-
Notifications
You must be signed in to change notification settings - Fork 1
/
main.py
157 lines (135 loc) · 6.05 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
149
150
151
152
153
154
155
156
157
import torch
import torch.nn as nn
from torch.autograd import Variable,Function
import torch.optim as optim
from torchvision import datasets, transforms
import torch.nn.functional as F
import model as M
import util
import argparse
def ParseArgs():
parser = argparse.ArgumentParser(description='XnorNet Pytorch MNIST Example.')
parser.add_argument('--batch-size',type=int,default=100,metavar='N',
help='batch size for training(default: 100)')
parser.add_argument('--test-batch-size',type=int,default=100,metavar='N',
help='batch size for testing(default: 100)')
parser.add_argument('--epochs',type=int,default=100,metavar='N',
help='number of epoch to train(default: 100)')
parser.add_argument('--lr-epochs',type=int,default=20,metavar='N',
help='number of epochs to decay learning rate(default: 20)')
parser.add_argument('--lr',type=float,default=1e-3,metavar='LR',
help='learning rate(default: 1e-3)')
parser.add_argument('--momentum',type=float,default=0.9,metavar='M',
help='SGD momentum(default: 0.9)')
parser.add_argument('--weight-decay','--wd',type=float,default=1e-5,metavar='WD',
help='weight decay(default: 1e-5)')
parser.add_argument('--no-cuda',action='store_true',default=False,
help='disable CUDA training')
parser.add_argument('--seed',type=int,default=1,metavar='S',
help='random seed(default: 1)')
parser.add_argument('--log-interval',type=int,default=100,metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
return args
def main():
args = ParseArgs()
if args.cuda:
torch.cuda.manual_seed(args.seed)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
BATCH_SIZE = args.batch_size
TEST_BATCH_SIZE = args.test_batch_size
learning_rate = args.lr
#momentum = args.momentum
weight_decay = args.weight_decay
###################################################################
## Load Train Dataset ##
###################################################################
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('./mnist_data', train=True, download=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=BATCH_SIZE, shuffle=True,**kwargs)
###################################################################
## Load Test Dataset ##
###################################################################
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('./mnist_data', train=False, download=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=TEST_BATCH_SIZE, shuffle=True,**kwargs)
model = M.LeNet5_Bin()
if args.cuda:
model.cuda()
criterion = nn.CrossEntropyLoss()
if args.cuda:
criterion.cuda()
#optimizer = optim.SGD(model.parameters(),lr=learning_rate,momentum=momentum)
optimizer = optim.Adam(model.parameters(),lr=learning_rate,weight_decay=weight_decay)
bin_op = util.Binop(model)
best_acc = 0.0
for epoch_index in range(1,args.epochs+1):
adjust_learning_rate(learning_rate,optimizer,epoch_index,args.lr_epochs)
train(args,epoch_index,train_loader,model,optimizer,criterion,bin_op)
acc = test(model,test_loader,bin_op,criterion)
if acc > best_acc:
best_acc = acc
bin_op.Binarization()
save_model(model,best_acc)
bin_op.Restore()
def save_model(model,acc):
print('==>>>Saving model ...')
state = {
'acc':acc,
'state_dict':model.state_dict()
}
torch.save(state,'model_state.pkl')
print('*** DONE! ***')
def train(args,epoch_index,train_loader,model,optimizer,criterion,bin_op):
model.train()
for batch_idx,(data,target) in enumerate(train_loader):
if args.cuda:
data,target = data.cuda(),target.cuda()
data,target = Variable(data),Variable(target)
optimizer.zero_grad()
bin_op.Binarization()
output = model(data)
loss = criterion(output,target)
loss.backward()
bin_op.Restore()
bin_op.UpdateBinaryGradWeight()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch_index, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data[0]))
def test(model,test_loader,bin_op,criterion):
model.eval()
test_loss = 0
correct = 0
bin_op.Binarization()
for data,target in test_loader:
data,target = data.cuda(),target.cuda()
data,target = Variable(data,volatile=True),Variable(target)
output = model(data)
test_loss += criterion(output,target).data[0]
pred = output.data.max(1,keepdim=True)[1]
correct += pred.eq(target.data.view_as(pred)).cpu().sum()
bin_op.Restore()
acc = 100. * correct/len(test_loader.dataset)
test_loss /= len(test_loader)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
return acc
def adjust_learning_rate(learning_rate,optimizer,epoch_index,lr_epoch):
lr = learning_rate * (0.1 ** (epoch_index // lr_epoch))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
return lr
if __name__ == '__main__':
main()