notebook.community

Edit and run 





In [1]:



    


import os, glob, platform, datetime, random
from collections import OrderedDict

import torch
import torch.nn as nn
import torch.utils.data as data_utils
import torch.nn.parallel
import torch.backends.cudnn as cudnn
import torch.optim as optim
from torch.autograd import Variable
from torch import functional as F
# import torchvision.datasets as datasets
import torchvision.models as models
import torchvision.transforms as transforms

import cv2
from PIL import Image
from tensorboardX import SummaryWriter

import numpy as np
from numpy.linalg import inv as denseinv
from scipy import sparse
from scipy.sparse import lil_matrix, csr_matrix
from scipy.sparse.linalg import spsolve
from scipy.sparse.linalg import inv as spinv
import scipy.misc

from myimagefolder import MyImageFolder
from mymodel import GradientNet
from myargs import Args
from myutils import MyUtils

Configurations





In [2]:



    


myutils = MyUtils()

args = Args()
args.arch = "densenet121"
args.epoches = 500
args.epoches_unary_threshold = 0
args.image_h = 256
args.image_w = 256
args.img_extentions = ["png"]
args.training_thresholds = [250,200,150,50,0,300]
args.base_lr = 1
args.lr = args.base_lr
args.snapshot_interval = 5000
args.debug = True


# growth_rate = (4*(2**(args.gpu_num)))
transition_scale=2
pretrained_scale=4
growth_rate = 32

#######
# args.test_scene = ['alley_2', 'bamboo_2', 'bandage_2', 'cave_4', 'market_5', 'mountain_1', 'shaman_3', 'sleeping_2', 'temple_3']
args.test_scene = 'bandage_2'
gradient=True
args.gpu_num = 2
#######

writer_comment = '{}_rgb'.format(args.test_scene)
if gradient == True:
    writer_comment = '{}_gd'.format(args.test_scene)

offset = 0.
if gradient == True: offset = 0.5

args.display_interval = 50
args.display_curindex = 0

system_ = platform.system()
system_dist, system_version, _ = platform.dist()
if system_ == "Darwin": 
    args.train_dir = '/Volumes/Transcend/dataset/sintel2'
    args.pretrained = False
elif platform.dist() ==  ('debian', 'jessie/sid', ''):
    args.train_dir = '/home/lwp/workspace/sintel2'
    args.pretrained = True
elif platform.dist() == ('debian', 'stretch/sid', ''):
    args.train_dir = '/home/cad/lwp/workspace/dataset/sintel2'
    args.pretrained = True

if platform.system() == 'Linux': use_gpu = True
else: use_gpu = False
if use_gpu:
    torch.cuda.set_device(args.gpu_num)
    

print(platform.dist())



    


















    






('debian', 'jessie/sid', '')

My DataLoader





In [3]:



    


train_dataset = MyImageFolder(args.train_dir, 'train',
                       transforms.Compose(
        [transforms.ToTensor()]
    ), random_crop=True, 
    img_extentions=args.img_extentions, test_scene=args.test_scene, image_h=args.image_h, image_w=args.image_w)
test_dataset = MyImageFolder(args.train_dir, 'test', 
                       transforms.Compose(
        [transforms.CenterCrop((args.image_h, args.image_w)),
         transforms.ToTensor()]
    ), random_crop=False,
    img_extentions=args.img_extentions, test_scene=args.test_scene, image_h=args.image_h, image_w=args.image_w)

train_loader = data_utils.DataLoader(train_dataset,1,True,num_workers=1)
test_loader = data_utils.DataLoader(test_dataset,1,True,num_workers=1)

Load Pretrained Model

Defination

  • DenseNet-121: num_init_features=64, growth_rate=32, block_config=(6, 12, 24, 16)
    • First Convolution: 32M -> 16M -> 8M
    • every transition: 8M -> 4M -> 2M (downsample 1/2, except the last block)




In [4]:



    


densenet = models.__dict__[args.arch](pretrained=args.pretrained)

for param in densenet.parameters():
    param.requires_grad = False

if use_gpu: densenet.cuda()



    











In [5]:



    


ss = 6
s0 = ss*5
# s0 = 2

args.display_curindex = 0
args.base_lr = 0.05
args.display_interval = 20
args.momentum = 0.9
args.epoches = 240
args.training_thresholds = [0,0,0,0,0,s0]
args.training_merge_thresholds = [s0+ss*3*3,s0+ss*2*3, s0+ss*1*3, s0, -1, s0+ss*4*3]
args.power = 0.5



# pretrained = PreTrainedModel(densenet)
# if use_gpu: 
#     pretrained.cuda()


net = GradientNet(densenet=densenet, growth_rate=growth_rate, 
                  transition_scale=transition_scale, pretrained_scale=pretrained_scale,
                 gradient=gradient)
if use_gpu:
    net.cuda()

if use_gpu: 
    mse_losses = [nn.MSELoss().cuda()] * 6
    test_losses = [nn.MSELoss().cuda()] * 6
    mse_merge_losses = [nn.MSELoss().cuda()] * 6
    test_merge_losses = [nn.MSELoss().cuda()] * 6
else:
    mse_losses = [nn.MSELoss()] * 6
    mse_merge_losses = [nn.MSELoss()] * 6
    test_losses = [nn.MSELoss()] * 6
    test_merge_losses = [nn.MSELoss()] * 6



    


















    






_ ConvTranspose2d weight 0.002867696673382022
_ ConvTranspose2d weight 0.002867696673382022
_ ConvTranspose2d weight 0.003031695312954162
_ ConvTranspose2d weight 0.003031695312954162
_ ConvTranspose2d weight 0.004419417382415922

















In [6]:



    


def test_model(epoch, go_through_merge=False, phase='train'):
    if phase == 'train': net.train()
    else: net.eval()
    
    test_losses_trainphase = [0] * len(args.training_thresholds)
    test_cnts_trainphase   = [0.00001] * len(args.training_thresholds)  
    test_merge_losses_trainphase = [0] * len(args.training_thresholds)
    test_merge_cnts_trainphase   = [0.00001] * len(args.training_thresholds)
    
    for ind, data in enumerate(test_loader, 0):
        input_img, gt_albedo, gt_shading, test_scene, img_path = data
        input_img = Variable(input_img)
        gt_albedo = Variable(gt_albedo)
        gt_shading = Variable(gt_shading)
        if use_gpu:
            input_img = input_img.cuda(args.gpu_num)
        
#         pretrained.train(); ft_pretreained = pretrained(input_img)
        ft_test, merged_RGB = net(input_img, go_through_merge=go_through_merge)
            
        for i,v in enumerate(ft_test):
            if epoch < args.training_thresholds[i]: continue
            if i == 5: s = 1
            else: s = (2**(i+1))
            gt0 = gt_albedo.cpu().data.numpy()
            n,c,h,w = gt0.shape
            gt, display = myutils.processGt(gt0, scale_factor=s, gd=gradient, return_image=True)
            gt_mg, display_mg = myutils.processGt(gt0, scale_factor=s//2, gd=gradient, return_image=True)
            
            if use_gpu: 
                gt = gt.cuda()
                gt_mg = gt_mg.cuda()
            
            if i != 5: 
                loss = mse_losses[i](ft_test[i], gt)
                test_losses_trainphase[i] += loss.data.cpu().numpy()[0]
                test_cnts_trainphase[i] += 1
            
            if go_through_merge != False and i != 4:
                if ((go_through_merge == '32M') or
                    (go_through_merge == '16M' and i != 5) or  
                    (go_through_merge == '08M' and i != 5 and i > 0) or
                    (go_through_merge == '04M' and i != 5 and i > 1) or
                    (go_through_merge == '02M' and i != 5 and i > 2)):
                    if i==5: gt2=gt
                    else: gt2=gt_mg
#                     print(i)
#                     print('merge size', merged_RGB[i].size())
#                     print('gt2 size', gt2.size())
                    loss = mse_merge_losses[i](merged_RGB[i], gt2)
                    test_merge_losses_trainphase[i] += loss.data.cpu().numpy()[0]
                    test_merge_cnts_trainphase[i] += 1
            

            
            if ind == 0: 
                if i != 5:
                    v = v[0].cpu().data.numpy()
                    v = v.transpose(1,2,0)
                    v = v[:,:,0:3]
                    cv2.imwrite('snapshot{}/test-phase_{}-{}-{}.png'.format(args.gpu_num, phase, epoch, i), (v[:,:,::-1]+offset)*255)
                if go_through_merge != False and i != 4:
                    if ((go_through_merge == '32M') or
                    (go_through_merge == '16M' and i != 5) or  
                    (go_through_merge == '08M' and i != 5 and i > 0) or
                    (go_through_merge == '04M' and i != 5 and i > 1) or
                    (go_through_merge == '02M' and i != 5 and i > 2)):
                        v = merged_RGB[i][0].cpu().data.numpy()
                        v = v.transpose(1,2,0)
                        v = v[:,:,0:3]
                        cv2.imwrite('snapshot{}/test-mg-phase_{}-{}-{}.png'.format(args.gpu_num, phase, epoch, i), (v[:,:,::-1]+offset)*255)
                    
    run_losses = test_losses_trainphase
    run_cnts = test_cnts_trainphase
    writer.add_scalars('16M loss', {'test 16M phase {}'.format(phase): np.array([run_losses[0]/ run_cnts[0]])}, global_step=epoch)  
    writer.add_scalars('8M loss', {'test 8M phase {}'.format(phase): np.array([run_losses[1]/ run_cnts[1]])}, global_step=epoch) 
    writer.add_scalars('4M loss', {'test 4M phase {}'.format(phase): np.array([run_losses[2]/ run_cnts[2]])}, global_step=epoch) 
    writer.add_scalars('2M loss', {'test 2M ': np.array([run_losses[3]/ run_cnts[3]])}, global_step=epoch) 
    writer.add_scalars('1M loss', {'test 1M phase {}'.format(phase): np.array([run_losses[4]/ run_cnts[4]])}, global_step=epoch) 
    writer.add_scalars('merged loss', {'test merged phase {}'.format(phase): np.array([run_losses[5]/ run_cnts[5]])}, global_step=epoch)
    
    run_losses = test_merge_losses_trainphase
    run_cnts = test_merge_cnts_trainphase
    writer.add_scalars('16M loss', {'mg test 16M phase {}'.format(phase): np.array([run_losses[0]/ run_cnts[0]])}, global_step=epoch)  
    writer.add_scalars('8M loss', {'mg test 8M phase {}'.format(phase): np.array([run_losses[1]/ run_cnts[1]])}, global_step=epoch) 
    writer.add_scalars('4M loss', {'mg test 4M phase {}'.format(phase): np.array([run_losses[2]/ run_cnts[2]])}, global_step=epoch) 
    writer.add_scalars('2M loss', {'mg test 2M ': np.array([run_losses[3]/ run_cnts[3]])}, global_step=epoch) 
    writer.add_scalars('1M loss', {'mg test 1M phase {}'.format(phase): np.array([run_losses[4]/ run_cnts[4]])}, global_step=epoch) 
    writer.add_scalars('merged loss', {'mg test merged phase {}'.format(phase): np.array([run_losses[5]/ run_cnts[5]])}, global_step=epoch)



    











In [7]:



    


# training loop

writer = SummaryWriter(comment='-{}'.format(writer_comment))

parameters = filter(lambda p: p.requires_grad, net.parameters())
optimizer = optim.SGD(parameters, lr=args.base_lr, momentum=args.momentum)

def adjust_learning_rate(optimizer, epoch, beg, end, reset_lr=None, base_lr=args.base_lr):
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    for param_group in optimizer.param_groups:
#         print('para gp', param_group)
        if reset_lr != None:
            param_group['lr'] = reset_lr
            continue
        param_group['lr'] = base_lr * (float(end-epoch)/(end-beg)) ** (args.power)
        if param_group['lr'] < 1.0e-8: param_group['lr'] = 1.0e-8
        

for epoch in range(args.epoches):
#     epoch = 234
    net.train()
    print('epoch: {} [{}]'.format(epoch, datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")))

    if epoch < args.training_thresholds[-1]: 
        adjust_learning_rate(optimizer, epoch, beg=0, end=s0-1)
    elif epoch < args.training_merge_thresholds[-1]:
        adjust_learning_rate(optimizer, (epoch-s0)%(ss), beg=0, end=ss-1, base_lr=args.base_lr)
    else:
        adjust_learning_rate(optimizer, epoch, beg=args.training_merge_thresholds[-1], end=args.epoches-1, base_lr=args.base_lr)  
        
        
    if epoch < args.training_thresholds[-1]: go_through_merge = False
    elif epoch >= args.training_merge_thresholds[5]: go_through_merge = '32M'
    elif epoch >= args.training_merge_thresholds[0]: go_through_merge = '16M'
    elif epoch >= args.training_merge_thresholds[1]: go_through_merge = '08M'
    elif epoch >= args.training_merge_thresholds[2]: go_through_merge = '04M'
    elif epoch >= args.training_merge_thresholds[3]: go_through_merge = '02M'

    run_losses = [0] * len(args.training_thresholds)
    run_cnts   = [0.00001] * len(args.training_thresholds)
    run_merge_losses = [0] * len(args.training_thresholds)
    run_merge_cnts   = [0.00001] * len(args.training_thresholds)
    if (epoch in args.training_thresholds) == True: 
        adjust_learning_rate(optimizer, epoch, reset_lr=args.base_lr, beg=-1, end=-1)
    if (epoch in args.training_merge_thresholds) == True:
        adjust_learning_rate(optimizer, epoch, reset_lr=args.base_lr, beg=-1, end=-1)
        
    writer.add_scalar('learning rate', optimizer.param_groups[0]['lr'], global_step=epoch)
    for ind, data in enumerate(train_loader, 0):
#         if  ind == 1 : break
        """prepare  training data"""
        input_img, gt_albedo, gt_shading, test_scene, img_path = data
        im = input_img[0,:,:,:].numpy(); im = im.transpose(1,2,0); im = im[:,:,::-1]*255
        input_img, gt_albedo, gt_shading = Variable(input_img), Variable(gt_albedo), Variable(gt_shading)
        if use_gpu: input_img, gt_albedo, gt_shading = input_img.cuda(), gt_albedo.cuda(), gt_shading.cuda()

        if args.display_curindex % args.display_interval == 0: cv2.imwrite('snapshot{}/input.png'.format(args.gpu_num), im)

        optimizer.zero_grad()
        
            
        ft_predict, merged_RGB = net(input_img, go_through_merge=go_through_merge)
        for i, threshold in enumerate(args.training_thresholds):
            if epoch >= threshold:
#             if epoch >= 0:
                """prepare resized gt"""
                if i == 5: s = 1
                else: s = (2**(i+1))
                gt0 = gt_albedo.cpu().data.numpy()
                n,c,h,w = gt0.shape
                gt, display = myutils.processGt(gt0, scale_factor=s, gd=gradient, return_image=True)
                gt_mg, display_mg = myutils.processGt(gt0, scale_factor=s//2, gd=gradient, return_image=True)
                if use_gpu: 
                    gt = gt.cuda()
                    gt_mg = gt_mg.cuda()
                if args.display_curindex % args.display_interval == 0:
                    display = display[:,:,0:3]
                    cv2.imwrite('snapshot{}/gt-{}-{}.png'.format(args.gpu_num, epoch, i), display[:,:,::-1]*255)                
                
                """compute loss"""
                if i != 5: 
                    loss = mse_losses[i](ft_predict[i], gt)
                    run_losses[i] += loss.data.cpu().numpy()[0]
                    loss.backward(retain_graph=True)
                    run_cnts[i] += 1
                
                if go_through_merge != False and i != 4:
                    if ((go_through_merge == '32M') or
                    (go_through_merge == '16M' and i != 5) or  
                    (go_through_merge == '08M' and i != 5 and i > 0) or
                    (go_through_merge == '04M' and i != 5 and i > 1) or
                    (go_through_merge == '02M' and i != 5 and i > 2)):
#                         print(epoch, go_through_merge, i)
                        
#                         print (merged_RGB[i].cpu().data.numpy().max(), merged_RGB[i].cpu().data.numpy().min())
                        if i==5: gt2=gt
                        else: gt2=gt_mg
#                         print(i)
#                         print('merge size', merged_RGB[i].size())
#                         print('gt2 size', gt2.size())
                        loss = mse_merge_losses[i](merged_RGB[i], gt2)
                        run_merge_losses[i] += loss.data.cpu().numpy()[0]
                        loss.backward(retain_graph=True)
                        run_merge_cnts[i] += 1
                
                """save training image"""
                if args.display_curindex % args.display_interval == 0:
                    
                    if i != 5:
                        im = (ft_predict[i].cpu().data.numpy()[0].transpose((1,2,0))+offset) * 255
                        im = im[:,:,0:3]
                        
                        cv2.imwrite('snapshot{}/train-{}-{}.png'.format(args.gpu_num, epoch, i), im[:,:,::-1])
                    
                    if go_through_merge != False and i != 4:
                        if ((go_through_merge == '32M') or
                        (go_through_merge == '16M' and i != 5) or  
                        (go_through_merge == '08M' and i != 5 and i > 0) or
                        (go_through_merge == '04M' and i != 5 and i > 1) or
                        (go_through_merge == '02M' and i != 5 and i > 2)):
                            im = (merged_RGB[i].cpu().data.numpy()[0].transpose((1,2,0))+offset) * 255
                            im = im[:,:,0:3]
                            cv2.imwrite('snapshot{}/train-mg-{}-{}.png'.format(args.gpu_num, epoch, i), im[:,:,::-1])
        optimizer.step()
        args.display_curindex += 1

    """ every epoch """
#     loss_output = 'ind: ' + str(args.display_curindex)
    loss_output = ''
    
    
    
    for i,v in enumerate(run_losses):
        if i == len(run_losses)-1: 
            loss_output += ' merged: %6f' % (run_losses[i] / run_cnts[i])
            continue
        loss_output += ' %2dM: %6f' % ((2**(4-i)), (run_losses[i] / run_cnts[i]))
    print(loss_output)
    loss_output = ''
    for i,v in enumerate(run_merge_losses):
        if i == len(run_merge_losses)-1: 
            loss_output += 'mg merged: %6f' % (run_merge_losses[i] / run_merge_cnts[i])
            continue
        loss_output += ' mg %2dM: %6f' % ((2**(4-i)), (run_merge_losses[i] / run_merge_cnts[i]))
    print(loss_output)
    
    """save at every epoch"""
    if (epoch+1) % 10 == 0:
        torch.save({
            'epoch': epoch,
            'args' : args,
            'state_dict': net.state_dict(),
            'optimizer': optimizer.state_dict()
        }, 'snapshot{}/snapshot-{}.pth.tar'.format(args.gpu_num, epoch))
    
    # test 
    if (epoch+1) % 5 == 0:
        test_model(epoch, phase='train', go_through_merge=go_through_merge)
        test_model(epoch, phase='test', go_through_merge=go_through_merge)

        writer.add_scalars('16M loss', {'train 16M ': np.array([run_losses[0]/ run_cnts[0]])}, global_step=epoch)  
        writer.add_scalars('8M loss', {'train 8M ': np.array([run_losses[1]/ run_cnts[1]])}, global_step=epoch) 
        writer.add_scalars('4M loss', {'train 4M ': np.array([run_losses[2]/ run_cnts[2]])}, global_step=epoch) 
        writer.add_scalars('2M loss', {'train 2M ': np.array([run_losses[3]/ run_cnts[3]])}, global_step=epoch) 
        writer.add_scalars('1M loss', {'train 1M ': np.array([run_losses[4]/ run_cnts[4]])}, global_step=epoch) 
        writer.add_scalars('merged loss', {'train merged ': np.array([run_losses[5]/ run_cnts[5]])}, global_step=epoch)



    


















    






epoch: 0 [2017-12-20 13:10:31]
 16M: 0.003274  8M: 0.004583  4M: 0.005646  2M: 0.007073  1M: 0.008078 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 1 [2017-12-20 13:11:53]
 16M: 0.002331  8M: 0.003484  4M: 0.004060  2M: 0.005248  1M: 0.005958 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 2 [2017-12-20 13:13:14]
 16M: 0.002155  8M: 0.003183  4M: 0.003660  2M: 0.004574  1M: 0.005107 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 3 [2017-12-20 13:14:34]
 16M: 0.002112  8M: 0.003131  4M: 0.003586  2M: 0.004459  1M: 0.004980 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 4 [2017-12-20 13:15:54]
 16M: 0.002028  8M: 0.002956  4M: 0.003299  2M: 0.003927  1M: 0.004477 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 5 [2017-12-20 13:17:21]
 16M: 0.001965  8M: 0.002860  4M: 0.003176  2M: 0.003817  1M: 0.004231 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 6 [2017-12-20 13:18:41]
 16M: 0.001943  8M: 0.002797  4M: 0.003046  2M: 0.003506  1M: 0.003807 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 7 [2017-12-20 13:20:01]
 16M: 0.001944  8M: 0.002783  4M: 0.002977  2M: 0.003371  1M: 0.003614 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 8 [2017-12-20 13:21:21]
 16M: 0.001923  8M: 0.002757  4M: 0.002941  2M: 0.003295  1M: 0.003560 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 9 [2017-12-20 13:22:41]
 16M: 0.001892  8M: 0.002680  4M: 0.002831  2M: 0.003191  1M: 0.003568 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 10 [2017-12-20 13:24:05]
 16M: 0.001907  8M: 0.002700  4M: 0.002794  2M: 0.003088  1M: 0.003347 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 11 [2017-12-20 13:25:25]
 16M: 0.001880  8M: 0.002645  4M: 0.002734  2M: 0.003000  1M: 0.003258 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 12 [2017-12-20 13:26:46]
 16M: 0.001850  8M: 0.002605  4M: 0.002668  2M: 0.002924  1M: 0.003216 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 13 [2017-12-20 13:28:05]
 16M: 0.001864  8M: 0.002612  4M: 0.002635  2M: 0.002865  1M: 0.003098 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 14 [2017-12-20 13:29:25]
 16M: 0.001808  8M: 0.002517  4M: 0.002545  2M: 0.002749  1M: 0.002972 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 15 [2017-12-20 13:30:51]
 16M: 0.001841  8M: 0.002577  4M: 0.002581  2M: 0.002786  1M: 0.002972 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 16 [2017-12-20 13:32:10]
 16M: 0.001806  8M: 0.002499  4M: 0.002477  2M: 0.002660  1M: 0.002846 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 17 [2017-12-20 13:33:32]
 16M: 0.001788  8M: 0.002465  4M: 0.002452  2M: 0.002632  1M: 0.002739 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 18 [2017-12-20 13:34:52]
 16M: 0.001815  8M: 0.002492  4M: 0.002443  2M: 0.002615  1M: 0.002791 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 19 [2017-12-20 13:36:12]
 16M: 0.001763  8M: 0.002436  4M: 0.002408  2M: 0.002571  1M: 0.002712 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 20 [2017-12-20 13:37:40]
 16M: 0.001809  8M: 0.002484  4M: 0.002415  2M: 0.002562  1M: 0.002727 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 21 [2017-12-20 13:39:01]
 16M: 0.001726  8M: 0.002382  4M: 0.002319  2M: 0.002464  1M: 0.002599 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 22 [2017-12-20 13:40:21]
 16M: 0.001752  8M: 0.002406  4M: 0.002325  2M: 0.002435  1M: 0.002582 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 23 [2017-12-20 13:41:41]
 16M: 0.001743  8M: 0.002393  4M: 0.002320  2M: 0.002441  1M: 0.002541 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 24 [2017-12-20 13:43:01]
 16M: 0.001705  8M: 0.002330  4M: 0.002235  2M: 0.002382  1M: 0.002533 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 25 [2017-12-20 13:44:26]
 16M: 0.001740  8M: 0.002396  4M: 0.002288  2M: 0.002410  1M: 0.002504 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 26 [2017-12-20 13:45:48]
 16M: 0.001736  8M: 0.002349  4M: 0.002229  2M: 0.002327  1M: 0.002367 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 27 [2017-12-20 13:47:08]
 16M: 0.001717  8M: 0.002346  4M: 0.002218  2M: 0.002319  1M: 0.002392 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 28 [2017-12-20 13:48:30]
 16M: 0.001739  8M: 0.002369  4M: 0.002235  2M: 0.002309  1M: 0.002384 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 29 [2017-12-20 13:49:49]
 16M: 0.001759  8M: 0.002395  4M: 0.002256  2M: 0.002306  1M: 0.002380 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.000000 mg  1M: 0.000000mg merged: 0.000000
epoch: 30 [2017-12-20 13:51:16]
 16M: 0.001717  8M: 0.002351  4M: 0.002262  2M: 0.002417  1M: 0.002512 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.005828 mg  1M: 0.000000mg merged: 0.000000
epoch: 31 [2017-12-20 13:52:56]
 16M: 0.001737  8M: 0.002364  4M: 0.002230  2M: 0.002359  1M: 0.002468 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004847 mg  1M: 0.000000mg merged: 0.000000
epoch: 32 [2017-12-20 13:54:36]
 16M: 0.001732  8M: 0.002343  4M: 0.002216  2M: 0.002346  1M: 0.002456 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004734 mg  1M: 0.000000mg merged: 0.000000
epoch: 33 [2017-12-20 13:56:17]
 16M: 0.001713  8M: 0.002322  4M: 0.002161  2M: 0.002287  1M: 0.002377 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004669 mg  1M: 0.000000mg merged: 0.000000
epoch: 34 [2017-12-20 13:57:55]
 16M: 0.001707  8M: 0.002301  4M: 0.002140  2M: 0.002227  1M: 0.002292 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004700 mg  1M: 0.000000mg merged: 0.000000
epoch: 35 [2017-12-20 13:59:41]
 16M: 0.001686  8M: 0.002256  4M: 0.002067  2M: 0.002124  1M: 0.002196 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004479 mg  1M: 0.000000mg merged: 0.000000
epoch: 36 [2017-12-20 14:01:20]
 16M: 0.001693  8M: 0.002296  4M: 0.002159  2M: 0.002293  1M: 0.002389 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004606 mg  1M: 0.000000mg merged: 0.000000
epoch: 37 [2017-12-20 14:02:58]
 16M: 0.001700  8M: 0.002282  4M: 0.002116  2M: 0.002212  1M: 0.002339 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004611 mg  1M: 0.000000mg merged: 0.000000
epoch: 38 [2017-12-20 14:04:36]
 16M: 0.001646  8M: 0.002195  4M: 0.002027  2M: 0.002121  1M: 0.002239 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004312 mg  1M: 0.000000mg merged: 0.000000
epoch: 39 [2017-12-20 14:06:15]
 16M: 0.001676  8M: 0.002250  4M: 0.002074  2M: 0.002153  1M: 0.002229 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004350 mg  1M: 0.000000mg merged: 0.000000
epoch: 40 [2017-12-20 14:08:01]
 16M: 0.001658  8M: 0.002222  4M: 0.002033  2M: 0.002096  1M: 0.002178 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004243 mg  1M: 0.000000mg merged: 0.000000
epoch: 41 [2017-12-20 14:09:38]
 16M: 0.001661  8M: 0.002218  4M: 0.002006  2M: 0.002042  1M: 0.002126 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004202 mg  1M: 0.000000mg merged: 0.000000
epoch: 42 [2017-12-20 14:11:17]
 16M: 0.001656  8M: 0.002209  4M: 0.002041  2M: 0.002130  1M: 0.002208 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004187 mg  1M: 0.000000mg merged: 0.000000
epoch: 43 [2017-12-20 14:12:56]
 16M: 0.001656  8M: 0.002213  4M: 0.002007  2M: 0.002091  1M: 0.002179 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004097 mg  1M: 0.000000mg merged: 0.000000
epoch: 44 [2017-12-20 14:14:36]
 16M: 0.001681  8M: 0.002225  4M: 0.002028  2M: 0.002080  1M: 0.002189 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.003967 mg  1M: 0.000000mg merged: 0.000000
epoch: 45 [2017-12-20 14:16:24]
 16M: 0.001653  8M: 0.002183  4M: 0.001952  2M: 0.002006  1M: 0.002077 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.004058 mg  1M: 0.000000mg merged: 0.000000
epoch: 46 [2017-12-20 14:18:00]
 16M: 0.001606  8M: 0.002104  4M: 0.001877  2M: 0.001922  1M: 0.001979 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.003846 mg  1M: 0.000000mg merged: 0.000000
epoch: 47 [2017-12-20 14:19:41]
 16M: 0.001602  8M: 0.002111  4M: 0.001903  2M: 0.001936  1M: 0.002012 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.000000 mg  2M: 0.003808 mg  1M: 0.000000mg merged: 0.000000
epoch: 48 [2017-12-20 14:21:22]
 16M: 0.001644  8M: 0.002168  4M: 0.002003  2M: 0.002079  1M: 0.002151 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.004281 mg  2M: 0.003860 mg  1M: 0.000000mg merged: 0.000000
epoch: 49 [2017-12-20 14:23:21]
 16M: 0.001618  8M: 0.002133  4M: 0.001954  2M: 0.002030  1M: 0.002116 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003555 mg  2M: 0.003799 mg  1M: 0.000000mg merged: 0.000000
epoch: 50 [2017-12-20 14:25:28]
 16M: 0.001663  8M: 0.002179  4M: 0.001949  2M: 0.001985  1M: 0.002101 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003526 mg  2M: 0.003816 mg  1M: 0.000000mg merged: 0.000000
epoch: 51 [2017-12-20 14:27:28]
 16M: 0.001631  8M: 0.002134  4M: 0.001927  2M: 0.002004  1M: 0.002056 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003362 mg  2M: 0.003694 mg  1M: 0.000000mg merged: 0.000000
epoch: 52 [2017-12-20 14:29:25]
 16M: 0.001579  8M: 0.002063  4M: 0.001842  2M: 0.001868  1M: 0.001916 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003253 mg  2M: 0.003543 mg  1M: 0.000000mg merged: 0.000000
epoch: 53 [2017-12-20 14:31:24]
 16M: 0.001613  8M: 0.002105  4M: 0.001854  2M: 0.001874  1M: 0.001918 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003259 mg  2M: 0.003515 mg  1M: 0.000000mg merged: 0.000000
epoch: 54 [2017-12-20 14:33:23]
 16M: 0.001592  8M: 0.002097  4M: 0.001880  2M: 0.001931  1M: 0.001976 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003241 mg  2M: 0.003585 mg  1M: 0.000000mg merged: 0.000000
epoch: 55 [2017-12-20 14:35:32]
 16M: 0.001599  8M: 0.002091  4M: 0.001873  2M: 0.001933  1M: 0.001987 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003170 mg  2M: 0.003510 mg  1M: 0.000000mg merged: 0.000000
epoch: 56 [2017-12-20 14:37:33]
 16M: 0.001608  8M: 0.002103  4M: 0.001885  2M: 0.001965  1M: 0.002014 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003184 mg  2M: 0.003584 mg  1M: 0.000000mg merged: 0.000000
epoch: 57 [2017-12-20 14:39:31]
 16M: 0.001563  8M: 0.002032  4M: 0.001796  2M: 0.001834  1M: 0.001882 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003097 mg  2M: 0.003433 mg  1M: 0.000000mg merged: 0.000000
epoch: 58 [2017-12-20 14:41:32]
 16M: 0.001614  8M: 0.002092  4M: 0.001844  2M: 0.001862  1M: 0.001926 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003127 mg  2M: 0.003557 mg  1M: 0.000000mg merged: 0.000000
epoch: 59 [2017-12-20 14:43:32]
 16M: 0.001595  8M: 0.002060  4M: 0.001798  2M: 0.001828  1M: 0.001839 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.003026 mg  2M: 0.003438 mg  1M: 0.000000mg merged: 0.000000
epoch: 60 [2017-12-20 14:45:38]
 16M: 0.001549  8M: 0.002017  4M: 0.001800  2M: 0.001856  1M: 0.001910 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.002998 mg  2M: 0.003406 mg  1M: 0.000000mg merged: 0.000000
epoch: 61 [2017-12-20 14:47:38]
 16M: 0.001630  8M: 0.002101  4M: 0.001858  2M: 0.001920  1M: 0.001957 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.002986 mg  2M: 0.003447 mg  1M: 0.000000mg merged: 0.000000
epoch: 62 [2017-12-20 14:49:36]
 16M: 0.001594  8M: 0.002058  4M: 0.001815  2M: 0.001861  1M: 0.001951 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.002927 mg  2M: 0.003396 mg  1M: 0.000000mg merged: 0.000000
epoch: 63 [2017-12-20 14:51:32]
 16M: 0.001567  8M: 0.002010  4M: 0.001750  2M: 0.001782  1M: 0.001860 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.002821 mg  2M: 0.003241 mg  1M: 0.000000mg merged: 0.000000
epoch: 64 [2017-12-20 14:53:34]
 16M: 0.001550  8M: 0.001990  4M: 0.001728  2M: 0.001727  1M: 0.001735 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.002800 mg  2M: 0.003227 mg  1M: 0.000000mg merged: 0.000000
epoch: 65 [2017-12-20 14:55:41]
 16M: 0.001531  8M: 0.001975  4M: 0.001722  2M: 0.001749  1M: 0.001792 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.000000 mg  4M: 0.002788 mg  2M: 0.003213 mg  1M: 0.000000mg merged: 0.000000
epoch: 66 [2017-12-20 14:57:39]
 16M: 0.001549  8M: 0.002008  4M: 0.001757  2M: 0.001816  1M: 0.001900 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.003190 mg  4M: 0.002811 mg  2M: 0.003308 mg  1M: 0.000000mg merged: 0.000000
epoch: 67 [2017-12-20 15:00:09]
 16M: 0.001577  8M: 0.002035  4M: 0.001772  2M: 0.001811  1M: 0.001846 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002670 mg  4M: 0.002825 mg  2M: 0.003293 mg  1M: 0.000000mg merged: 0.000000
epoch: 68 [2017-12-20 15:02:43]
 16M: 0.001557  8M: 0.001993  4M: 0.001726  2M: 0.001763  1M: 0.001835 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002507 mg  4M: 0.002754 mg  2M: 0.003223 mg  1M: 0.000000mg merged: 0.000000
epoch: 69 [2017-12-20 15:05:14]
 16M: 0.001533  8M: 0.001962  4M: 0.001706  2M: 0.001740  1M: 0.001780 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002441 mg  4M: 0.002712 mg  2M: 0.003198 mg  1M: 0.000000mg merged: 0.000000
epoch: 70 [2017-12-20 15:07:53]
 16M: 0.001512  8M: 0.001918  4M: 0.001642  2M: 0.001659  1M: 0.001680 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002368 mg  4M: 0.002622 mg  2M: 0.003086 mg  1M: 0.000000mg merged: 0.000000
epoch: 71 [2017-12-20 15:10:21]
 16M: 0.001543  8M: 0.001959  4M: 0.001667  2M: 0.001687  1M: 0.001732 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002425 mg  4M: 0.002692 mg  2M: 0.003176 mg  1M: 0.000000mg merged: 0.000000
epoch: 72 [2017-12-20 15:12:59]
 16M: 0.001543  8M: 0.001986  4M: 0.001731  2M: 0.001774  1M: 0.001799 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002408 mg  4M: 0.002704 mg  2M: 0.003219 mg  1M: 0.000000mg merged: 0.000000
epoch: 73 [2017-12-20 15:15:39]
 16M: 0.001541  8M: 0.001958  4M: 0.001707  2M: 0.001740  1M: 0.001775 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002342 mg  4M: 0.002629 mg  2M: 0.003141 mg  1M: 0.000000mg merged: 0.000000
epoch: 74 [2017-12-20 15:18:28]
 16M: 0.001553  8M: 0.001964  4M: 0.001686  2M: 0.001710  1M: 0.001726 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002311 mg  4M: 0.002598 mg  2M: 0.003101 mg  1M: 0.000000mg merged: 0.000000
epoch: 75 [2017-12-20 15:21:22]
 16M: 0.001523  8M: 0.001935  4M: 0.001664  2M: 0.001682  1M: 0.001703 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002309 mg  4M: 0.002595 mg  2M: 0.003081 mg  1M: 0.000000mg merged: 0.000000
epoch: 76 [2017-12-20 15:24:04]
 16M: 0.001536  8M: 0.001943  4M: 0.001680  2M: 0.001703  1M: 0.001726 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002269 mg  4M: 0.002557 mg  2M: 0.003077 mg  1M: 0.000000mg merged: 0.000000
epoch: 77 [2017-12-20 15:26:34]
 16M: 0.001496  8M: 0.001890  4M: 0.001615  2M: 0.001634  1M: 0.001665 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002197 mg  4M: 0.002489 mg  2M: 0.003015 mg  1M: 0.000000mg merged: 0.000000
epoch: 78 [2017-12-20 15:29:08]
 16M: 0.001489  8M: 0.001894  4M: 0.001641  2M: 0.001716  1M: 0.001737 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002202 mg  4M: 0.002510 mg  2M: 0.003042 mg  1M: 0.000000mg merged: 0.000000
epoch: 79 [2017-12-20 15:31:43]
 16M: 0.001514  8M: 0.001914  4M: 0.001652  2M: 0.001690  1M: 0.001710 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002183 mg  4M: 0.002505 mg  2M: 0.003056 mg  1M: 0.000000mg merged: 0.000000
epoch: 80 [2017-12-20 15:34:32]
 16M: 0.001501  8M: 0.001897  4M: 0.001624  2M: 0.001664  1M: 0.001686 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002148 mg  4M: 0.002457 mg  2M: 0.003007 mg  1M: 0.000000mg merged: 0.000000
epoch: 81 [2017-12-20 15:37:13]
 16M: 0.001494  8M: 0.001876  4M: 0.001625  2M: 0.001656  1M: 0.001670 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002112 mg  4M: 0.002406 mg  2M: 0.002951 mg  1M: 0.000000mg merged: 0.000000
epoch: 82 [2017-12-20 15:39:55]
 16M: 0.001485  8M: 0.001875  4M: 0.001603  2M: 0.001630  1M: 0.001671 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002114 mg  4M: 0.002400 mg  2M: 0.002940 mg  1M: 0.000000mg merged: 0.000000
epoch: 83 [2017-12-20 15:42:34]
 16M: 0.001490  8M: 0.001870  4M: 0.001592  2M: 0.001634  1M: 0.001607 merged: 0.000000
 mg 16M: 0.000000 mg  8M: 0.002119 mg  4M: 0.002416 mg  2M: 0.002962 mg  1M: 0.000000mg merged: 0.000000
epoch: 84 [2017-12-20 15:45:16]
 16M: 0.001496  8M: 0.001884  4M: 0.001627  2M: 0.001669  1M: 0.001718 merged: 0.000000
 mg 16M: 0.001946 mg  8M: 0.002140 mg  4M: 0.002443 mg  2M: 0.003021 mg  1M: 0.000000mg merged: 0.000000
epoch: 85 [2017-12-20 15:49:22]
 16M: 0.001492  8M: 0.001861  4M: 0.001593  2M: 0.001641  1M: 0.001660 merged: 0.000000
 mg 16M: 0.001471 mg  8M: 0.002068 mg  4M: 0.002352 mg  2M: 0.002893 mg  1M: 0.000000mg merged: 0.000000
epoch: 86 [2017-12-20 15:53:19]
 16M: 0.001491  8M: 0.001863  4M: 0.001596  2M: 0.001613  1M: 0.001612 merged: 0.000000
 mg 16M: 0.001370 mg  8M: 0.002062 mg  4M: 0.002356 mg  2M: 0.002894 mg  1M: 0.000000mg merged: 0.000000
epoch: 87 [2017-12-20 15:57:17]
 16M: 0.001499  8M: 0.001854  4M: 0.001564  2M: 0.001602  1M: 0.001593 merged: 0.000000
 mg 16M: 0.001345 mg  8M: 0.002069 mg  4M: 0.002360 mg  2M: 0.002889 mg  1M: 0.000000mg merged: 0.000000
epoch: 88 [2017-12-20 16:01:25]
 16M: 0.001453  8M: 0.001810  4M: 0.001532  2M: 0.001557  1M: 0.001562 merged: 0.000000
 mg 16M: 0.001313 mg  8M: 0.002046 mg  4M: 0.002330 mg  2M: 0.002885 mg  1M: 0.000000mg merged: 0.000000
epoch: 89 [2017-12-20 16:05:35]
 16M: 0.001493  8M: 0.001850  4M: 0.001575  2M: 0.001590  1M: 0.001571 merged: 0.000000
 mg 16M: 0.001324 mg  8M: 0.002057 mg  4M: 0.002350 mg  2M: 0.002880 mg  1M: 0.000000mg merged: 0.000000
epoch: 90 [2017-12-20 16:09:37]
 16M: 0.001476  8M: 0.001857  4M: 0.001598  2M: 0.001613  1M: 0.001644 merged: 0.000000
 mg 16M: 0.001296 mg  8M: 0.002034 mg  4M: 0.002329 mg  2M: 0.002868 mg  1M: 0.000000mg merged: 0.000000
epoch: 91 [2017-12-20 16:13:39]
 16M: 0.001494  8M: 0.001860  4M: 0.001596  2M: 0.001629  1M: 0.001644 merged: 0.000000
 mg 16M: 0.001276 mg  8M: 0.002012 mg  4M: 0.002304 mg  2M: 0.002850 mg  1M: 0.000000mg merged: 0.000000
epoch: 92 [2017-12-20 16:17:38]
 16M: 0.001461  8M: 0.001796  4M: 0.001515  2M: 0.001557  1M: 0.001559 merged: 0.000000
 mg 16M: 0.001226 mg  8M: 0.001956 mg  4M: 0.002243 mg  2M: 0.002806 mg  1M: 0.000000mg merged: 0.000000
epoch: 93 [2017-12-20 16:21:42]
 16M: 0.001459  8M: 0.001805  4M: 0.001538  2M: 0.001560  1M: 0.001564 merged: 0.000000
 mg 16M: 0.001230 mg  8M: 0.001975 mg  4M: 0.002261 mg  2M: 0.002805 mg  1M: 0.000000mg merged: 0.000000
epoch: 94 [2017-12-20 16:25:45]
 16M: 0.001442  8M: 0.001780  4M: 0.001506  2M: 0.001528  1M: 0.001538 merged: 0.000000
 mg 16M: 0.001199 mg  8M: 0.001944 mg  4M: 0.002242 mg  2M: 0.002800 mg  1M: 0.000000mg merged: 0.000000
epoch: 95 [2017-12-20 16:29:55]
 16M: 0.001464  8M: 0.001795  4M: 0.001518  2M: 0.001530  1M: 0.001530 merged: 0.000000
 mg 16M: 0.001209 mg  8M: 0.001948 mg  4M: 0.002226 mg  2M: 0.002783 mg  1M: 0.000000mg merged: 0.000000
epoch: 96 [2017-12-20 16:34:01]
 16M: 0.001454  8M: 0.001796  4M: 0.001530  2M: 0.001576  1M: 0.001602 merged: 0.000000
 mg 16M: 0.001210 mg  8M: 0.001961 mg  4M: 0.002234 mg  2M: 0.002746 mg  1M: 0.000000mg merged: 0.000000
epoch: 97 [2017-12-20 16:37:58]
 16M: 0.001441  8M: 0.001789  4M: 0.001522  2M: 0.001568  1M: 0.001589 merged: 0.000000
 mg 16M: 0.001194 mg  8M: 0.001960 mg  4M: 0.002258 mg  2M: 0.002790 mg  1M: 0.000000mg merged: 0.000000
epoch: 98 [2017-12-20 16:41:54]
 16M: 0.001443  8M: 0.001782  4M: 0.001507  2M: 0.001562  1M: 0.001584 merged: 0.000000
 mg 16M: 0.001163 mg  8M: 0.001913 mg  4M: 0.002208 mg  2M: 0.002771 mg  1M: 0.000000mg merged: 0.000000
epoch: 99 [2017-12-20 16:46:00]
 16M: 0.001456  8M: 0.001795  4M: 0.001512  2M: 0.001546  1M: 0.001566 merged: 0.000000
 mg 16M: 0.001164 mg  8M: 0.001921 mg  4M: 0.002210 mg  2M: 0.002755 mg  1M: 0.000000mg merged: 0.000000
epoch: 100 [2017-12-20 16:50:09]
 16M: 0.001440  8M: 0.001776  4M: 0.001499  2M: 0.001509  1M: 0.001509 merged: 0.000000
 mg 16M: 0.001147 mg  8M: 0.001895 mg  4M: 0.002180 mg  2M: 0.002762 mg  1M: 0.000000mg merged: 0.000000
epoch: 101 [2017-12-20 16:54:11]
 16M: 0.001424  8M: 0.001749  4M: 0.001473  2M: 0.001497  1M: 0.001514 merged: 0.000000
 mg 16M: 0.001134 mg  8M: 0.001874 mg  4M: 0.002159 mg  2M: 0.002716 mg  1M: 0.000000mg merged: 0.000000
epoch: 102 [2017-12-20 16:57:55]
 16M: 0.001476  8M: 0.001813  4M: 0.001527  2M: 0.001546  1M: 0.001541 merged: 0.000000
 mg 16M: 0.001153 mg  8M: 0.001924 mg  4M: 0.002212 mg  2M: 0.002738 mg  1M: 0.000000mg merged: 0.001153
epoch: 103 [2017-12-20 17:02:57]
 16M: 0.001404  8M: 0.001724  4M: 0.001447  2M: 0.001483  1M: 0.001502 merged: 0.000000
 mg 16M: 0.001105 mg  8M: 0.001862 mg  4M: 0.002125 mg  2M: 0.002660 mg  1M: 0.000000mg merged: 0.001105
epoch: 104 [2017-12-20 17:08:03]
 16M: 0.001469  8M: 0.001794  4M: 0.001504  2M: 0.001542  1M: 0.001546 merged: 0.000000
 mg 16M: 0.001115 mg  8M: 0.001903 mg  4M: 0.002184 mg  2M: 0.002736 mg  1M: 0.000000mg merged: 0.001115
epoch: 105 [2017-12-20 17:13:22]
 16M: 0.001432  8M: 0.001758  4M: 0.001495  2M: 0.001532  1M: 0.001543 merged: 0.000000
 mg 16M: 0.001076 mg  8M: 0.001862 mg  4M: 0.002155 mg  2M: 0.002715 mg  1M: 0.000000mg merged: 0.001076
epoch: 106 [2017-12-20 17:18:28]
 16M: 0.001411  8M: 0.001741  4M: 0.001483  2M: 0.001545  1M: 0.001562 merged: 0.000000
 mg 16M: 0.001057 mg  8M: 0.001861 mg  4M: 0.002158 mg  2M: 0.002765 mg  1M: 0.000000mg merged: 0.001057
epoch: 107 [2017-12-20 17:23:31]
 16M: 0.001397  8M: 0.001725  4M: 0.001473  2M: 0.001515  1M: 0.001524 merged: 0.000000
 mg 16M: 0.001041 mg  8M: 0.001850 mg  4M: 0.002126 mg  2M: 0.002673 mg  1M: 0.000000mg merged: 0.001041
epoch: 108 [2017-12-20 17:28:39]
 16M: 0.001403  8M: 0.001729  4M: 0.001482  2M: 0.001511  1M: 0.001529 merged: 0.000000
 mg 16M: 0.001025 mg  8M: 0.001823 mg  4M: 0.002115 mg  2M: 0.002640 mg  1M: 0.000000mg merged: 0.001025
epoch: 109 [2017-12-20 17:33:50]
 16M: 0.001423  8M: 0.001744  4M: 0.001481  2M: 0.001537  1M: 0.001540 merged: 0.000000
 mg 16M: 0.001020 mg  8M: 0.001818 mg  4M: 0.002119 mg  2M: 0.002688 mg  1M: 0.000000mg merged: 0.001020
epoch: 110 [2017-12-20 17:39:05]
 16M: 0.001384  8M: 0.001688  4M: 0.001418  2M: 0.001471  1M: 0.001486 merged: 0.000000
 mg 16M: 0.000994 mg  8M: 0.001779 mg  4M: 0.002054 mg  2M: 0.002613 mg  1M: 0.000000mg merged: 0.000994
epoch: 111 [2017-12-20 17:44:11]
 16M: 0.001425  8M: 0.001742  4M: 0.001469  2M: 0.001514  1M: 0.001526 merged: 0.000000
 mg 16M: 0.001014 mg  8M: 0.001809 mg  4M: 0.002096 mg  2M: 0.002672 mg  1M: 0.000000mg merged: 0.001014
epoch: 112 [2017-12-20 17:49:17]
 16M: 0.001390  8M: 0.001701  4M: 0.001445  2M: 0.001495  1M: 0.001506 merged: 0.000000
 mg 16M: 0.000970 mg  8M: 0.001751 mg  4M: 0.002034 mg  2M: 0.002606 mg  1M: 0.000000mg merged: 0.000970
epoch: 113 [2017-12-20 17:54:26]
 16M: 0.001408  8M: 0.001721  4M: 0.001449  2M: 0.001492  1M: 0.001493 merged: 0.000000
 mg 16M: 0.000999 mg  8M: 0.001808 mg  4M: 0.002085 mg  2M: 0.002658 mg  1M: 0.000000mg merged: 0.000999
epoch: 114 [2017-12-20 17:59:33]
 16M: 0.001387  8M: 0.001687  4M: 0.001439  2M: 0.001489  1M: 0.001508 merged: 0.000000
 mg 16M: 0.000969 mg  8M: 0.001761 mg  4M: 0.002061 mg  2M: 0.002656 mg  1M: 0.000000mg merged: 0.000969
epoch: 115 [2017-12-20 18:04:44]
 16M: 0.001417  8M: 0.001722  4M: 0.001458  2M: 0.001506  1M: 0.001482 merged: 0.000000
 mg 16M: 0.000978 mg  8M: 0.001781 mg  4M: 0.002070 mg  2M: 0.002656 mg  1M: 0.000000mg merged: 0.000978
epoch: 116 [2017-12-20 18:09:52]
 16M: 0.001378  8M: 0.001696  4M: 0.001433  2M: 0.001475  1M: 0.001475 merged: 0.000000
 mg 16M: 0.000959 mg  8M: 0.001761 mg  4M: 0.002051 mg  2M: 0.002604 mg  1M: 0.000000mg merged: 0.000959
epoch: 117 [2017-12-20 18:14:57]
 16M: 0.001348  8M: 0.001657  4M: 0.001412  2M: 0.001460  1M: 0.001470 merged: 0.000000
 mg 16M: 0.000930 mg  8M: 0.001711 mg  4M: 0.001997 mg  2M: 0.002567 mg  1M: 0.000000mg merged: 0.000930
epoch: 118 [2017-12-20 18:20:09]
 16M: 0.001362  8M: 0.001663  4M: 0.001398  2M: 0.001437  1M: 0.001447 merged: 0.000000
 mg 16M: 0.000939 mg  8M: 0.001721 mg  4M: 0.001980 mg  2M: 0.002508 mg  1M: 0.000000mg merged: 0.000939
epoch: 119 [2017-12-20 18:25:15]
 16M: 0.001387  8M: 0.001685  4M: 0.001421  2M: 0.001437  1M: 0.001416 merged: 0.000000
 mg 16M: 0.000955 mg  8M: 0.001753 mg  4M: 0.002024 mg  2M: 0.002566 mg  1M: 0.000000mg merged: 0.000955
epoch: 120 [2017-12-20 18:30:31]
 16M: 0.001354  8M: 0.001641  4M: 0.001374  2M: 0.001402  1M: 0.001403 merged: 0.000000
 mg 16M: 0.000926 mg  8M: 0.001702 mg  4M: 0.001959 mg  2M: 0.002493 mg  1M: 0.000000mg merged: 0.000926
epoch: 121 [2017-12-20 18:35:35]
 16M: 0.001342  8M: 0.001637  4M: 0.001385  2M: 0.001435  1M: 0.001418 merged: 0.000000
 mg 16M: 0.000918 mg  8M: 0.001697 mg  4M: 0.001965 mg  2M: 0.002531 mg  1M: 0.000000mg merged: 0.000918
epoch: 122 [2017-12-20 18:40:42]
 16M: 0.001358  8M: 0.001648  4M: 0.001384  2M: 0.001433  1M: 0.001416 merged: 0.000000
 mg 16M: 0.000920 mg  8M: 0.001698 mg  4M: 0.001960 mg  2M: 0.002516 mg  1M: 0.000000mg merged: 0.000920
epoch: 123 [2017-12-20 18:45:46]
 16M: 0.001315  8M: 0.001611  4M: 0.001366  2M: 0.001412  1M: 0.001407 merged: 0.000000
 mg 16M: 0.000890 mg  8M: 0.001661 mg  4M: 0.001935 mg  2M: 0.002506 mg  1M: 0.000000mg merged: 0.000890
epoch: 124 [2017-12-20 18:50:51]
 16M: 0.001332  8M: 0.001622  4M: 0.001368  2M: 0.001410  1M: 0.001397 merged: 0.000000
 mg 16M: 0.000901 mg  8M: 0.001681 mg  4M: 0.001943 mg  2M: 0.002477 mg  1M: 0.000000mg merged: 0.000901
epoch: 125 [2017-12-20 18:56:10]
 16M: 0.001343  8M: 0.001624  4M: 0.001354  2M: 0.001400  1M: 0.001383 merged: 0.000000
 mg 16M: 0.000907 mg  8M: 0.001693 mg  4M: 0.001968 mg  2M: 0.002528 mg  1M: 0.000000mg merged: 0.000907
epoch: 126 [2017-12-20 19:01:18]
 16M: 0.001327  8M: 0.001614  4M: 0.001349  2M: 0.001400  1M: 0.001376 merged: 0.000000
 mg 16M: 0.000888 mg  8M: 0.001654 mg  4M: 0.001912 mg  2M: 0.002466 mg  1M: 0.000000mg merged: 0.000888
epoch: 127 [2017-12-20 19:06:27]
 16M: 0.001337  8M: 0.001622  4M: 0.001354  2M: 0.001394  1M: 0.001390 merged: 0.000000
 mg 16M: 0.000901 mg  8M: 0.001697 mg  4M: 0.001965 mg  2M: 0.002521 mg  1M: 0.000000mg merged: 0.000901
epoch: 128 [2017-12-20 19:11:32]
 16M: 0.001321  8M: 0.001591  4M: 0.001333  2M: 0.001368  1M: 0.001370 merged: 0.000000
 mg 16M: 0.000884 mg  8M: 0.001636 mg  4M: 0.001884 mg  2M: 0.002425 mg  1M: 0.000000mg merged: 0.000884
epoch: 129 [2017-12-20 19:16:46]
 16M: 0.001338  8M: 0.001625  4M: 0.001343  2M: 0.001362  1M: 0.001351 merged: 0.000000
 mg 16M: 0.000890 mg  8M: 0.001665 mg  4M: 0.001923 mg  2M: 0.002471 mg  1M: 0.000000mg merged: 0.000890
epoch: 130 [2017-12-20 19:22:16]
 16M: 0.001311  8M: 0.001594  4M: 0.001330  2M: 0.001363  1M: 0.001359 merged: 0.000000
 mg 16M: 0.000871 mg  8M: 0.001625 mg  4M: 0.001883 mg  2M: 0.002425 mg  1M: 0.000000mg merged: 0.000871
epoch: 131 [2017-12-20 19:27:25]
 16M: 0.001322  8M: 0.001594  4M: 0.001329  2M: 0.001359  1M: 0.001343 merged: 0.000000
 mg 16M: 0.000876 mg  8M: 0.001640 mg  4M: 0.001880 mg  2M: 0.002401 mg  1M: 0.000000mg merged: 0.000876
epoch: 132 [2017-12-20 19:32:28]
 16M: 0.001309  8M: 0.001587  4M: 0.001324  2M: 0.001355  1M: 0.001336 merged: 0.000000
 mg 16M: 0.000869 mg  8M: 0.001634 mg  4M: 0.001889 mg  2M: 0.002419 mg  1M: 0.000000mg merged: 0.000869
epoch: 133 [2017-12-20 19:37:38]
 16M: 0.001303  8M: 0.001570  4M: 0.001290  2M: 0.001339  1M: 0.001302 merged: 0.000000
 mg 16M: 0.000859 mg  8M: 0.001610 mg  4M: 0.001862 mg  2M: 0.002392 mg  1M: 0.000000mg merged: 0.000859
epoch: 134 [2017-12-20 19:42:55]
 16M: 0.001309  8M: 0.001568  4M: 0.001300  2M: 0.001340  1M: 0.001324 merged: 0.000000
 mg 16M: 0.000864 mg  8M: 0.001616 mg  4M: 0.001859 mg  2M: 0.002404 mg  1M: 0.000000mg merged: 0.000864
epoch: 135 [2017-12-20 19:48:12]
 16M: 0.001309  8M: 0.001574  4M: 0.001299  2M: 0.001313  1M: 0.001288 merged: 0.000000
 mg 16M: 0.000864 mg  8M: 0.001623 mg  4M: 0.001854 mg  2M: 0.002379 mg  1M: 0.000000mg merged: 0.000864
epoch: 136 [2017-12-20 19:53:16]
 16M: 0.001287  8M: 0.001556  4M: 0.001280  2M: 0.001318  1M: 0.001292 merged: 0.000000
 mg 16M: 0.000854 mg  8M: 0.001604 mg  4M: 0.001835 mg  2M: 0.002344 mg  1M: 0.000000mg merged: 0.000854
epoch: 137 [2017-12-20 19:58:25]
 16M: 0.001271  8M: 0.001536  4M: 0.001269  2M: 0.001310  1M: 0.001292 merged: 0.000000
 mg 16M: 0.000841 mg  8M: 0.001601 mg  4M: 0.001839 mg  2M: 0.002373 mg  1M: 0.000000mg merged: 0.000841
epoch: 138 [2017-12-20 20:03:34]
 16M: 0.001295  8M: 0.001558  4M: 0.001294  2M: 0.001333  1M: 0.001303 merged: 0.000000
 mg 16M: 0.000852 mg  8M: 0.001616 mg  4M: 0.001856 mg  2M: 0.002396 mg  1M: 0.000000mg merged: 0.000852
epoch: 139 [2017-12-20 20:08:42]
 16M: 0.001300  8M: 0.001582  4M: 0.001316  2M: 0.001349  1M: 0.001304 merged: 0.000000
 mg 16M: 0.000857 mg  8M: 0.001624 mg  4M: 0.001877 mg  2M: 0.002439 mg  1M: 0.000000mg merged: 0.000857
epoch: 140 [2017-12-20 20:13:57]
 16M: 0.001306  8M: 0.001569  4M: 0.001298  2M: 0.001327  1M: 0.001309 merged: 0.000000
 mg 16M: 0.000854 mg  8M: 0.001602 mg  4M: 0.001831 mg  2M: 0.002350 mg  1M: 0.000000mg merged: 0.000854
epoch: 141 [2017-12-20 20:19:00]
 16M: 0.001284  8M: 0.001551  4M: 0.001271  2M: 0.001296  1M: 0.001284 merged: 0.000000
 mg 16M: 0.000845 mg  8M: 0.001605 mg  4M: 0.001843 mg  2M: 0.002363 mg  1M: 0.000000mg merged: 0.000845
epoch: 142 [2017-12-20 20:24:11]
 16M: 0.001268  8M: 0.001525  4M: 0.001250  2M: 0.001293  1M: 0.001247 merged: 0.000000
 mg 16M: 0.000831 mg  8M: 0.001582 mg  4M: 0.001818 mg  2M: 0.002334 mg  1M: 0.000000mg merged: 0.000831
epoch: 143 [2017-12-20 20:29:20]
 16M: 0.001269  8M: 0.001529  4M: 0.001263  2M: 0.001301  1M: 0.001294 merged: 0.000000
 mg 16M: 0.000829 mg  8M: 0.001574 mg  4M: 0.001809 mg  2M: 0.002344 mg  1M: 0.000000mg merged: 0.000829
epoch: 144 [2017-12-20 20:34:26]
 16M: 0.001278  8M: 0.001554  4M: 0.001293  2M: 0.001315  1M: 0.001295 merged: 0.000000
 mg 16M: 0.000836 mg  8M: 0.001597 mg  4M: 0.001842 mg  2M: 0.002374 mg  1M: 0.000000mg merged: 0.000836
epoch: 145 [2017-12-20 20:39:38]
 16M: 0.001254  8M: 0.001523  4M: 0.001269  2M: 0.001283  1M: 0.001234 merged: 0.000000
 mg 16M: 0.000818 mg  8M: 0.001557 mg  4M: 0.001788 mg  2M: 0.002284 mg  1M: 0.000000mg merged: 0.000818
epoch: 146 [2017-12-20 20:44:48]
 16M: 0.001293  8M: 0.001565  4M: 0.001293  2M: 0.001319  1M: 0.001269 merged: 0.000000
 mg 16M: 0.000840 mg  8M: 0.001595 mg  4M: 0.001827 mg  2M: 0.002342 mg  1M: 0.000000mg merged: 0.000840
epoch: 147 [2017-12-20 20:49:58]
 16M: 0.001228  8M: 0.001485  4M: 0.001225  2M: 0.001260  1M: 0.001255 merged: 0.000000
 mg 16M: 0.000801 mg  8M: 0.001534 mg  4M: 0.001766 mg  2M: 0.002265 mg  1M: 0.000000mg merged: 0.000801
epoch: 148 [2017-12-20 20:55:05]
 16M: 0.001245  8M: 0.001514  4M: 0.001259  2M: 0.001302  1M: 0.001302 merged: 0.000000
 mg 16M: 0.000802 mg  8M: 0.001540 mg  4M: 0.001784 mg  2M: 0.002302 mg  1M: 0.000000mg merged: 0.000802
epoch: 149 [2017-12-20 21:00:11]
 16M: 0.001262  8M: 0.001524  4M: 0.001255  2M: 0.001273  1M: 0.001238 merged: 0.000000
 mg 16M: 0.000829 mg  8M: 0.001584 mg  4M: 0.001806 mg  2M: 0.002307 mg  1M: 0.000000mg merged: 0.000829
epoch: 150 [2017-12-20 21:05:24]
 16M: 0.001261  8M: 0.001528  4M: 0.001276  2M: 0.001293  1M: 0.001269 merged: 0.000000
 mg 16M: 0.000813 mg  8M: 0.001554 mg  4M: 0.001795 mg  2M: 0.002333 mg  1M: 0.000000mg merged: 0.000813
epoch: 151 [2017-12-20 21:10:27]
 16M: 0.001258  8M: 0.001522  4M: 0.001254  2M: 0.001298  1M: 0.001239 merged: 0.000000
 mg 16M: 0.000819 mg  8M: 0.001572 mg  4M: 0.001806 mg  2M: 0.002336 mg  1M: 0.000000mg merged: 0.000819
epoch: 152 [2017-12-20 21:15:35]
 16M: 0.001268  8M: 0.001524  4M: 0.001255  2M: 0.001283  1M: 0.001232 merged: 0.000000
 mg 16M: 0.000823 mg  8M: 0.001568 mg  4M: 0.001810 mg  2M: 0.002345 mg  1M: 0.000000mg merged: 0.000823
epoch: 153 [2017-12-20 21:20:43]
 16M: 0.001254  8M: 0.001517  4M: 0.001255  2M: 0.001286  1M: 0.001257 merged: 0.000000
 mg 16M: 0.000815 mg  8M: 0.001550 mg  4M: 0.001781 mg  2M: 0.002296 mg  1M: 0.000000mg merged: 0.000815
epoch: 154 [2017-12-20 21:25:54]
 16M: 0.001240  8M: 0.001500  4M: 0.001235  2M: 0.001266  1M: 0.001228 merged: 0.000000
 mg 16M: 0.000799 mg  8M: 0.001533 mg  4M: 0.001766 mg  2M: 0.002282 mg  1M: 0.000000mg merged: 0.000799
epoch: 155 [2017-12-20 21:31:08]
 16M: 0.001238  8M: 0.001496  4M: 0.001218  2M: 0.001241  1M: 0.001221 merged: 0.000000
 mg 16M: 0.000799 mg  8M: 0.001521 mg  4M: 0.001743 mg  2M: 0.002227 mg  1M: 0.000000mg merged: 0.000799
epoch: 156 [2017-12-20 21:36:24]
 16M: 0.001218  8M: 0.001471  4M: 0.001221  2M: 0.001252  1M: 0.001222 merged: 0.000000
 mg 16M: 0.000787 mg  8M: 0.001514 mg  4M: 0.001727 mg  2M: 0.002229 mg  1M: 0.000000mg merged: 0.000787
epoch: 157 [2017-12-20 21:41:42]
 16M: 0.001255  8M: 0.001504  4M: 0.001230  2M: 0.001264  1M: 0.001240 merged: 0.000000
 mg 16M: 0.000812 mg  8M: 0.001552 mg  4M: 0.001771 mg  2M: 0.002286 mg  1M: 0.000000mg merged: 0.000812
epoch: 158 [2017-12-20 21:46:47]
 16M: 0.001241  8M: 0.001498  4M: 0.001230  2M: 0.001248  1M: 0.001188 merged: 0.000000
 mg 16M: 0.000804 mg  8M: 0.001542 mg  4M: 0.001761 mg  2M: 0.002268 mg  1M: 0.000000mg merged: 0.000804
epoch: 159 [2017-12-20 21:52:08]
 16M: 0.001226  8M: 0.001472  4M: 0.001201  2M: 0.001213  1M: 0.001176 merged: 0.000000
 mg 16M: 0.000794 mg  8M: 0.001522 mg  4M: 0.001737 mg  2M: 0.002232 mg  1M: 0.000000mg merged: 0.000794
epoch: 160 [2017-12-20 21:57:17]
 16M: 0.001228  8M: 0.001475  4M: 0.001207  2M: 0.001224  1M: 0.001165 merged: 0.000000
 mg 16M: 0.000798 mg  8M: 0.001531 mg  4M: 0.001739 mg  2M: 0.002207 mg  1M: 0.000000mg merged: 0.000798
epoch: 161 [2017-12-20 22:02:16]
 16M: 0.001214  8M: 0.001468  4M: 0.001203  2M: 0.001228  1M: 0.001176 merged: 0.000000
 mg 16M: 0.000787 mg  8M: 0.001511 mg  4M: 0.001726 mg  2M: 0.002205 mg  1M: 0.000000mg merged: 0.000787
epoch: 162 [2017-12-20 22:07:40]
 16M: 0.001210  8M: 0.001453  4M: 0.001197  2M: 0.001216  1M: 0.001189 merged: 0.000000
 mg 16M: 0.000782 mg  8M: 0.001506 mg  4M: 0.001714 mg  2M: 0.002177 mg  1M: 0.000000mg merged: 0.000782
epoch: 163 [2017-12-20 22:13:00]
 16M: 0.001223  8M: 0.001485  4M: 0.001221  2M: 0.001243  1M: 0.001205 merged: 0.000000
 mg 16M: 0.000787 mg  8M: 0.001505 mg  4M: 0.001724 mg  2M: 0.002218 mg  1M: 0.000000mg merged: 0.000787
epoch: 164 [2017-12-20 22:18:07]
 16M: 0.001240  8M: 0.001498  4M: 0.001222  2M: 0.001238  1M: 0.001192 merged: 0.000000
 mg 16M: 0.000797 mg  8M: 0.001539 mg  4M: 0.001761 mg  2M: 0.002256 mg  1M: 0.000000mg merged: 0.000797
epoch: 165 [2017-12-20 22:23:28]
 16M: 0.001236  8M: 0.001487  4M: 0.001224  2M: 0.001247  1M: 0.001190 merged: 0.000000
 mg 16M: 0.000798 mg  8M: 0.001526 mg  4M: 0.001746 mg  2M: 0.002244 mg  1M: 0.000000mg merged: 0.000798
epoch: 166 [2017-12-20 22:28:42]
 16M: 0.001223  8M: 0.001476  4M: 0.001203  2M: 0.001219  1M: 0.001165 merged: 0.000000
 mg 16M: 0.000788 mg  8M: 0.001518 mg  4M: 0.001737 mg  2M: 0.002239 mg  1M: 0.000000mg merged: 0.000788
epoch: 167 [2017-12-20 22:33:54]
 16M: 0.001240  8M: 0.001492  4M: 0.001220  2M: 0.001242  1M: 0.001194 merged: 0.000000
 mg 16M: 0.000799 mg  8M: 0.001535 mg  4M: 0.001753 mg  2M: 0.002250 mg  1M: 0.000000mg merged: 0.000799
epoch: 168 [2017-12-20 22:39:04]
 16M: 0.001208  8M: 0.001457  4M: 0.001202  2M: 0.001215  1M: 0.001182 merged: 0.000000
 mg 16M: 0.000781 mg  8M: 0.001505 mg  4M: 0.001720 mg  2M: 0.002192 mg  1M: 0.000000mg merged: 0.000781
epoch: 169 [2017-12-20 22:44:17]
 16M: 0.001248  8M: 0.001496  4M: 0.001218  2M: 0.001233  1M: 0.001172 merged: 0.000000
 mg 16M: 0.000801 mg  8M: 0.001531 mg  4M: 0.001742 mg  2M: 0.002225 mg  1M: 0.000000mg merged: 0.000801
epoch: 170 [2017-12-20 22:49:44]
 16M: 0.001220  8M: 0.001462  4M: 0.001193  2M: 0.001217  1M: 0.001154 merged: 0.000000
 mg 16M: 0.000784 mg  8M: 0.001514 mg  4M: 0.001727 mg  2M: 0.002222 mg  1M: 0.000000mg merged: 0.000784
epoch: 171 [2017-12-20 22:54:52]
 16M: 0.001205  8M: 0.001457  4M: 0.001194  2M: 0.001208  1M: 0.001150 merged: 0.000000
 mg 16M: 0.000779 mg  8M: 0.001502 mg  4M: 0.001716 mg  2M: 0.002198 mg  1M: 0.000000mg merged: 0.000779
epoch: 172 [2017-12-20 23:00:04]
 16M: 0.001212  8M: 0.001459  4M: 0.001194  2M: 0.001217  1M: 0.001162 merged: 0.000000
 mg 16M: 0.000780 mg  8M: 0.001502 mg  4M: 0.001726 mg  2M: 0.002229 mg  1M: 0.000000mg merged: 0.000780
epoch: 173 [2017-12-20 23:05:11]
 16M: 0.001190  8M: 0.001440  4M: 0.001174  2M: 0.001199  1M: 0.001153 merged: 0.000000
 mg 16M: 0.000765 mg  8M: 0.001481 mg  4M: 0.001694 mg  2M: 0.002178 mg  1M: 0.000000mg merged: 0.000765
epoch: 174 [2017-12-20 23:10:14]
 16M: 0.001208  8M: 0.001454  4M: 0.001195  2M: 0.001227  1M: 0.001182 merged: 0.000000
 mg 16M: 0.000780 mg  8M: 0.001505 mg  4M: 0.001723 mg  2M: 0.002231 mg  1M: 0.000000mg merged: 0.000780
epoch: 175 [2017-12-20 23:15:31]
 16M: 0.001197  8M: 0.001435  4M: 0.001165  2M: 0.001194  1M: 0.001145 merged: 0.000000
 mg 16M: 0.000774 mg  8M: 0.001490 mg  4M: 0.001684 mg  2M: 0.002131 mg  1M: 0.000000mg merged: 0.000774
epoch: 176 [2017-12-20 23:20:32]
 16M: 0.001197  8M: 0.001437  4M: 0.001183  2M: 0.001199  1M: 0.001144 merged: 0.000000
 mg 16M: 0.000765 mg  8M: 0.001472 mg  4M: 0.001680 mg  2M: 0.002144 mg  1M: 0.000000mg merged: 0.000765
epoch: 177 [2017-12-20 23:25:45]
 16M: 0.001210  8M: 0.001461  4M: 0.001187  2M: 0.001207  1M: 0.001154 merged: 0.000000
 mg 16M: 0.000780 mg  8M: 0.001509 mg  4M: 0.001721 mg  2M: 0.002197 mg  1M: 0.000000mg merged: 0.000780
epoch: 178 [2017-12-20 23:30:54]
 16M: 0.001202  8M: 0.001438  4M: 0.001174  2M: 0.001191  1M: 0.001121 merged: 0.000000
 mg 16M: 0.000773 mg  8M: 0.001483 mg  4M: 0.001687 mg  2M: 0.002174 mg  1M: 0.000000mg merged: 0.000773
epoch: 179 [2017-12-20 23:36:03]
 16M: 0.001184  8M: 0.001413  4M: 0.001152  2M: 0.001166  1M: 0.001119 merged: 0.000000
 mg 16M: 0.000761 mg  8M: 0.001467 mg  4M: 0.001665 mg  2M: 0.002119 mg  1M: 0.000000mg merged: 0.000761
epoch: 180 [2017-12-20 23:41:16]
 16M: 0.001179  8M: 0.001421  4M: 0.001152  2M: 0.001164  1M: 0.001107 merged: 0.000000
 mg 16M: 0.000758 mg  8M: 0.001466 mg  4M: 0.001662 mg  2M: 0.002127 mg  1M: 0.000000mg merged: 0.000758
epoch: 181 [2017-12-20 23:46:27]
 16M: 0.001195  8M: 0.001442  4M: 0.001185  2M: 0.001207  1M: 0.001143 merged: 0.000000
 mg 16M: 0.000758 mg  8M: 0.001460 mg  4M: 0.001684 mg  2M: 0.002177 mg  1M: 0.000000mg merged: 0.000758
epoch: 182 [2017-12-20 23:51:30]
 16M: 0.001174  8M: 0.001420  4M: 0.001157  2M: 0.001176  1M: 0.001114 merged: 0.000000
 mg 16M: 0.000751 mg  8M: 0.001453 mg  4M: 0.001664 mg  2M: 0.002150 mg  1M: 0.000000mg merged: 0.000751
epoch: 183 [2017-12-20 23:56:41]
 16M: 0.001183  8M: 0.001418  4M: 0.001146  2M: 0.001163  1M: 0.001106 merged: 0.000000
 mg 16M: 0.000760 mg  8M: 0.001470 mg  4M: 0.001667 mg  2M: 0.002139 mg  1M: 0.000000mg merged: 0.000760
epoch: 184 [2017-12-21 00:01:52]
 16M: 0.001170  8M: 0.001411  4M: 0.001148  2M: 0.001178  1M: 0.001111 merged: 0.000000
 mg 16M: 0.000743 mg  8M: 0.001446 mg  4M: 0.001649 mg  2M: 0.002132 mg  1M: 0.000000mg merged: 0.000743
epoch: 185 [2017-12-21 00:07:03]
 16M: 0.001180  8M: 0.001426  4M: 0.001158  2M: 0.001171  1M: 0.001110 merged: 0.000000
 mg 16M: 0.000759 mg  8M: 0.001472 mg  4M: 0.001679 mg  2M: 0.002153 mg  1M: 0.000000mg merged: 0.000759
epoch: 186 [2017-12-21 00:12:13]
 16M: 0.001176  8M: 0.001426  4M: 0.001163  2M: 0.001188  1M: 0.001122 merged: 0.000000
 mg 16M: 0.000752 mg  8M: 0.001464 mg  4M: 0.001675 mg  2M: 0.002155 mg  1M: 0.000000mg merged: 0.000752
epoch: 187 [2017-12-21 00:17:29]
 16M: 0.001137  8M: 0.001378  4M: 0.001128  2M: 0.001154  1M: 0.001101 merged: 0.000000
 mg 16M: 0.000729 mg  8M: 0.001424 mg  4M: 0.001631 mg  2M: 0.002097 mg  1M: 0.000000mg merged: 0.000729
epoch: 188 [2017-12-21 00:22:44]
 16M: 0.001171  8M: 0.001413  4M: 0.001149  2M: 0.001169  1M: 0.001126 merged: 0.000000
 mg 16M: 0.000751 mg  8M: 0.001455 mg  4M: 0.001659 mg  2M: 0.002126 mg  1M: 0.000000mg merged: 0.000751
epoch: 189 [2017-12-21 00:27:53]
 16M: 0.001174  8M: 0.001416  4M: 0.001157  2M: 0.001165  1M: 0.001096 merged: 0.000000
 mg 16M: 0.000746 mg  8M: 0.001446 mg  4M: 0.001652 mg  2M: 0.002119 mg  1M: 0.000000mg merged: 0.000746
epoch: 190 [2017-12-21 00:33:08]
 16M: 0.001168  8M: 0.001410  4M: 0.001147  2M: 0.001159  1M: 0.001107 merged: 0.000000
 mg 16M: 0.000746 mg  8M: 0.001453 mg  4M: 0.001657 mg  2M: 0.002134 mg  1M: 0.000000mg merged: 0.000746
epoch: 191 [2017-12-21 00:38:17]
 16M: 0.001166  8M: 0.001410  4M: 0.001146  2M: 0.001162  1M: 0.001109 merged: 0.000000
 mg 16M: 0.000738 mg  8M: 0.001431 mg  4M: 0.001640 mg  2M: 0.002094 mg  1M: 0.000000mg merged: 0.000738
epoch: 192 [2017-12-21 00:43:27]
 16M: 0.001145  8M: 0.001390  4M: 0.001132  2M: 0.001148  1M: 0.001076 merged: 0.000000
 mg 16M: 0.000732 mg  8M: 0.001423 mg  4M: 0.001623 mg  2M: 0.002078 mg  1M: 0.000000mg merged: 0.000732
epoch: 193 [2017-12-21 00:48:36]
 16M: 0.001186  8M: 0.001420  4M: 0.001146  2M: 0.001154  1M: 0.001080 merged: 0.000000
 mg 16M: 0.000753 mg  8M: 0.001455 mg  4M: 0.001658 mg  2M: 0.002125 mg  1M: 0.000000mg merged: 0.000753
epoch: 194 [2017-12-21 00:53:46]
 16M: 0.001170  8M: 0.001417  4M: 0.001153  2M: 0.001162  1M: 0.001085 merged: 0.000000
 mg 16M: 0.000744 mg  8M: 0.001444 mg  4M: 0.001646 mg  2M: 0.002125 mg  1M: 0.000000mg merged: 0.000744
epoch: 195 [2017-12-21 00:59:07]
 16M: 0.001169  8M: 0.001403  4M: 0.001126  2M: 0.001141  1M: 0.001106 merged: 0.000000
 mg 16M: 0.000750 mg  8M: 0.001453 mg  4M: 0.001654 mg  2M: 0.002102 mg  1M: 0.000000mg merged: 0.000750
epoch: 196 [2017-12-21 01:04:16]
 16M: 0.001163  8M: 0.001407  4M: 0.001138  2M: 0.001138  1M: 0.001076 merged: 0.000000
 mg 16M: 0.000745 mg  8M: 0.001442 mg  4M: 0.001636 mg  2M: 0.002094 mg  1M: 0.000000mg merged: 0.000745
epoch: 197 [2017-12-21 01:09:29]
 16M: 0.001155  8M: 0.001386  4M: 0.001129  2M: 0.001146  1M: 0.001103 merged: 0.000000
 mg 16M: 0.000734 mg  8M: 0.001428 mg  4M: 0.001625 mg  2M: 0.002098 mg  1M: 0.000000mg merged: 0.000734
epoch: 198 [2017-12-21 01:14:36]
 16M: 0.001178  8M: 0.001417  4M: 0.001145  2M: 0.001145  1M: 0.001085 merged: 0.000000
 mg 16M: 0.000750 mg  8M: 0.001459 mg  4M: 0.001657 mg  2M: 0.002118 mg  1M: 0.000000mg merged: 0.000750
epoch: 199 [2017-12-21 01:19:41]
 16M: 0.001163  8M: 0.001404  4M: 0.001137  2M: 0.001157  1M: 0.001109 merged: 0.000000
 mg 16M: 0.000743 mg  8M: 0.001442 mg  4M: 0.001644 mg  2M: 0.002103 mg  1M: 0.000000mg merged: 0.000743
epoch: 200 [2017-12-21 01:25:03]
 16M: 0.001124  8M: 0.001363  4M: 0.001118  2M: 0.001142  1M: 0.001086 merged: 0.000000
 mg 16M: 0.000713 mg  8M: 0.001390 mg  4M: 0.001596 mg  2M: 0.002079 mg  1M: 0.000000mg merged: 0.000713
epoch: 201 [2017-12-21 01:30:07]
 16M: 0.001172  8M: 0.001413  4M: 0.001146  2M: 0.001146  1M: 0.001074 merged: 0.000000
 mg 16M: 0.000747 mg  8M: 0.001455 mg  4M: 0.001657 mg  2M: 0.002123 mg  1M: 0.000000mg merged: 0.000747
epoch: 202 [2017-12-21 01:35:23]
 16M: 0.001169  8M: 0.001398  4M: 0.001130  2M: 0.001133  1M: 0.001060 merged: 0.000000
 mg 16M: 0.000735 mg  8M: 0.001423 mg  4M: 0.001624 mg  2M: 0.002109 mg  1M: 0.000000mg merged: 0.000735
epoch: 203 [2017-12-21 01:40:38]
 16M: 0.001150  8M: 0.001381  4M: 0.001120  2M: 0.001133  1M: 0.001064 merged: 0.000000
 mg 16M: 0.000739 mg  8M: 0.001441 mg  4M: 0.001636 mg  2M: 0.002082 mg  1M: 0.000000mg merged: 0.000739
epoch: 204 [2017-12-21 01:45:47]
 16M: 0.001138  8M: 0.001374  4M: 0.001111  2M: 0.001122  1M: 0.001075 merged: 0.000000
 mg 16M: 0.000727 mg  8M: 0.001423 mg  4M: 0.001614 mg  2M: 0.002073 mg  1M: 0.000000mg merged: 0.000727
epoch: 205 [2017-12-21 01:51:06]
 16M: 0.001131  8M: 0.001364  4M: 0.001104  2M: 0.001107  1M: 0.001040 merged: 0.000000
 mg 16M: 0.000720 mg  8M: 0.001398 mg  4M: 0.001588 mg  2M: 0.002036 mg  1M: 0.000000mg merged: 0.000720
epoch: 206 [2017-12-21 01:56:13]
 16M: 0.001138  8M: 0.001359  4M: 0.001093  2M: 0.001102  1M: 0.001027 merged: 0.000000
 mg 16M: 0.000725 mg  8M: 0.001397 mg  4M: 0.001584 mg  2M: 0.002026 mg  1M: 0.000000mg merged: 0.000725
epoch: 207 [2017-12-21 02:01:21]
 16M: 0.001137  8M: 0.001370  4M: 0.001116  2M: 0.001121  1M: 0.001057 merged: 0.000000
 mg 16M: 0.000723 mg  8M: 0.001398 mg  4M: 0.001587 mg  2M: 0.002039 mg  1M: 0.000000mg merged: 0.000723
epoch: 208 [2017-12-21 02:06:22]
 16M: 0.001146  8M: 0.001375  4M: 0.001103  2M: 0.001109  1M: 0.001022 merged: 0.000000
 mg 16M: 0.000731 mg  8M: 0.001423 mg  4M: 0.001606 mg  2M: 0.002043 mg  1M: 0.000000mg merged: 0.000731
epoch: 209 [2017-12-21 02:11:20]
 16M: 0.001138  8M: 0.001369  4M: 0.001116  2M: 0.001126  1M: 0.001044 merged: 0.000000
 mg 16M: 0.000722 mg  8M: 0.001405 mg  4M: 0.001603 mg  2M: 0.002052 mg  1M: 0.000000mg merged: 0.000722
epoch: 210 [2017-12-21 02:16:37]
 16M: 0.001128  8M: 0.001355  4M: 0.001095  2M: 0.001114  1M: 0.001060 merged: 0.000000
 mg 16M: 0.000711 mg  8M: 0.001378 mg  4M: 0.001586 mg  2M: 0.002066 mg  1M: 0.000000mg merged: 0.000711
epoch: 211 [2017-12-21 02:21:49]
 16M: 0.001159  8M: 0.001392  4M: 0.001113  2M: 0.001121  1M: 0.001050 merged: 0.000000
 mg 16M: 0.000745 mg  8M: 0.001448 mg  4M: 0.001627 mg  2M: 0.002055 mg  1M: 0.000000mg merged: 0.000745
epoch: 212 [2017-12-21 02:26:59]
 16M: 0.001137  8M: 0.001367  4M: 0.001105  2M: 0.001104  1M: 0.001038 merged: 0.000000
 mg 16M: 0.000726 mg  8M: 0.001418 mg  4M: 0.001610 mg  2M: 0.002041 mg  1M: 0.000000mg merged: 0.000726
epoch: 213 [2017-12-21 02:32:05]
 16M: 0.001141  8M: 0.001373  4M: 0.001100  2M: 0.001105  1M: 0.001041 merged: 0.000000
 mg 16M: 0.000733 mg  8M: 0.001427 mg  4M: 0.001604 mg  2M: 0.002033 mg  1M: 0.000000mg merged: 0.000733
epoch: 214 [2017-12-21 02:37:14]
 16M: 0.001154  8M: 0.001374  4M: 0.001102  2M: 0.001109  1M: 0.001038 merged: 0.000000
 mg 16M: 0.000738 mg  8M: 0.001428 mg  4M: 0.001609 mg  2M: 0.002065 mg  1M: 0.000000mg merged: 0.000738
epoch: 215 [2017-12-21 02:42:35]
 16M: 0.001146  8M: 0.001377  4M: 0.001109  2M: 0.001109  1M: 0.001042 merged: 0.000000
 mg 16M: 0.000727 mg  8M: 0.001411 mg  4M: 0.001606 mg  2M: 0.002048 mg  1M: 0.000000mg merged: 0.000727
epoch: 216 [2017-12-21 02:47:45]
 16M: 0.001134  8M: 0.001366  4M: 0.001098  2M: 0.001107  1M: 0.001047 merged: 0.000000
 mg 16M: 0.000722 mg  8M: 0.001407 mg  4M: 0.001583 mg  2M: 0.002019 mg  1M: 0.000000mg merged: 0.000722
epoch: 217 [2017-12-21 02:52:50]
 16M: 0.001123  8M: 0.001346  4M: 0.001084  2M: 0.001095  1M: 0.001027 merged: 0.000000
 mg 16M: 0.000710 mg  8M: 0.001378 mg  4M: 0.001564 mg  2M: 0.001998 mg  1M: 0.000000mg merged: 0.000710
epoch: 218 [2017-12-21 02:57:54]
 16M: 0.001134  8M: 0.001367  4M: 0.001099  2M: 0.001111  1M: 0.001017 merged: 0.000000
 mg 16M: 0.000721 mg  8M: 0.001400 mg  4M: 0.001585 mg  2M: 0.002020 mg  1M: 0.000000mg merged: 0.000721
epoch: 219 [2017-12-21 03:03:03]
 16M: 0.001126  8M: 0.001360  4M: 0.001092  2M: 0.001091  1M: 0.001020 merged: 0.000000
 mg 16M: 0.000716 mg  8M: 0.001405 mg  4M: 0.001595 mg  2M: 0.002021 mg  1M: 0.000000mg merged: 0.000716
epoch: 220 [2017-12-21 03:08:24]
 16M: 0.001114  8M: 0.001344  4M: 0.001077  2M: 0.001085  1M: 0.001020 merged: 0.000000
 mg 16M: 0.000708 mg  8M: 0.001388 mg  4M: 0.001574 mg  2M: 0.001996 mg  1M: 0.000000mg merged: 0.000708
epoch: 221 [2017-12-21 03:13:35]
 16M: 0.001097  8M: 0.001316  4M: 0.001067  2M: 0.001072  1M: 0.001010 merged: 0.000000
 mg 16M: 0.000697 mg  8M: 0.001360 mg  4M: 0.001540 mg  2M: 0.001969 mg  1M: 0.000000mg merged: 0.000697
epoch: 222 [2017-12-21 03:18:42]
 16M: 0.001131  8M: 0.001349  4M: 0.001082  2M: 0.001079  1M: 0.001009 merged: 0.000000
 mg 16M: 0.000722 mg  8M: 0.001399 mg  4M: 0.001567 mg  2M: 0.001997 mg  1M: 0.000000mg merged: 0.000722
epoch: 223 [2017-12-21 03:23:50]
 16M: 0.001130  8M: 0.001353  4M: 0.001088  2M: 0.001094  1M: 0.001034 merged: 0.000000
 mg 16M: 0.000718 mg  8M: 0.001400 mg  4M: 0.001586 mg  2M: 0.002022 mg  1M: 0.000000mg merged: 0.000718
epoch: 224 [2017-12-21 03:29:02]
 16M: 0.001109  8M: 0.001337  4M: 0.001072  2M: 0.001079  1M: 0.001018 merged: 0.000000
 mg 16M: 0.000703 mg  8M: 0.001376 mg  4M: 0.001572 mg  2M: 0.002024 mg  1M: 0.000000mg merged: 0.000703
epoch: 225 [2017-12-21 03:34:15]
 16M: 0.001107  8M: 0.001331  4M: 0.001072  2M: 0.001075  1M: 0.001008 merged: 0.000000
 mg 16M: 0.000704 mg  8M: 0.001375 mg  4M: 0.001559 mg  2M: 0.002003 mg  1M: 0.000000mg merged: 0.000704
epoch: 226 [2017-12-21 03:39:25]
 16M: 0.001129  8M: 0.001350  4M: 0.001076  2M: 0.001071  1M: 0.001008 merged: 0.000000
 mg 16M: 0.000723 mg  8M: 0.001400 mg  4M: 0.001583 mg  2M: 0.002008 mg  1M: 0.000000mg merged: 0.000723
epoch: 227 [2017-12-21 03:44:39]
 16M: 0.001140  8M: 0.001371  4M: 0.001106  2M: 0.001103  1M: 0.001009 merged: 0.000000
 mg 16M: 0.000722 mg  8M: 0.001405 mg  4M: 0.001588 mg  2M: 0.002017 mg  1M: 0.000000mg merged: 0.000722
epoch: 228 [2017-12-21 03:49:52]
 16M: 0.001138  8M: 0.001358  4M: 0.001084  2M: 0.001076  1M: 0.000999 merged: 0.000000
 mg 16M: 0.000721 mg  8M: 0.001392 mg  4M: 0.001566 mg  2M: 0.001969 mg  1M: 0.000000mg merged: 0.000721
epoch: 229 [2017-12-21 03:55:05]
 16M: 0.001119  8M: 0.001333  4M: 0.001063  2M: 0.001053  1M: 0.000983 merged: 0.000000
 mg 16M: 0.000710 mg  8M: 0.001375 mg  4M: 0.001554 mg  2M: 0.001965 mg  1M: 0.000000mg merged: 0.000710
epoch: 230 [2017-12-21 04:00:21]
 16M: 0.001130  8M: 0.001353  4M: 0.001082  2M: 0.001085  1M: 0.001009 merged: 0.000000
 mg 16M: 0.000717 mg  8M: 0.001395 mg  4M: 0.001576 mg  2M: 0.002000 mg  1M: 0.000000mg merged: 0.000717
epoch: 231 [2017-12-21 04:05:33]
 16M: 0.001122  8M: 0.001346  4M: 0.001065  2M: 0.001053  1M: 0.000971 merged: 0.000000
 mg 16M: 0.000711 mg  8M: 0.001376 mg  4M: 0.001552 mg  2M: 0.001971 mg  1M: 0.000000mg merged: 0.000711
epoch: 232 [2017-12-21 04:10:41]
 16M: 0.001110  8M: 0.001324  4M: 0.001064  2M: 0.001069  1M: 0.001009 merged: 0.000000
 mg 16M: 0.000701 mg  8M: 0.001371 mg  4M: 0.001546 mg  2M: 0.001971 mg  1M: 0.000000mg merged: 0.000701
epoch: 233 [2017-12-21 04:15:51]
 16M: 0.001143  8M: 0.001378  4M: 0.001100  2M: 0.001105  1M: 0.001013 merged: 0.000000
 mg 16M: 0.000722 mg  8M: 0.001408 mg  4M: 0.001595 mg  2M: 0.002029 mg  1M: 0.000000mg merged: 0.000722
epoch: 234 [2017-12-21 04:21:08]
 16M: 0.001108  8M: 0.001326  4M: 0.001057  2M: 0.001053  1M: 0.000988 merged: 0.000000
 mg 16M: 0.000711 mg  8M: 0.001391 mg  4M: 0.001562 mg  2M: 0.001968 mg  1M: 0.000000mg merged: 0.000711
epoch: 235 [2017-12-21 04:26:16]
 16M: 0.001111  8M: 0.001334  4M: 0.001071  2M: 0.001072  1M: 0.001005 merged: 0.000000
 mg 16M: 0.000710 mg  8M: 0.001385 mg  4M: 0.001570 mg  2M: 0.001987 mg  1M: 0.000000mg merged: 0.000710
epoch: 236 [2017-12-21 04:31:36]
 16M: 0.001112  8M: 0.001338  4M: 0.001077  2M: 0.001070  1M: 0.001012 merged: 0.000000
 mg 16M: 0.000705 mg  8M: 0.001380 mg  4M: 0.001565 mg  2M: 0.002017 mg  1M: 0.000000mg merged: 0.000705
epoch: 237 [2017-12-21 04:36:58]
 16M: 0.001103  8M: 0.001326  4M: 0.001062  2M: 0.001051  1M: 0.000980 merged: 0.000000
 mg 16M: 0.000704 mg  8M: 0.001381 mg  4M: 0.001561 mg  2M: 0.001985 mg  1M: 0.000000mg merged: 0.000704
epoch: 238 [2017-12-21 04:42:10]
 16M: 0.001109  8M: 0.001336  4M: 0.001072  2M: 0.001068  1M: 0.000990 merged: 0.000000
 mg 16M: 0.000704 mg  8M: 0.001378 mg  4M: 0.001558 mg  2M: 0.001988 mg  1M: 0.000000mg merged: 0.000704
epoch: 239 [2017-12-21 04:47:46]
 16M: 0.001125  8M: 0.001349  4M: 0.001085  2M: 0.001084  1M: 0.001009 merged: 0.000000
 mg 16M: 0.000717 mg  8M: 0.001398 mg  4M: 0.001580 mg  2M: 0.002021 mg  1M: 0.000000mg merged: 0.000717

Visualize Graph





In [8]:



    


from graphviz import Digraph
import torch
from torch.autograd import Variable


def make_dot(var, params=None):
    """ Produces Graphviz representation of PyTorch autograd graph
    Blue nodes are the Variables that require grad, orange are Tensors
    saved for backward in torch.autograd.Function
    Args:
        var: output Variable
        params: dict of (name, Variable) to add names to node that
            require grad (TODO: make optional)
    """
    if params is not None:
        assert isinstance(params.values()[0], Variable)
        param_map = {id(v): k for k, v in params.items()}

    node_attr = dict(style='filled',
                     shape='box',
                     align='left',
                     fontsize='12',
                     ranksep='0.1',
                     height='0.2')
    dot = Digraph(node_attr=node_attr, graph_attr=dict(size="10240,10240"), format='svg')
    seen = set()

    def size_to_str(size):
        return '('+(', ').join(['%d' % v for v in size])+')'

    def add_nodes(var):
        if var not in seen:
            if torch.is_tensor(var):
                dot.node(str(id(var)), size_to_str(var.size()), fillcolor='orange')
            elif hasattr(var, 'variable'):
                u = var.variable
                name = param_map[id(u)] if params is not None else ''
                node_name = '%s\n %s' % (name, size_to_str(u.size()))
                dot.node(str(id(var)), node_name, fillcolor='lightblue')
            else:
                dot.node(str(id(var)), str(type(var).__name__))
            seen.add(var)
            if hasattr(var, 'next_functions'):
                for u in var.next_functions:
                    if u[0] is not None:
                        dot.edge(str(id(u[0])), str(id(var)))
                        add_nodes(u[0])
            if hasattr(var, 'saved_tensors'):
                for t in var.saved_tensors:
                    dot.edge(str(id(t)), str(id(var)))
                    add_nodes(t)
    add_nodes(var.grad_fn)
    return dot



    











In [9]:



    


# x = Variable(torch.zeros(1,3,256,256))
# y = net(x.cuda())
# g = make_dot(y[-1])



    











In [10]:



    


# g.render('net-transition_scale_{}'.format(transition_scale))



    











In [ ]:



    






    











In [ ]:

Content source: albertxavier001/graduation-project

Similar notebooks:

notebook.community | gallery | about