-
Notifications
You must be signed in to change notification settings - Fork 164
/
main.py
148 lines (124 loc) · 6.17 KB
/
main.py
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
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
from __future__ import print_function
import argparse
from math import log10
import os
import torch
import torch.nn as nn
import torch.optim as optim
from torch.autograd import Variable
from torch.utils.data import DataLoader
from dbpn import Net as DBPN
from dbpn_v1 import Net as DBPNLL
from dbpns import Net as DBPNS
from data import get_training_set, get_test_set
import pdb
import socket
import time
# Training settings
parser = argparse.ArgumentParser(description='PyTorch Super Res Example')
parser.add_argument('--upscale_factor', type=int, default=8, help="super resolution upscale factor")
parser.add_argument('--batchSize', type=int, default=16, help='training batch size')
parser.add_argument('--testBatchSize', type=int, default=5, help='testing batch size')
parser.add_argument('--nEpochs', type=int, default=2000, help='number of epochs to train for')
parser.add_argument('--snapshots', type=int, default=100, help='Snapshots')
parser.add_argument('--lr', type=float, default=1e-4, help='Learning Rate. Default=0.01')
parser.add_argument('--gpu_mode', type=bool, default=True)
parser.add_argument('--threads', type=int, default=10, help='number of threads for data loader to use')
parser.add_argument('--seed', type=int, default=123, help='random seed to use. Default=123')
parser.add_argument('--gpus', default=4, type=float, help='number of gpu')
parser.add_argument('--data_dir', type=str, default='./Dataset')
parser.add_argument('--data_augmentation', type=bool, default=True)
parser.add_argument('--hr_train_dataset', type=str, default='DIV2K_HR_aug')
parser.add_argument('--train_dataset', type=str, default='DIV2K_LR_aug_x8')
parser.add_argument('--hr_test_dataset', type=str, default='Set5')
parser.add_argument('--test_dataset', type=str, default='Set5_LR_x4')
parser.add_argument('--model_type', type=str, default='DBPN')
parser.add_argument('--patch_size', type=int, default=32, help='Size of cropped HR image')
parser.add_argument('--pretrained_sr', default=None, help='sr pretrained base model')
parser.add_argument('--pretrained', type=bool, default=False)
parser.add_argument('--save_folder', default='weights/', help='Location to save checkpoint models')
parser.add_argument('--prefix', default='dbpn', help='Location to save checkpoint models')
opt = parser.parse_args()
gpus_list = range(opt.gpus)
hostname = str(socket.gethostname())
print(opt)
def train(epoch):
epoch_loss = 0
model.train()
for iteration, batch in enumerate(training_data_loader, 1):
input, target = Variable(batch[0]), Variable(batch[1])
if cuda:
input = input.cuda(gpus_list[0])
target = target.cuda(gpus_list[0])
optimizer.zero_grad()
t0 = time.time()
loss = criterion(model(input), target)
t1 = time.time()
epoch_loss += loss.data[0]
loss.backward()
optimizer.step()
print("===> Epoch[{}]({}/{}): Loss: {:.4f} || Timer: {:.4f} sec.".format(epoch, iteration, len(training_data_loader), loss.data[0], (t1 - t0)))
print("===> Epoch {} Complete: Avg. Loss: {:.4f}".format(epoch, epoch_loss / len(training_data_loader)))
def test():
avg_psnr = 0
for batch in testing_data_loader:
input, target = Variable(batch[0]), Variable(batch[1])
if cuda:
input = input.cuda(gpus_list[0])
target = target.cuda(gpus_list[0])
prediction = model(input)
mse = criterion(prediction, target)
psnr = 10 * log10(1 / mse.data[0])
avg_psnr += psnr
print("===> Avg. PSNR: {:.4f} dB".format(avg_psnr / len(testing_data_loader)))
def print_network(net):
num_params = 0
for param in net.parameters():
num_params += param.numel()
print(net)
print('Total number of parameters: %d' % num_params)
def checkpoint(epoch):
model_out_path = opt.save_folder+opt.train_dataset+hostname+opt.model_type+opt.prefix+"_epoch_{}.pth".format(epoch)
torch.save(model.state_dict(), model_out_path)
print("Checkpoint saved to {}".format(model_out_path))
cuda = opt.gpu_mode
if cuda and not torch.cuda.is_available():
raise Exception("No GPU found, please run without --cuda")
torch.manual_seed(opt.seed)
if cuda:
torch.cuda.manual_seed(opt.seed)
print('===> Loading datasets')
train_set = get_training_set(opt.data_dir, opt.train_dataset, opt.hr_train_dataset, opt.upscale_factor, opt.patch_size, opt.data_augmentation)
#test_set = get_test_set(opt.data_dir, opt.test_dataset, opt.hr_test_dataset, opt.upscale_factor, opt.patch_size)
training_data_loader = DataLoader(dataset=train_set, num_workers=opt.threads, batch_size=opt.batchSize, shuffle=True)
#testing_data_loader = DataLoader(dataset=test_set, num_workers=opt.threads, batch_size=opt.testBatchSize, shuffle=False)
print('===> Building model ', opt.model_type)
if opt.model_type == 'DBPNLL':
model = DBPNLL(num_channels=3, base_filter=64, feat = 256, num_stages=10, scale_factor=opt.upscale_factor) ###For NTIRE2018
else:
model = DBPN(num_channels=3, base_filter=64, feat = 256, num_stages=7, scale_factor=opt.upscale_factor) ###D-DBPN
model = torch.nn.DataParallel(model, device_ids=gpus_list)
criterion = nn.L1Loss()
print('---------- Networks architecture -------------')
print_network(model)
print('----------------------------------------------')
if opt.pretrained:
model_name = os.path.join(opt.save_folder + opt.pretrained_sr)
if os.path.exists(model_name):
#model= torch.load(model_name, map_location=lambda storage, loc: storage)
model.load_state_dict(torch.load(model_name, map_location=lambda storage, loc: storage))
print('Pre-trained SR model is loaded.')
if cuda:
model = model.cuda(gpus_list[0])
criterion = criterion.cuda(gpus_list[0])
optimizer = optim.Adam(model.parameters(), lr=opt.lr, betas=(0.9, 0.999), eps=1e-8)
for epoch in range(1, opt.nEpochs + 1):
train(epoch)
#test()
# learning rate is decayed by a factor of 10 every half of total epochs
if (epoch+1) % (opt.nEpochs/2) == 0:
for param_group in optimizer.param_groups:
param_group['lr'] /= 10.0
print('Learning rate decay: lr={}'.format(optimizer.param_groups[0]['lr']))
if (epoch+1) % (opt.snapshots) == 0:
checkpoint(epoch)