def main():
# 创建一个解析器对象，并告诉它将会有些什么参数。当程序运行时，该解析器就可以用于处理命令行参数。
parser = argparse.ArgumentParser()
# 定义参数
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
# 定义了所有参数之后，你就可以给 parse_args() 传递一组参数字符串来解析命令行。默认情况下，参数是从 sys.argv[1:] 中获取
# parse_args() 的返回值是一个命名空间，包含传递给命令的参数。该对象将参数保存其属性
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu # 设置环境变量
yolo = YOLONet(False) # 创建YOLO网络对象
weight_file = os.path.join(args.data_dir, args.weight_dir,
args.weights) # 加载检查点文件
detector = Detector(yolo, weight_file) # 创建测试对象
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
# imname = 'test/person.jpg'
# detector.image_detector(imname)
# detect from camera
# GTX 1060 25FPS
detector.camera_detector()
def main():
'''
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
'''
datautil = MyDataUtil('DIYdata', 'test')
yolo = YOLONet(False)
#weight_file = os.path.join('DIYdata', 'output/V3', 'yolo.ckpt')
#detector = Detector(yolo, weight_file)
#weight_dir = os.path.join('DIYdata', 'output/V3', 'yolo.ckpt')
#detector = Detector(yolo, weight_dir=weight_dir)
detector = Detector(
yolo,
weight_file=
'/home/wlk/Develop/gitDownload/yolo_tensorflow/data/YOLO_small.ckpt')
# detect from camera
cap = cv2.VideoCapture(-1)
detector.camera_detector(cap)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="D:\\reference\\5-dataset\\YOLO_small.ckpt", type=str) # 预训练的数据集
parser.add_argument('--data_dir', default="D:\\reference\\5-dataset", type=str) # voc数据集文件夹pascal_voc所在路径
parser.add_argument('--threshold', default=0.2, type=float) # 格子有目标的置信度阈值
parser.add_argument('--iou_threshold', default=0.5, type=float)
parser.add_argument('--gpu', default='0', type=str)
args = parser.parse_args()
if args.gpu is not None:
cfg.GPU = args.gpu
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU # 获取系统环境变量
yolo = YOLONet()
pascal = pascal_voc('train')
solver = Solver(yolo, pascal)
print('Start training ...')
solver.train()
print('Done training.')
def main(): #自定义参数
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt",
type=str) #定义权重文件
parser.add_argument('--data_dir', default="data", type=str) #定义数据文件夹
parser.add_argument('--threshold', default=0.2, type=float) #阈值
parser.add_argument('--iou_threshold', default=0.5, type=float) #IOU阈值
parser.add_argument('--gpu', default='', type=str) #是否用gpu训练
args = parser.parse_args()
if args.gpu is not None: #是否用gpu训练
cfg.GPU = args.gpu
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
yolo = YOLONet() #Yolo网络
pascal = pascal_voc('train') #获得训练的数据， 包含了经过水平翻转后的训练实例
solver = Solver(yolo, pascal) #准备训练的环境，包括设置优化器，学习率等内容
print('Start training ...')
solver.train() #start training
print('done!!!')
def main():
parser = argparse.ArgumentParser()
# parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weights', default="yolo-1000.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
# imname = 'test/person.jpg'
imname = 'data/test_jpg/CAM01-2014-02-15-20140215161032-20140215162620-frame415.jpg'
# imname = 'data/test_jpg/CAM01-2014-02-20-20140220170007-20140220171314-frame4700.jpg'
detector.image_detector(imname)
def main():
parser = argparse.ArgumentParser() #参数解析
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='./YOLO_small.ckpt', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False) #定义网络的框架
# weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights) #模型文件路径
weight_file = args.weight_dir
detector = Detector(yolo, weight_file) #初始化Detector类
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
imname = 'test/street1.jpeg' #测试文件
detector.image_detector(imname)
imname = 'test/car2.jpeg'
detector.image_detector(imname)
imname = 'test/car3.jpeg'
detector.image_detector(imname)
imname = 'test/person2.jpeg'
detector.image_detector(imname)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
lb = 1
ub = 5
for i in xrange(lb, ub + 1):
folderName = 'test/'
index = i
nZeroes = 6 - len(str(index))
fileName = '0' * nZeroes + str(index) + '.jpg'
imageName = os.path.join(folderName, fileName)
imname = imageName
detector.image_detector(imname)
def main():
parser = argparse.ArgumentParser() # 创建一个解析器对象，并告诉它将会有些什么参数
# 当程序运行时，该解析器就可以用于处理命令行参数
'''定义参数'''
parser.add_argument('--weights', default="YOLO_small.ckpt",
type=str) # 权重文件名
parser.add_argument('--data_dir', default="data", type=str) # 数据集目录
parser.add_argument('--threshold', default=0.2, type=float) # 目标存在阈值
parser.add_argument('--iou_threshold', default=0.5, type=float)
parser.add_argument('--gpu', default='', type=str)
# 定义了所有参数之后，就可以给parse_args()传递一组参数字符串来解析命令行
# 默认情况下参数从sys.argv[1:]中获取
args = parser.parse_args() #将命令行中的参数保存相应的属性
if args.gpu is not None:
cfg.GPU = args.gpu # 判断是否使用GPU
if args.data_dir != cfg.DATA_PATH:
# 检查当前数据集路径，并进行更新
update_config_paths(args.data_dir, args.weights)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU # 设置环境变量
yolo = YOLONet() #创建yolo
pascal = pascal_voc('train') #数据集
solver = Solver(yolo, pascal) # 求解器
print('Start training ...')
solver.train()
print('Done training.')
def main():
'''
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--threshold', default=0.2, type=float)
parser.add_argument('--iou_threshold', default=0.5, type=float)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
args = easydict.EasyDict( {
"weights":"YOLO_small.ckpt",
"data_dir":"data",
"threshold":0.2,
"gpu":"",
"iou_threshold":0.5
})
if args.gpu is not None:
cfg.GPU = args.gpu
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
'''
yolo = YOLONet()
print("build yolo model done")
pascal = pascal_voc('train')
solver = Solver(yolo, pascal)
print('Start training ...')
#solver.train()
print("假装已经训练玩啦")
print('Done training.')
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
# os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
yolo = YOLONet(False)
# weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
weight_file = cfg.WEIGHTS_DIR
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(0)
# detector.camera_detector(cap)
# detect from image file
# imname = os.path.join(cfg.PASCAL_PATH, 'VOCdevkit', 'VOC2007+2012', 'JPEGImages', '000005.jpg')
imname = './test/person.jpg'
# detector.detect_test(imname, 5000)
detector.detect_non_max(imname, 5000)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--threshold', default=0.2, type=float)
parser.add_argument('--iou_threshold', default=0.5, type=float)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
if args.gpu is not None:
cfg.GPU = args.gpu
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
yolo = YOLONet()
pascal = pascal_voc('train')
solver = Solver(yolo, pascal)
print('Start training ...')
solver.train()
print('Done training.')
def main():
parser = argparse.ArgumentParser()
# parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weights', default="save.ckpt-19000", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
# weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
weight_file = os.path.join(args.data_dir, 'pascal_voc', 'output',
'2018_01_03_09_17', args.weights)
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
imname = 'test/000015.jpg'
# image = cv2.imread(imname)
# cv2.rectangle(image, (20, 20), (250, 250), (255, 0, 0), 10)
# cv2.imshow('a',image)
# cv2.waitKey(0)
detector.image_detector(imname)
def main():
# 创建一个解析器对象，并告诉它将会有些什么参数。当程序运行时，该解析器就可以用于处理命令行参数。
parser = argparse.ArgumentParser() # 定义参数
parser.add_argument('--weights', default="YOLO_small.ckpt",
type=str) # 权重文件名
parser.add_argument('--data_dir', default="data", type=str) # 数据集路径
parser.add_argument('--threshold', default=0.2, type=float)
parser.add_argument('--iou_threshold', default=0.5, type=float)
parser.add_argument('--gpu', default='', type=str)
# 定义了所有参数之后，你就可以给 parse_args() 传递一组参数字符串来解析命令行。默认情况下，参数是从 sys.argv[1:] 中获取
# parse_args() 的返回值是一个命名空间，包含传递给命令的参数。该对象将参数保存其属性
args = parser.parse_args()
# 判断是否是使用gpu
if args.gpu is not None:
cfg.GPU = args.gpu
# 设定数据集路径，以及检查点文件路径
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
# 设置环境变量
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
yolo = YOLONet() # 创建YOLO网络对象
pascal = pascal_voc('train') # 数据集对象
solver = Solver(yolo, pascal) # 求解器对象
print('Start training ...')
solver.train() # 开始训练
print('Done training.')
def main():
# TO clear defualt graph and nodes
tf.reset_default_graph()
# here, no use parse, only use default value to set weight
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
yolo = YOLONet(False)
detector = Detector(yolo, weight_file)
# ---data source select only choose one---
# ----'detect from camera'
# cap = cv2.VideoCapture(0)
# detector.camera_detector(cap)
# ----'detect from image file'
imname = './test/bahe.jpg'
detector.image_detector(imname)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="save.ckpt-30000", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='/gpu:0', type=str)
parser.add_argument('--mode', default='0', type=str)
args = parser.parse_args()
#os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
# detect from image file
if args.mode == '0':
list = np.random.randint(0,1019,5)
for i in list:
img = "data/mydata/Pic/img/"+str(i)+".jpg"
print img
detector.image_detector(img)
#detect from camera
elif args.mode == '1':
cap = cv2.VideoCapture(0)
cap.set(cv2.cv.CV_CAP_PROP_FPS, 30)
detector.camera_detector(cap)
def oncle(self):
if self.statusbar.currentMessage() != '':
if self.comboBox.currentText() == "YOLO":
parser = argparse.ArgumentParser()
parser.add_argument('--weights',
default="YOLO_small.ckpt",
type=str)
parser.add_argument('--weight_dir',
default='weights',
type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir,
args.weights)
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
imname = self.file
detector.image_detector(imname)
scene = QGraphicsScene()
pixmap = QPixmap("D:\\result.jpg")
scene.addPixmap(pixmap)
self.graphicsView_2.setScene(scene)
elif self.comboBox.currentText() == "MaskRCNN":
self.maskRCNN = demo.MaskRCNN()
self.maskRCNN.detect(self.file)
scene = QGraphicsScene()
pixmap = QPixmap("D:\\result3.jpg")
scene.addPixmap(pixmap)
self.graphicsView_2.setScene(scene)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--threshold', default=0.2, type=float)
parser.add_argument('--iou_threshold', default=0.5, type=float)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
if args.gpu is not None:
cfg.GPU = args.gpu
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
yolo = YOLONet(True)
data = pascal_voc('train')
for i in range(10):
display_gt(data.gt_labels[i])
solver = Solver(yolo, data)
print('Start training ...')
solver.train()
print('Done training.')
def main():
yolo = YOLONet(False)
weight_file = 'YOLO_small.ckpt' # model directory
detector = Detector(yolo, weight_file)
# detect from camera
cap = cv2.VideoCapture('test.mp4') # test video
detector.camera_detector(cap)
def oncedectect(self):
if self.file != '':
_translate = QtCore.QCoreApplication.translate
classesall = ['person', 'car', 'cat', 'dog']
classesallnum = [7, 8, 15, 12]
detect_timer = Timer()
yolo = YOLONet(False)
detector = Detector(yolo)
detect_timer.tic()
yolostringresults = detector.image_detector(self.file, classesall)
yolotime = detect_timer.toc()
self.yoloTime.setText(_translate("MainWindow",
str(yolotime) + 's'))
pixmap = QPixmap("D:\\result.jpg")
self.yolo_result.setPixmap(pixmap)
self.yolo_result.setScaledContents(True)
self.save.alt('YOLO', yolotime)
self.save.dl(self.fileName(), 'YOLO', yolostringresults)
self.maskRCNN = demo.MaskRCNN()
detect_timer.tic()
maskRCNNstringresults = self.maskRCNN.detect(self.file, classesall)
MaskRCNNtime = detect_timer.toc()
self.maskTime.setText(
_translate("MainWindow",
str(MaskRCNNtime) + 's'))
pixmap = QPixmap("D:\\result2.jpg")
self.Mask_result.setPixmap(pixmap)
self.Mask_result.setScaledContents(True)
self.save.alt('MaskRCNN', MaskRCNNtime)
self.save.dl(self.fileName(), 'MaskRCNN', maskRCNNstringresults)
detect_timer.tic()
ssdstringresult = ssd_notebook.dome(self.file, classesallnum)
SSDtime = detect_timer.toc()
self.ssdTime.setText(_translate("MainWindow", str(SSDtime) + 's'))
pixmap = QPixmap("D:\\result3.jpg")
self.SSD_result.setPixmap(pixmap)
self.SSD_result.setScaledContents(True)
self.save.alt('SSD', SSDtime)
self.save.dl(self.fileName(), 'SSD', ssdstringresult)
detect_timer.tic()
fasterrcnnresult = test.dectect(self.file, classesall)
fasterTime = detect_timer.toc()
self.fasterTime.setText(
_translate("MainWindow",
str(fasterTime) + 's'))
pixmap = QPixmap(r"D:\result4.jpg")
self.Faster_result.setPixmap(pixmap)
self.Faster_result.setScaledContents(True)
self.save.alt('FasterRCNN', fasterTime)
self.save.dl(self.fileName(), 'FasterRCNN', fasterrcnnresult)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
imname = 'test/image1.jpg'
detector.image_detector(imname)
def main():
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
yolo = YOLONet('test')
weight_file = 'data/weights/YOLO_small.ckpt'
detector = Detector(yolo, weight_file)
# detect from camera
cap = cv2.VideoCapture(-1)
detector.camera_detector(cap)
# detect from image file
imname = 'test/person.jpg'
detector.image_detector(imname)
def oncle(self):
if self.file != '':
if self.checkBox.isChecked():
self.classes.append("person")
if self.checkBox_2.isChecked():
self.classes.append("car")
if self.checkBox_3.isChecked():
self.classes.append("dog")
if self.checkBox_4.isChecked():
self.classes.append("cat")
if self.comboBox.currentText() == "YOLO":
yolo = YOLONet(False)
detector = Detector(yolo)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
imname = self.file
detector.image_detector(imname, self.classes)
pixmap = QPixmap("D:\\result.jpg")
self.image2.setPixmap(pixmap)
self.image2.setScaledContents(True)
elif self.comboBox.currentText() == "MaskRCNN":
self.maskRCNN = demo.MaskRCNN()
self.maskRCNN.detect(self.file, self.classes)
scene = QGraphicsScene()
pixmap = QPixmap("D:\\result2.jpg")
self.image2.setPixmap(pixmap)
self.image2.setScaledContents(True)
elif self.comboBox.currentText() == "SSD":
classes1 = []
for item in self.classes:
if (item == 'person'):
classes1.append(15)
elif (item == 'dog'):
classes1.append(12)
elif (item == 'cat'):
classes1.append(8)
elif (item == 'car'):
classes1.append(7)
ssd_notebook.dome(self.file, classes1)
pixmap = QPixmap("D:\\result3.jpg")
self.image2.setPixmap(pixmap)
self.image2.setScaledContents(True)
elif self.comboBox.currentText() == "FasterRCNN":
test.dectect(self.file, self.classes)
pixmap = QPixmap(r"D:\result4.jpg")
self.image2.setPixmap(pixmap)
self.image2.setScaledContents(True)
self.classes.clear()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
parser.add_argument('--read_image_path', default='/run/images/', type=str)
parser.add_argument('--result_path', default='/run/result_path/', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
detector.detector_run(args.read_image_path, args.result_path)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--gpu', default=None, type=int)
args = parser.parse_args()
cfg.WEIGHTS_FILE = os.path.join(cfg.WEIGHTS_DIR, args.weights)
if args.gpu is not None:
cfg.GPU = str(args.gpu)
yolo = YOLONet('train')
pascal = pascal_voc('train')
solver = Solver(yolo, pascal)
solver.train()
def __init__(self):
self.net = YOLONet(False)
self.weights_file = cfg.WERIGHTS_READ
self.cell_size = cfg.CELL_SIZE
self.boxes_per_cell = cfg.BOXES_PER_CELL
self.ap_iou_threshold = cfg.TEST_IOU_THRESHOLD
self.nms_iou_threshold = cfg.NMS_IOU_THERSHOLD
self.boundary2 = self.cell_size * self.cell_size * self.boxes_per_cell
self.batch_size = cfg.TEST_batch_size
self.total_obj = 0
self.recall = None
self.precise = None
self.pro_num = 0
"""
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights',default = 'YOLO_small.ckpt',type = str)
parser.add_argument('--weight_dir',default = 'weights',type = str)
parser.add_argument('--data_dir',default = 'data',type = str)
parser.add_argument('--gpu',default = '',type = str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir,args.weight_dir,args.weights)#权重路径
detector = Detector(yolo,weight_file)
imname = 'test/person.jpg'
detector.image_detector(imname)
def main():
os.environ['CUDA_VISIBLE_DEVICES'] = '' #cfg.GPU
yolo = YOLONet(False)
weight_file = cfg.WERIGHTS_READ #os.path.join(cfg.WEIGHT_READ,'save.ckpt-{}'.format(cfg.LAST_STEP))
detector = Detector(yolo, weight_file)
# detect from camera
# cap = cv2.VideoCapture(-1)
# detector.camera_detector(cap)
# detect from image file
imname = cfg.IMAGE_dir_file
detector.image_detector(imname)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
# detect from camera
cap = cv2.VideoCapture(0)
detector.camera_detector(cap)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', default="YOLO_small.ckpt", type=str)
parser.add_argument('--weight_dir', default='weights', type=str)
parser.add_argument('--data_dir', default="data", type=str)
parser.add_argument('--gpu', default='', type=str)
args = parser.parse_args()
os.environ['CUDA_VISIBLE_DEVICES'] = args.gpu
yolo = YOLONet(False)
weight_file = os.path.join(args.data_dir, args.weight_dir, args.weights)
detector = Detector(yolo, weight_file)
# detect from image file
image_file = 'test/cat.jpg'
detector.detect(image_file)
def main(args):
if args.gpu is not None:
cfg.GPU = args.gpu
if args.data_dir != cfg.DATA_PATH:
update_config_paths(args.data_dir, args.weights)
os.environ['CUDA_VISIBLE_DEVICES'] = cfg.GPU
yolo = YOLONet()
pascal = pascal_voc('train')
solver = Solver(yolo, pascal)
print('Start training ...')
solver.train()
print('Done training.')
