-
Notifications
You must be signed in to change notification settings - Fork 0
/
PyTorchMNIST.py
125 lines (103 loc) · 3.69 KB
/
PyTorchMNIST.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
# Example of training a CNN on the MNIST dataset in Keras
# Some of this code is likely outdated since it was written in ~2016
# Note: lacks train/val accuracy/metrics and loading a trained model and generating predictions
import sys
import time
import numpy as np
import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
from torch.autograd import Variable
print(time.strftime('%Y/%m/%d %H:%M'))
print('OS:', sys.platform)
print('Python:', sys.version)
print('NumPy:', np.__version__)
print('PyTorch:', torch.__version__)
if torch.cuda.is_available() == True:
print('GPU:', torch.cuda.current_device())
# Checking if there is a GPU and assigning it to a variable
if torch.cuda.is_available() == True:
gpu = True
else:
gpu = False
# Hyper Parameters
num_epochs = 5
batch_size = 100
learning_rate = 0.001
# MNIST Dataset
train_dataset = dsets.MNIST(root='./data/',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = dsets.MNIST(root='./data/',
train=False,
transform=transforms.ToTensor())
# Data Loader (Input Pipeline)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# CNN Model (2 conv layer)
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, padding=2),
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(2))
self.fc = nn.Linear(7*7*32, 10)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.view(out.size(0), -1)
out = self.fc(out)
return out
cnn = CNN()
if gpu == True:
cnn.cuda()
# Loss and Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate)
# Train the Model
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
if gpu == True:
images = Variable(images).cuda()
labels = Variable(labels).cuda()
else:
images = Variable(images)
labels = Variable(labels)
# Forward + Backward + Optimize
optimizer.zero_grad()
outputs = cnn(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print ('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
%(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
# Test the Model
cnn.eval() # Change model to 'eval' mode (BN uses moving mean/var).
correct = 0
total = 0
for images, labels in test_loader:
if gpu == True:
images = Variable(images).cuda()
else:
images = Variable(images)
outputs = cnn(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('Test Accuracy of the model on the 10000 test images: %d %%' % (100.0 * correct / total))
# Save the Trained Model
# torch.save(cnn.state_dict(), 'cnn.pkl')