Join the “Zero to Data Analyst” Bootcamp. Limited seats.
A 20-week program covering 7 courses, 12 assignments, 4 real-world projects, and 12 months of career support.
In [1]:
import torch
import torch.nn as nn
import torch.nn.functional as FIn [31]:
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# 1 input image channel, 6 output channels, 3x3 square convolution
# kernel
self.conv1 = nn.Conv2d(1, 6, 3)
self.conv2 = nn.Conv2d(6, 16, 3)
# an affine operation: y = Wx + b
self.fc1 = nn.Linear(16 * 6 * 6, 120) # 6*6 from image dimension
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
# Max pooling over a (2, 2) window
x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
# If the size is a square you can only specify a single number
x = F.max_pool2d(F.relu(self.conv2(x)), 2)
x = x.view(-1, self.num_flat_features(x))
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def num_flat_features(self, x):
size = x.size()[1:] # all dimensions except the batch dimension
num_features = 1
for s in size:
num_features *= s
return num_features
In [32]:
net = Net()
print(net)
Net(
(conv1): Conv2d(1, 6, kernel_size=(3, 3), stride=(1, 1))
(conv2): Conv2d(6, 16, kernel_size=(3, 3), stride=(1, 1))
(fc1): Linear(in_features=576, out_features=120, bias=True)
(fc2): Linear(in_features=120, out_features=84, bias=True)
(fc3): Linear(in_features=84, out_features=10, bias=True)
)
In [33]:
params = list(net.parameters())
print(len(params))
print(params[0].size())10
torch.Size([6, 1, 3, 3])
In [34]:
input = torch.randn(1, 1, 32, 32)
out = net(input)
print(out)
tensor([[ 0.1707, -0.0176, 0.0281, -0.0333, 0.0537, -0.0026, 0.2111, -0.0131,
-0.1948, 0.0129]], grad_fn=<AddmmBackward>)
In [35]:
net.zero_grad()
out.backward(torch.randn(1, 10))In [36]:
output = net(input)
target = torch.randn(10) # a dummy target, for example
target = target.view(1, -1) # make it the same shape as output
criterion = nn.MSELoss()
loss = criterion(output, target)
print(loss)
tensor(0.7265, grad_fn=<MseLossBackward>)
In [37]:
print(loss.grad_fn) # MSELoss
print(loss.grad_fn.next_functions[0][0]) # Linear
print(loss.grad_fn.next_functions[0][0].next_functions[0][0]) # ReLU<MseLossBackward object at 0x143f638d0>
<AddmmBackward object at 0x143f63cd0>
<AccumulateGrad object at 0x143f638d0>
In [38]:
net.zero_grad() # zeroes the gradient buffers of all parameters
print('conv1.bias.grad before backward')
print(net.conv1.bias.grad)
loss.backward()
print('conv1.bias.grad after backward')
print(net.conv1.bias.grad)
conv1.bias.grad before backward
tensor([0., 0., 0., 0., 0., 0.])
conv1.bias.grad after backward
tensor([ 0.0144, 0.0010, 0.0151, -0.0027, 0.0071, 0.0171])
In [39]:
import torch.optim as optim
# create your optimizer
optimizer = optim.SGD(net.parameters(), lr=0.01)
# in your training loop:
optimizer.zero_grad() # zero the gradient buffers
output = net(input)
loss = criterion(output, target)
loss.backward()
optimizer.step() # Does the updateIn [5]:
import torch
import torchvision
import torchvision.transforms as transforms
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset1 = torchvision.datasets.CIFAR10(root='./data', train=True,download=True, transform=transform)
testset1 = torchvision.datasets.CIFAR10(root='./data', train=False,download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset1, batch_size=4,shuffle=True, num_workers=0)
testloader = torch.utils.data.DataLoader(testset1, batch_size=4,shuffle=False, num_workers=0)
classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck')
Files already downloaded and verified
Files already downloaded and verified
In [6]:
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
deer horse frog cat
In [7]:
import matplotlib.pyplot as plt
import numpy as np
# functions to show an image
def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4)))
dog deer frog car
In [8]:
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
In [9]:
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)In [10]:
for epoch in range(2): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = data
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')[1, 2000] loss: 2.260
[1, 4000] loss: 1.965
[1, 6000] loss: 1.712
[1, 8000] loss: 1.604
[1, 10000] loss: 1.510
[1, 12000] loss: 1.477
[2, 2000] loss: 1.414
[2, 4000] loss: 1.381
[2, 6000] loss: 1.352
[2, 8000] loss: 1.306
[2, 10000] loss: 1.305
[2, 12000] loss: 1.275
Finished Training
In [12]:
PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)
dataiter = iter(testloader)
images, labels = dataiter.next()
# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))
GroundTruth: cat ship ship plane
In [13]:
net = Net()
net.load_state_dict(torch.load(PATH))
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(4)))Predicted: cat ship ship ship
In [14]:
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))Accuracy of the network on the 10000 test images: 54 %
In [16]:
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(4):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(10):
print('Accuracy of %5s : %2d %%' % (
classes[i], 100 * class_correct[i] / class_total[i]))Accuracy of plane : 47 %
Accuracy of car : 62 %
Accuracy of bird : 50 %
Accuracy of cat : 32 %
Accuracy of deer : 43 %
Accuracy of dog : 44 %
Accuracy of frog : 64 %
Accuracy of horse : 57 %
Accuracy of ship : 81 %
Accuracy of truck : 63 %
In [ ]: