Пример #1
0
def bootup ():
    try:
        opts, args = getopt.getopt (sys.argv[1:], "hc:p:", ["config=", "pid-file="])
    except getopt.GetoptError:
        # print help information and exit:
        usage()
        sys.exit(2)
    verbose = False
    config_file = None
    pidfile = None
    for o, a in opts:
        if o == "-v":
            verbose = True
        if o in ("-h", "--help"):
            usage()
            sys.exit()
        if o in ("-c", "--config"):
            config_file = a
        if o in ("-p", "--pid-file"):
            pidfile = a
    if config_file == None:
        # print help information and exit:
        usage()
        sys.exit(2)

    config.initialise(config_file)

    if pidfile is not None:
        #Command line override
        config.set('dbAlerter', 'pid_file', pidfile)

    if (config.has_option('dbAlerter', 'pid_file')):
        pidfile = config.get('dbAlerter', 'pid_file')
        try:
            pf = file(pidfile,'r')
            pid = int(pf.read().strip())
            pf.close()
        except IOError:
            pid = None

        if pid:
            message = "pidfile %s already exists. dbAlerter may already be running,\ncheck the process / task list and dbAlerter log file for any\nouststanding issues before removing the existing pidfile.\n"
            sys.stderr.write(message % pidfile)
            sys.exit(1)

    daemonize('/dev/null', config.get('dbAlerter','dbalerter_log'), config.get('dbAlerter','dbalerter_log'))

    main()
import torch
import torch.nn as nn
from torch.nn import functional as F
from utils.ops import unpixel_shuffle

from models.lr_net import SmoothDilatedResidualAtrousGuidedBlock, LRNet
from models.model_utils import AdaptiveInstanceNorm

from sacred import Experiment
from config import initialise

ex = Experiment("DAGF")
ex = initialise(ex)


class ConvGuidedFilter(nn.Module):
    """
    Adapted from https://github.com/wuhuikai/DeepGuidedFilter
    """
    def __init__(self,
                 radius=1,
                 norm=nn.BatchNorm2d,
                 conv_a_kernel_size: int = 1):
        super(ConvGuidedFilter, self).__init__()

        self.box_filter = nn.Conv2d(3,
                                    3,
                                    kernel_size=3,
                                    padding=radius,
                                    dilation=radius,
                                    bias=False,