本例:为使用ssd模型对行人数据集进行标注 提取行人坐标信息,提取的结果好坏取决于使用的模型的好坏.需要手动指定保存的类别,修改第129行,图片格式指定在127行
#encoding=utf8
import os
import sys
import argparse,time
import numpy as np
import cv2
# Make sure that caffe is on the python path:
caffe_root = '/home/caffe-ssd'
sys.path.insert(0, os.path.join(caffe_root, 'python'))
#os.environ['GLOG_minloglevel'] = '2' # 将caffe的输出log信息不显示,必须放到import caffe前
import caffe
from google.protobuf import text_format
from caffe.proto import caffe_pb2
from tqdm import tqdm
#read name from labelmap.prototxt
def get_labelname(labelmap, labels):
num_labels = len(labelmap.item)
labelnames = []
if type(labels) is not list:
labels = [labels]
for label in labels:
found = False
for i in range(0, num_labels):
if label == labelmap.item[i].label:
found = True
labelnames.append(labelmap.item[i].display_name)
break
assert found == True
return labelnames
class CaffeDetection:
def __init__(self, model_def, model_weights, image_resize, labelmap_file):
#switch mode:cpu/gpu
caffe.set_device(0)
caffe.set_mode_gpu()
#caffe.set_mode_cpu()
self.image_resize = image_resize
# Load the net in the test phase for inference, and configure input preprocessing.
self.net = caffe.Net(model_def, # defines the structure of the model
model_weights, # contains the trained weights
caffe.TEST) # use test mode (e.g., don't perform dropout)
# input preprocessing: 'data' is the name of the input blob == net.inputs[0]
# load PASCAL VOC labels
file = open(labelmap_file, 'r')
self.labelmap = caffe_pb2.LabelMap()
text_format.Merge(str(file.read()), self.labelmap)
def detect(self, image, conf_thresh=0.7, topn=3):
'''
SSD detection
'''
# set net to batch size of 1
# image_resize = 300
self.net.blobs['data'].reshape(1, 3, self.image_resize, self.image_resize)
#Run the net and examine the top_k results
image = cv2.resize(image,(self.image_resize, self.image_resize))
#image *= 255#[0,1]->0,255
image1 = np.asarray(image,np.float32)
image1 -= [127.5]
image1 *= 0.007843
#RGB-->BGR
#image1 = image1[:, :, (2, 1, 0)]
#[high,weight,channels] --> [channels,high,weight]
image1 = image1.transpose(2,0,1)
#obtain the machine time
now = time.time()
self.net.blobs['data'].data[...] = image1
# Forward pass.
detections = self.net.forward()['detection_out']
#print('inference time:',time.time() - now) #time
# Parse the outputs.
det_label = detections[0,0,:,1]
det_conf = detections[0,0,:,2]
det_xmin = detections[0,0,:,3]
det_ymin = detections[0,0,:,4]
det_xmax = detections[0,0,:,5]
det_ymax = detections[0,0,:,6]
# Get detections with confidence higher than 0.6.
top_indices = [i for i, conf in enumerate(det_conf) if conf >= conf_thresh]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_labels = get_labelname(self.labelmap, top_label_indices)
top_xmin = det_xmin[top_indices]
top_ymin = det_ymin[top_indices]
top_xmax = det_xmax[top_indices]
top_ymax = det_ymax[top_indices]
result = []
for i in range(min(topn, top_conf.shape[0])):
xmin = top_xmin[i] # xmin = int(round(top_xmin[i] * image.shape[1]))
ymin = top_ymin[i] # ymin = int(round(top_ymin[i] * image.shape[0]))
xmax = top_xmax[i] # xmax = int(round(top_xmax[i] * image.shape[1]))
ymax = top_ymax[i] # ymax = int(round(top_ymax[i] * image.shape[0]))
score = top_conf[i]
label = int(top_label_indices[i])
label_name = top_labels[i]
result.append([xmin, ymin, xmax, ymax, label, score, label_name])
return result
def main(args):
'''main '''
detection = CaffeDetection(args.model_def, args.model_weights,
args.image_resize, args.labelmap_file)
#traverse folder args.image
imagefile_list = os.listdir(args.image)
for image_name in tqdm(imagefile_list):
#print(image_name)
#create path of each image
image_path=os.path.join(args.image,image_name)
frame = cv2.imread(image_path)
#detect the input-image
result = detection.detect(frame,conf_thresh=0.7)
#obtain the input-image's width and height
height = frame.shape[0]
width = frame.shape[1]
#continue if no result is found
if len(result) == 0:
continue
#create information file for each image
fout=open(os.path.join(args.txt,image_name.replace('.jpg','.txt')),'w')
for item in result:
if item[-1] not in ['person',]:
continue
xmin = int(round(item[0] * width)) #the x-intercept of top left corner
ymin = int(round(item[1] * height)) #the y-intercept of top left corner
xmax = int(round(item[2] * width)) #the x-intercept of bottom right corner
ymax = int(round(item[3] * height)) #the y-intercept of bottom right corner
fout.write("%s %d %d %d %d\n"%(item[-1],xmin,ymin,xmax,ymax)) #write the label and coordinate of boundingbox
fout.close()
def parse_args():
'''parse args'''
parser = argparse.ArgumentParser()
parser.add_argument('--labelmap_file','-lf',
default=None)
parser.add_argument('--model_def','-md',
default=None)
parser.add_argument('--image_resize', '-ir',default=300, type=int)
parser.add_argument('--model_weights','-mw',
default=None)
parser.add_argument('--image','-im',
default=None,help='image path to read')
parser.add_argument('--txt','-t',type=str,
default='None',help='txt path to save')
return parser.parse_args()
if __name__ == '__main__':
args = parse_args()
#exit if either of them is not found
if args.labelmap_file == None or args.model_def == None or args.model_weights == None:
exit(0)
main(args)