def main():
parser = argparse.ArgumentParser(description="PyTorch FCN Training")
parser.add_argument(
"--config_file", default="", help="path to config file", type=str
)
parser.add_argument("opts", help="Modify config options using the command-line", default=None,
nargs=argparse.REMAINDER)
args = parser.parse_args()
num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
if args.config_file != "":
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
output_dir = cfg.OUTPUT_DIR
if output_dir and not os.path.exists(output_dir):
mkdir(output_dir)
logger = setup_logger("FCN_Model", output_dir, 0)
logger.info("Using {} GPUS".format(num_gpus))
logger.info(args)
if args.config_file != "":
logger.info("Loaded configuration file {}".format(args.config_file))
with open(args.config_file, 'r') as cf:
config_str = "\n" + cf.read()
logger.info(config_str)
logger.info("Running with config:\n{}".format(cfg))
train(cfg)
def main():
parser = argparse.ArgumentParser(description="BtrflyNet training with PyTorch")
parser.add_argument(
"--config_file",
default="config/btrfly.yaml",
metavar="FILE",
help="path to config file",
type=str
)
parser.add_argument("--log_step", default=1, type=int, help="print logs every log_step")
parser.add_argument("--save_step", default=5, type=int, help="save checkpoint every save_step")
parser.add_argument("--eval_step", default=5, type=int, help="evaluate dataset every eval_step, disabled if eval_step <= 0")
parser.add_argument("--use_tensorboard", default=1, type=int, help="use visdom to illustrate training process, unless use_visdom == 0")
parser.add_argument("--train_from_no_checkpoint", default=1, type=int, help="train_from_no_checkpoint")
args = parser.parse_args()
# if torch.cuda.is_available():
# torch.backends.cudnn.benchmark = True
cfg.merge_from_file(args.config_file)
cfg.freeze()
# make output directory designated by OUTPUT_DIR if necessary
if cfg.OUTPUT_PATH:
pathlib.Path(cfg.OUTPUT_PATH).mkdir(exist_ok=True)
# logger_message help print message
# it will also print info to stdout and to OUTPUT_DIR/log.txt (way: append)
logger_message = setup_colorful_logger(
"main_message",
save_dir=os.path.join(cfg.OUTPUT_PATH, 'log.txt'),
format="only_message")
# print config info (cfg and args)
# args are obtained by command line
# cfg is obtained by yaml file and defaults.py in configs/
separator(logger_message)
logger_message.warning(" ---------------------------------------")
logger_message.warning("| Your config: |")
logger_message.warning(" ---------------------------------------")
logger_message.info(args)
logger_message.warning(" ---------------------------------------")
logger_message.warning("| Running with entire config: |")
logger_message.warning(" ---------------------------------------")
logger_message.info(cfg)
separator(logger_message)
train(cfg, args)
help="Directory to dataset")
parser.add_argument('--experiment_dir',
default='experiments/base_model',
help="Directory to experiment")
parser.add_argument(
'--checkpoint_dir',
help="Reload weights from .pth.tar file ('best' or 'last')")
args = parser.parse_args()
# Set the logger, import Tensorboard (fixes conflict with the logger)
set_logger(os.path.join(args.experiment_dir, 'train.log'))
from torch.utils.tensorboard import SummaryWriter
# Import configs
config_dir = args.experiment_dir + '/config.yaml'
cfg.merge_from_file(config_dir)
cfg.freeze()
# Check GPU
cuda = torch.cuda.is_available()
# Fix seed
torch.manual_seed(0)
if cuda: torch.cuda.manual_seed(0)
# Fetch dataloaders
logging.info("Loading datasets...\n")
dl = dataloaders.fetch_dataloaders(args.data_dir)
train_dl, valid_dl, test_dl = dl['train'], dl['valid'], dl['test']
else:
print("[INFO] opening video file...")
# vs = cv2.VideoCapture(RTSP_URL)
vs = cv2.VideoCapture(cfg.DATA.INPUT)
print(cfg.DATA.INPUT)
return vs
# 越线值
total_down = 0 # 出现人数
total_up = 0 # 过线人数
# 加载配置信息，如果FRAME.CATE=0代表通道，1表示闸机
if cfg.FRAME.CATE == 0:
cfg.merge_from_file('./config/asile.yaml')
else:
cfg.merge_from_file('./config/gate.yaml')
cfg.freeze()
def main_func(args, vs, yolo):
scheduler = BackgroundScheduler() # 初始化任务函数
# 添加调度任务
# 调度方法为 timedTask，触发器选择 interval(间隔性)，间隔时长为 1 秒
scheduler.add_job(timedTask, 'interval',
seconds=cfg.KAFKA.PUSHINTER) # 间隔为1秒
# 启动调度任务
scheduler.start()
writer = None # 写入对象，如果要写入视频，将实例化该对象
W = None