + b[0] 22 images = load_img(imgname) 23 images = img_to_array(images).astype('float32') 24 # 对图片进行归一化（不归一化也行） 25 # images /= 255.0 26 image = np.expand_dims(images, axis=0) 27 lables = np.array(lable) 28 29 # lable =keras.utils.np_utils.to_categorical(lable) 30 # lable = np.expand_dims(lable, axis=0) 31 lable = lables.reshape(1, 10) 32 #这里使用了生成器 33 yield (image,lable)
第四步：搭建网络：
这里使用非常简单的网络
1 def __CNN__(self): 2 model = Sequential()#178*178*3 3 model.add(Conv2D(32, (3, 3), input_shape=(imgsize, imgsize, 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 return model 21 #因为是回归问题，抛弃了softmax
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 176, 176, 32) 896
_________________________________________________________________
activation_1 (Activation) (None, 176, 176, 32) 0
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 88, 88, 32) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 86, 86, 32) 9248
_________________________________________________________________
activation_2 (Activation) (None, 86, 86, 32) 0
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 43, 43, 32) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 41, 41, 64) 18496
_________________________________________________________________
activation_3 (Activation) (None, 41, 41, 64) 0
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 20, 20, 64) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 25600) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1638464
_________________________________________________________________
activation_4 (Activation) (None, 64) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 10) 650
=================================================================
Total params: 1,667,754
Trainable params: 1,667,754
Non-trainable params: 0
_________________________________________________________________
第五步：训练网络：
1 def train(model): 2 # print(lable.shape) 3 model.compile(loss='mse', optimizer='adam') 4 # optimizer = SGD(lr=0.03, momentum=0.9, nesterov=True) 5 # model.compile(loss='mse', optimizer=optimizer, metrics=['accuracy']) 6 epoch_num = 14 7 learning_rate = np.linspace(0.03, 0.01, epoch_num) 8 change_lr = LearningRateScheduler(lambda epoch: float(learning_rate[epoch])) 9 early_stop = EarlyStopping(monitor='val_loss', patience=20, verbose=1, mode='auto') 10 check_point = ModelCheckpoint('CNN_model_final.h5', monitor='val_loss', verbose=0, save_best_only=True, 11 save_weights_only=False, mode='auto', period=1) 12 13 model.fit_generator(__data_label__(trainpath),callbacks=[check_point,early_stop,change_lr],samples_per_epoch=int(train_samples // batch_size), 14 epochs=epoch_num,validation_steps = int(test_samples // batch_size),validation_data=__data_label__(testpath)) 15 16 # model.fit(traindata, trainlabel, batch_size=32, epochs=50, 17 # validation_data=(testdata, testlabel)) 18 model.evaluate_generator(__data_label__(testpath),steps=10) 19 20 def save(model, file_path=FILE_PATH): 21 print('Model Saved.') 22 model.save_weights(file_path) 23 24 25 def predict(model,image): 26 # 预测样本分类 27 image = cv2.resize(image, (imgsize, imgsize)) 28 image.astype('float32') 29 image /= 255 30 31 #归一化 32 result = model.predict(image) 33 result = result*1000+20 34 35 print(result) 36 return result
使用了fit_generator这一方法，加入了learning_rate,LearningRateScheduler,early_stop等参数。
第六步：图像验证
1 import tes_main 2 from keras.preprocessing.image import load_img, img_to_array 3 import numpy as np 4 import cv2 5 FILE_PATH = 'E:\\pycode\\facial-keypoints-master\\code\\CNN_model_final.h5' 6 imgsize =178 7 def point(img,x, y): 8 cv2.circle(img, (x, y), 1, (0, 0, 255), 10) 9 10 Model = tes_main.Model() 11 model = Model.__CNN__() 12 Model.load(model,FILE_PATH) 13 img = [] 14 # path = "D:\\Users\\a\\Pictures\\face_landmark_data\data\\test\\000803.jpg" 15 path = "E:\pycode\\facial-keypoints-master\data\\50000test\\049971.jpg" 16 # image = load_img(path) 17 # img.append(img_to_array(image)) 18 # img_data = np.array(img) 19 imgs = cv2.imread(path) 20 # img_datas = np.reshape(imgs,(imgsize, imgsize,3)) 21 image = cv2.resize(imgs, (imgsize, imgsize)) 22 rects = Model.predict(model,imgs) 23 24 for x, y, w, h, a,b,c,d,e,f in rects: 25 point(image,x,y) 26 point(image,w, h) 27 point(image,a,b) 28 point(image,c,d) 29 point(image,e,f) 30 31 cv2.imshow('img', image) 32 cv2.waitKey(0) 33 cv2.destroyAllWindows()
完整代码如下
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.preprocessing.image import load_img, img_to_array 7 from keras.optimizers import SGD 8 import numpy as np 9 import cv2 10 from keras.callbacks import * 11 import keras 12 13 FILE_PATH = 'E:\\pycode\\facial-keypoints-master\\code\\CNN_model_final.h5' 14 trainpath = 'E:/pycode/facial-keypoints-master/data/50000train/' 15 testpath = 'E:/pycode/facial-keypoints-master/data/50000test/' 16 imgsize = 178 17 train_samples =40000 18 test_samples = 200 19 batch_size = 32 20 def __data_label__(path): 21 f = open(path + "lable-40.txt", "r") 22 j = 0 23 i = -1 24 datalist = [] 25 labellist = [] 26 while True: 27 28 for line in f.readlines(): 29 i += 1 30 j += 1 31 a = line.replace("\n", "") 32 b = a.split(",") 33 lable = b[1:] 34 # print(b[1:]) 35 #对标签进行归一化（不归一化也行） 36 # for num in b[1:]: 37 # lab = int(num) / 255.0 38 # labellist.append(lab) 39 # lab = labellist[i * 10:j * 10] 40 imgname = path + b[0] 41 images = load_img(imgname) 42 images = img_to_array(images).astype('float32') 43 # 对图片进行归一化（不归一化也行） 44 # images /= 255.0 45 image = np.expand_dims(images, axis=0) 46 lables = np.array(lable) 47 48 # lable =keras.utils.np_utils.to_categorical(lable) 49 # lable = np.expand_dims(lable, axis=0) 50 lable = lables.reshape(1, 10) 51 52 yield (image,lable) 53 54 ###############: 55 56 # 开始建立CNN模型 57 ############### 58 59 # 生成一个model 60 class Model(object): 61 def __CNN__(self): 62 model = Sequential()#218*178*3 63 model.add(Conv2D(32, (3, 3), input_shape=(imgsize, imgsize, 3))) 64 model.add(Activation('relu')) 65 model.add(MaxPooling2D(pool_size=(2, 2))) 66 67 model.add(Conv2D(32, (3, 3))) 68 model.add(Activation('relu')) 69 model.add(MaxPooling2D(pool_size=(2, 2))) 70 71 model.add(Conv2D(64, (3, 3))) 72 model.add(Activation('relu')) 73 model.add(MaxPooling2D(pool_size=(2, 2))) 74 75 model.add(Flatten()) 76 model.add(Dense(64)) 77 model.add(Activation('relu')) 78 model.add(Dropout(0.5)) 79 model.add(Dense(10)) 80 model.summary() 81 return model 82 83 84 def train(self,model): 85 # print(lable.shape) 86 model.compile(loss='mse', optimizer='adam', metrics=['accuracy']) 87 # optimizer = SGD(lr=0.03, momentum=0.9, nesterov=True) 88 # model.compile(loss='mse', optimizer=optimizer, metrics=['accuracy']) 89 epoch_num = 10 90 learning_rate = np.linspace(0.03, 0.01, epoch_num) 91 change_lr = LearningRateScheduler(lambda epoch: float(learning_rate[epoch])) 92 early_stop = EarlyStopping(monitor='val_loss', patience=20, verbose=1, mode='auto') 93 check_point = ModelCheckpoint('CNN_model_final.h5', monitor='val_loss', verbose=0, save_best_only=True, 94 save_weights_only=False, mode='auto', period=1) 95 96 model.fit_generator(__data_label__(trainpath),callbacks=[check_point,early_stop,change_lr],samples_per_epoch=int(train_samples // batch_size), 97 epochs=epoch_num,validation_steps = int(test_samples // batch_size),validation_data=__data_label__(testpath)) 98 99 # model.fit(traindata, trainlabel, batch_size=32, epochs=50, 100 # validation_data=(testdata, testlabel)) 101 model.evaluate_generator(__data_label__(testpath)) 102 103 def save(self,model, file_path=FILE_PATH): 104 print('Model Saved.') 105 model.save_weights(file_path) 106 107 def load(self,model, file_path=FILE_PATH): 108 print('Model Loaded.') 109 model.load_weights(file_path) 110 111 def predict(self,model,image): 112 # 预测样本分类 113 print(image.shape) 114 image = cv2.resize(image, (imgsize, imgsize)) 115 image.astype('float32') 116 image = np.expand_dims(image, axis=0) 117 118 #归一化 119 result = model.predict(image) 120 121 print(result) 122 return result