forked from itayhubara/BinaryNet.pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmain_mnist.py
174 lines (149 loc) · 6.44 KB
/
main_mnist.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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
from __future__ import print_function
import argparse
import logging
import os
import sys
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
from models.binarized_modules import BinarizeLinear,BinarizeConv2d
from models.binarized_modules import Binarize,HingeLoss
from utils import *
# Training settings
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--results_dir', metavar='RESULTS_DIR', default='./results',
help='results dir')
parser.add_argument('--save', metavar='SAVE', default='',
help='saved folder')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 256)')
parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
help='input batch size for testing (default: 1000)')
parser.add_argument('--epochs', type=int, default=100, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
help='learning rate (default: 0.001)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--gpus', default=0,
help='gpus used for training - e.g 0,1,3')
parser.add_argument('--log-interval', type=int, default=10, 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()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
if args.save is '':
args.save = datetime.now().strftime('%Y-%m-%d_%H-%M-%S')
save_path = os.path.join(args.results_dir, args.save)
if not os.path.exists(save_path):
os.makedirs(save_path)
setup_logging(os.path.join(save_path, 'log.txt'))
results_file = os.path.join(save_path, 'results.%s')
results = ResultsLog(results_file % 'csv', results_file % 'html')
logging.info("saving to %s", save_path)
logging.debug("run arguments: %s", args)
kwargs = {'num_workers': 1, 'pin_memory': True} if args.cuda else {}
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('../../data', train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('../../data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.test_batch_size, shuffle=True, **kwargs)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.infl_ratio=3
self.fc1 = BinarizeLinear(784, 2048*self.infl_ratio)
self.htanh1 = nn.Hardtanh()
self.bn1 = nn.BatchNorm1d(2048*self.infl_ratio)
self.fc2 = BinarizeLinear(2048*self.infl_ratio, 2048*self.infl_ratio)
self.htanh2 = nn.Hardtanh()
self.bn2 = nn.BatchNorm1d(2048*self.infl_ratio)
self.fc3 = BinarizeLinear(2048*self.infl_ratio, 2048*self.infl_ratio)
self.htanh3 = nn.Hardtanh()
self.bn3 = nn.BatchNorm1d(2048*self.infl_ratio)
self.fc4 = nn.Linear(2048*self.infl_ratio, 10)
self.logsoftmax=nn.LogSoftmax()
self.drop=nn.Dropout(0.5)
def forward(self, x):
x = x.view(-1, 28*28)
x = self.fc1(x)
x = self.bn1(x)
x = self.htanh1(x)
x = self.fc2(x)
x = self.bn2(x)
x = self.htanh2(x)
x = self.fc3(x)
x = self.drop(x)
x = self.bn3(x)
x = self.htanh3(x)
x = self.fc4(x)
return self.logsoftmax(x)
model = Net()
if args.cuda:
torch.cuda.set_device(3)
model.cuda()
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
def train(epoch):
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()
output = model(data)
loss = criterion(output, target)
if epoch%40==0:
optimizer.param_groups[0]['lr']=optimizer.param_groups[0]['lr']*0.1
optimizer.zero_grad()
loss.backward()
for p in list(model.parameters()):
if hasattr(p,'org'):
p.data.copy_(p.org)
optimizer.step()
for p in list(model.parameters()):
if hasattr(p,'org'):
p.org.copy_(p.data.clamp_(-1,1))
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data.item()))
logging.info('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.data.item()))
def test():
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
output = model(data)
test_loss += criterion(output, target).data.item() # sum up batch loss
pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
correct += pred.eq(target.data.view_as(pred)).cpu().sum()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
for epoch in range(1, args.epochs + 1):
train(epoch)
test()