正文共6736个字，5张图，预计阅读时间17分钟。

01

概述

02

数据准备

# -*- coding:utf-8 -*-
 # 录像转换为图片
from time import gmtime, strftime
import cv2
videoFile = '/media/kingstar/kingstardata/safety_eyes/nohatdata/7.mp4'
cap = cv2.VideoCapture(videoFile)
cap.set(3,640)
cap.set(4,480)
 while(True):    
ret, frame = cap.read()    
img = frame    
cv2.imshow('my', img)    
f = strftime("%Y%m%d%H%M%S.jpg", gmtime())    
cv2.imwrite('output/'+ f, img)  
if cv2.waitKey(1) & 0xFF == ord('q'):        
break  
 if img.size == 0:        
break
cap.release
cv2.destroyAllWindows()

# -*-coding: utf-8-*-
from keras.preprocessing import image
from keras.applications.imagenet_utils
import preprocess_input from scipy.misc
import imread
import numpy as np
from ssd import SSD300
from ssd_utils import BBoxUtility
import matplotlib.pyplot as plt
import cv2
from os import listdir
 voc_classes = ['Aeroplane', 'Bicycle', 'Bird', 'Boat', 'Bottle',              
 'Bus', 'Car', 'Cat', 'Chair', 'Cow', 'Diningtable',              
 'Dog', 'Horse','Motorbike', 'Person', 'Pottedplant',              
 'Sheep', 'Sofa', 'Train', 'Tvmonitor']
NUM_CLASSES = len(voc_classes) + 1
input_shape=(300, 300, 3)
model = SSD300(input_shape, num_classes=NUM_CLASSES) model.load_weights('weights_SSD300.hdf5', by_name=True)
bbox_util = BBoxUtility(NUM_CLASSES)
 def ssd(img_path):    
global oPath    
inputs = []    
images = []    
#img_path = 'test02.jpg'    
img0 = cv2.imread(img_path)    
img = image.load_img(img_path, target_size=(300, 300))    
img = image.img_to_array(img)  
 images.append(imread(img_path))    
inputs.append(img.copy())    
inputs = preprocess_input(np.array(inputs))    
preds = model.predict(inputs, batch_size=1, verbose=1)    
results = bbox_util.detection_out(preds)    
#print results    
# Parse the outputs.    
for i, img in enumerate(images):        
det_label = results[i][:, 0]        
det_conf = results[i][:, 1]        
det_xmin = results[i][:, 2]        
det_ymin = results[i][:, 3]        
det_xmax = results[i][:, 4]        
det_ymax = results[i][:, 5]        
#print i,det_label,det_conf        
# Get detections with confidence higher than 0.6.        
top_indices = [i for i, conf in enumerate(det_conf) if conf >= 0.5]        
top_conf = det_conf[top_indices]        
top_label_indices = det_label[top_indices].tolist()        
top_xmin = det_xmin[top_indices]        
top_ymin = det_ymin[top_indices]        
top_xmax = det_xmax[top_indices]        
top_ymax = det_ymax[top_indices]      
 #colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()        
#plt.imshow(img / 255.)        
#currentAxis = plt.gca()        
#print top_label_indices        
#print top_conf        
#print top_conf.shape[0]        
for i0 in range(top_conf.shape[0]):            
xmin = int(round(top_xmin[i0] * img.shape[1]))

ymin = int(round(top_ymin[i0] * img.shape[0]))            
xmax = int(round(top_xmax[i0] * img.shape[1]))            
ymax = int(round(top_ymax[i0] * img.shape[0]))

score = top_conf[i0]          
 label = int(top_label_indices[i0])            
label_name = voc_classes[label - 1]            
#display_txt = '{:0.2f}, {}'.format(score, label_name)            
#coords = (xmin, ymin), xmax-xmin+1, ymax-ymin+1            
#color = colors[label]            
#currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2))            
#currentAxis.text(xmin, ymin, display_txt, bbox={'facecolor':color, 'alpha':0.5})            print label_name,score,xmin,ymin,xmax,ymax            
fileStr0 = img_path.split('.')[-2]            
fileStr0 = fileStr0.split('/')[-1]            
if label_name == 'Person':                
fileStr = '%s/Person5/%s.%d.jpg' %(oPath,fileStr0,i0+1)                
im = img0[ymin:ymax,xmin:xmax]                
r = cv2.imwrite(fileStr,im)                
print 'Person0',fileStr            
if label_name == 'Car1' or label_name == 'Motorbike1':                
fileStr = '%s/Car/%s.%d.jpg' %(oPath,fileStr0,i0+1)                
im = img0[ymin:ymax,xmin:xmax]                
r = cv2.imwrite(fileStr,im)                
print 'Car0',fileStr        
#plt.show()        
#cv2.imshow('im', im)        
#cv2.waitKey(0) if __name__ == "__main__":    img_path = 'test02.jpg'    
mPath = '/media/kingstar/kingstardata/safety_eyes/baidu5'    
oPath = '/media/kingstar/kingstardata/safety_eyes/out'    
trainFileList = listdir(mPath)    
m =len(trainFileList)    
print m    
for i in range(m):        
fileNameStr = trainFileList[i]        
fileStr = fileNameStr.split('.')[-2]        
print i,fileNameStr,fileStr

fileNameStr = '%s/%s' % (mPath,fileNameStr)        
print 'step:%d/%d' % (i,m)        
ssd(fileNameStr)

03

搭建模型

model = Sequential() model.add(Convolution2D(32, 3, 3, input_shape=( img_width, img_height, 3))) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(64, 3, 3)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(64, 3, 3)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Flatten()) model.add(Dense(64)) model.add(Activation('relu')) model.add(Dropout(0.5)) model.add(Dense(1)) model.add(Activation('sigmoid')) model.compile(loss='binary_crossentropy',              optimizer='rmsprop',              metrics=['accuracy'])

04

训练神经网络

# -*-coding: utf-8-*-
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Convolution2D, MaxPooling2D
from keras.layers
import Activation, Dropout, Flatten, Dense
 # dimensions of our images.
img_width, img_height = 128, 128
 train_data_dir = '/media/kingstar/kingstardata/data/train'
validation_data_dir = '/media/kingstar/kingstardata/data/test'
nb_train_samples = 4000
nb_validation_samples = 800
nb_epoch = 60 model = Sequential()
model.add(Convolution2D(32, 3, 3, input_shape=( img_width, img_height, 3))) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(64, 3, 3)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Convolution2D(64, 3, 3)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Flatten()) model.add(Dense(64)) model.add(Activation('relu')) model.add(Dropout(0.5)) model.add(Dense(1)) model.add(Activation('sigmoid')) model.compile(loss='binary_crossentropy',              
optimizer='rmsprop',              
metrics=['accuracy'])
train_datagen = ImageDataGenerator(        rescale=1./255,        
shear_range=0.2,        
zoom_range=0.2,        
horizontal_flip=True)
 test_datagen = ImageDataGenerator(rescale=1./255)
 train_generator = train_datagen.flow_from_directory(        
train_data_dir,        
target_size=(img_width, img_height),        
batch_size=32,      
 class_mode='binary')
 validation_generator = test_datagen.flow_from_directory(        
validation_data_dir,        
target_size=(img_width, img_height),        
batch_size=32,        
class_mode='binary')
 model.fit_generator(        
train_generator,        
samples_per_epoch=nb_train_samples,        
nb_epoch=nb_epoch,        
validation_data=validation_generator,        
nb_val_samples=nb_validation_samples)

model.save('trianHat12801.h5')

05

结论