-
Notifications
You must be signed in to change notification settings - Fork 1
/
20171114-mnist-torch-linear.py
166 lines (145 loc) · 6.08 KB
/
20171114-mnist-torch-linear.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
# ==============================================================================
# Torch MNIST CNN classifier + without activation (linear NN)
# --------------------------------------------------------------------------
# Copied from https://github.com/pytorch/examples/blob/master/mnist/main.py
#
# To test effect of nonlinearity
# ==============================================================================
from __future__ import print_function
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
def get_parser():
import argparse
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=256, 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=10, 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: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--cuda', action='store_true', default=False,
help='enables 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=15, metavar='N',
help='how many batches to wait before logging training status')
return parser
def load_mnist_data(save_dir, kwargs):
train_loader = torch.utils.data.DataLoader(
datasets.MNIST(save_dir, 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(save_dir, train=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081, ))
])),
batch_size=args.test_batch_size, shuffle=True, **kwargs)
return (train_loader, test_loader)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(
in_channels=1,
out_channels=10,
kernel_size=5,
stride=1,
padding=0)
self.conv2 = nn.Conv2d(
in_channels=10,
out_channels=20,
kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
'''
# Input x shape (1, 28^2)
x = F.relu(F.max_pool2d(self.conv1(x), 2)) # 10, 12^2
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2)) # 20, 4^2
x = x.view(-1, 320) # Flatten
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x)
'''
return self.forward_lin(x)
def forward_lin(self, x):
x = F.max_pool2d(self.conv1(x), 2) # 10, 12^2
x = F.max_pool2d(self.conv2_drop(self.conv2(x)), 2) # 20, 4^2
x = x.view(-1, 320) # Flatten
x = self.fc1(x)
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x)
def main(args):
# ============
# Set up Model
# ------------
kwargs = {'num_workers':1, 'pin_memory':True} if args.cuda else {}
train_loader, test_loader = load_mnist_data('../data', kwargs)
model = Net()
if args.cuda:
model.cuda()
optimizer = optim.SGD(
model.parameters(),
lr=args.lr,
momentum=args.momentum)
metrics = {"loss":[]}
# ============
# Train and Test
# ------------
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 = F.nll_loss(output, target)
loss.backward()
optimizer.step()
metrics["loss"].append(loss.data[0])
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[0]))
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 += F.nll_loss(output, target, size_average=False).data[0] # 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(args.epochs + 1):
train(epoch)
test()
if __name__ == '__main__':
args = get_parser().parse_args()
args.cuda = args.cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
main(args)