-
-
Notifications
You must be signed in to change notification settings - Fork 107
/
bayesian_LeNet_mnist.py
81 lines (73 loc) · 3.03 KB
/
bayesian_LeNet_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
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision.datasets as dsets
import torchvision.transforms as transforms
from blitz.modules import BayesianLinear, BayesianConv2d
from blitz.losses import kl_divergence_from_nn
from blitz.utils import variational_estimator
train_dataset = dsets.MNIST(root="./data",
train=True,
transform=transforms.ToTensor(),
download=True
)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=64,
shuffle=True)
test_dataset = dsets.MNIST(root="./data",
train=False,
transform=transforms.ToTensor(),
download=True
)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=64,
shuffle=True)
@variational_estimator
class BayesianCNN(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = BayesianConv2d(1, 6, (5,5))
self.conv2 = BayesianConv2d(6, 16, (5,5))
self.fc1 = BayesianLinear(256, 120)
self.fc2 = BayesianLinear(120, 84)
self.fc3 = BayesianLinear(84, 10)
def forward(self, x):
out = F.relu(self.conv1(x))
out = F.max_pool2d(out, 2)
out = F.relu(self.conv2(out))
out = F.max_pool2d(out, 2)
out = out.view(out.size(0), -1)
out = F.relu(self.fc1(out))
out = F.relu(self.fc2(out))
out = self.fc3(out)
return out
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
classifier = BayesianCNN().to(device)
optimizer = optim.Adam(classifier.parameters(), lr=0.001)
criterion = torch.nn.CrossEntropyLoss()
iteration = 0
for epoch in range(100):
for i, (datapoints, labels) in enumerate(train_loader):
optimizer.zero_grad()
loss = classifier.sample_elbo(inputs=datapoints.to(device),
labels=labels.to(device),
criterion=criterion,
sample_nbr=3,
complexity_cost_weight=1/50000)
#print(loss)
loss.backward()
optimizer.step()
iteration += 1
if iteration%250==0:
print(loss)
correct = 0
total = 0
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = classifier(images.to(device))
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels.to(device)).sum().item()
print('Iteration: {} | Accuracy of the network on the 10000 test images: {} %'.format(str(iteration) ,str(100 * correct / total)))