1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
|
### Copyright (C) 2017 NVIDIA Corporation. All rights reserved.
### Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
import time
from collections import OrderedDict
from options.train_options import TrainOptions
from data.data_loader import CreateDataLoader
from models.models import create_model
import util.util as util
from util.visualizer import Visualizer
import os
import numpy as np
import torch
from torch.autograd import Variable
opt = TrainOptions().parse()
iter_path = os.path.join(opt.checkpoints_dir, opt.name, 'iter.txt')
if opt.continue_train:
try:
start_epoch, epoch_iter = np.loadtxt(iter_path , delimiter=',', dtype=int)
except:
start_epoch, epoch_iter = 1, 0
print('Resuming from epoch %d at iteration %d' % (start_epoch, epoch_iter))
else:
start_epoch, epoch_iter = 1, 0
if opt.debug:
opt.display_freq = 1
opt.print_freq = 1
opt.niter = 1
opt.niter_decay = 0
opt.max_dataset_size = 10
data_loader = CreateDataLoader(opt)
dataset = data_loader.load_data()
dataset_size = len(data_loader)
print('#training images = %d' % dataset_size)
model = create_model(opt)
visualizer = Visualizer(opt)
total_steps = (start_epoch-1) * dataset_size + epoch_iter
display_delta = total_steps % opt.display_freq
print_delta = total_steps % opt.print_freq
save_delta = total_steps % opt.save_latest_freq
print("{} {}".format(start_epoch, start_epoch + opt.niter + opt.niter_decay + 1))
for epoch in range(start_epoch, start_epoch + opt.niter + opt.niter_decay + 1):
epoch_start_time = time.time()
if epoch != start_epoch:
epoch_iter = epoch_iter % dataset_size
for i, data in enumerate(dataset, start=epoch_iter):
iter_start_time = time.time()
total_steps += opt.batchSize
epoch_iter += opt.batchSize
# whether to collect output images
save_fake = total_steps % opt.display_freq == display_delta
############## Forward Pass ######################
losses, generated = model(Variable(data['label']), Variable(data['inst']),
Variable(data['image']), Variable(data['feat']), infer=save_fake)
# sum per device losses
losses = [ torch.mean(x) if not isinstance(x, int) else x for x in losses ]
loss_dict = dict(zip(model.module.loss_names, losses))
# calculate final loss scalar
loss_D = (loss_dict['D_fake'] + loss_dict['D_real']) * 0.5
loss_G = loss_dict['G_GAN'] + loss_dict.get('G_GAN_Feat',0) + loss_dict.get('G_VGG',0)
############### Backward Pass ####################
# update generator weights
model.module.optimizer_G.zero_grad()
loss_G.backward()
model.module.optimizer_G.step()
# update discriminator weights
model.module.optimizer_D.zero_grad()
loss_D.backward()
model.module.optimizer_D.step()
#call(["nvidia-smi", "--format=csv", "--query-gpu=memory.used,memory.free"])
############## Display results and errors ##########
### print out errors
if total_steps % opt.print_freq == print_delta:
errors = {k: v.data[0] if not isinstance(v, int) else v for k, v in loss_dict.items()}
t = (time.time() - iter_start_time) / opt.batchSize
visualizer.print_current_errors(epoch, epoch_iter, errors, t)
visualizer.plot_current_errors(errors, total_steps)
### display output images
if save_fake:
visuals = OrderedDict([('input_label', util.tensor2label(data['label'][0], opt.label_nc)),
('synthesized_image', util.tensor2im(generated.data[0])),
('real_image', util.tensor2im(data['image'][0]))])
visualizer.display_current_results(visuals, epoch, total_steps)
### save latest model
if total_steps % opt.save_latest_freq == save_delta:
print('saving the latest model (epoch %d, total_steps %d)' % (epoch, total_steps))
model.module.save('latest')
np.savetxt(iter_path, (epoch, epoch_iter), delimiter=',', fmt='%d')
# end of epoch
iter_end_time = time.time()
print('End of epoch %d / %d \t Time Taken: %d sec' %
(epoch, opt.niter + opt.niter_decay, time.time() - epoch_start_time))
### save model for this epoch
if epoch % opt.save_epoch_freq == 0:
print('saving the model at the end of epoch %d, iters %d' % (epoch, total_steps))
model.module.save('latest')
model.module.save(epoch)
np.savetxt(iter_path, (epoch+1, 0), delimiter=',', fmt='%d')
### instead of only training the local enhancer, train the entire network after certain iterations
if (opt.niter_fix_global != 0) and (epoch == opt.niter_fix_global):
model.module.update_fixed_params()
### linearly decay learning rate after certain iterations
if epoch > opt.niter:
model.module.update_learning_rate()
|
