import torch
import torchvision
import torchvision.transforms as transforms::: {.cell _cell_guid=‘b1076dfc-b9ad-4769-8c92-a6c4dae69d19’ _uuid=‘8f2839f25d086af736a60e9eeb907d3b93b6e0e5’ execution=‘{“iopub.execute_input”:“2022-10-21T01:57:51.117932Z”,“iopub.status.busy”:“2022-10-21T01:57:51.117345Z”,“iopub.status.idle”:“2022-10-21T01:57:51.124105Z”,“shell.execute_reply”:“2022-10-21T01:57:51.123122Z”,“shell.execute_reply.started”:“2022-10-21T01:57:51.117892Z”}’ trusted=‘true’ execution_count=2}
import numpy as np
import pandas as pd :::
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gzExtracting ./data/cifar-10-python.tar.gz to ./data
Files already downloaded and verifiedimport matplotlib.pyplot as plt
# 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 = next(dataiter)
# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join(f'{classes[labels[j]]:5s}' for j in range(batch_size)))
dog dog car ship import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super().__init__()
self.conv1 = nn.Conv2d(3, 18, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(18, 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 = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)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(f'[{epoch + 1}, {i + 1:5d}] loss: {running_loss / 2000:.3f}')
running_loss = 0.0
print('Finished Training')[1, 2000] loss: 2.184
[1, 4000] loss: 1.806
[1, 6000] loss: 1.639
[1, 8000] loss: 1.523
[1, 10000] loss: 1.464
[1, 12000] loss: 1.405
[2, 2000] loss: 1.321
[2, 4000] loss: 1.285
[2, 6000] loss: 1.276
[2, 8000] loss: 1.239
[2, 10000] loss: 1.173
[2, 12000] loss: 1.170
Finished TrainingPATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)dataiter = iter(testloader)
images, labels = next(dataiter)
# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join(f'{classes[labels[j]]:5s}' for j in range(4)))
GroundTruth: cat ship ship planenet = Net()
net.load_state_dict(torch.load(PATH))<All keys matched successfully>outputs = net(images)_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join(f'{classes[predicted[j]]:5s}'
for j in range(4)))Predicted: cat ship ship ship correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for data in testloader:
images, labels = data
# calculate outputs by running images through the network
outputs = net(images)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(f'Accuracy of the network on the 10000 test images: {100 * correct // total} %')Accuracy of the network on the 10000 test images: 59 %# prepare to count predictions for each class
correct_pred = {classname: 0 for classname in classes}
total_pred = {classname: 0 for classname in classes}
# again no gradients needed
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predictions = torch.max(outputs, 1)
# collect the correct predictions for each class
for label, prediction in zip(labels, predictions):
if label == prediction:
correct_pred[classes[label]] += 1
total_pred[classes[label]] += 1
# print accuracy for each class
for classname, correct_count in correct_pred.items():
accuracy = 100 * float(correct_count) / total_pred[classname]
print(f'Accuracy for class: {classname:5s} is {accuracy:.1f} %')Accuracy for class: plane is 45.7 %
Accuracy for class: car is 78.1 %
Accuracy for class: bird is 28.4 %
Accuracy for class: cat is 37.0 %
Accuracy for class: deer is 56.6 %
Accuracy for class: dog is 56.5 %
Accuracy for class: frog is 77.1 %
Accuracy for class: horse is 64.0 %
Accuracy for class: ship is 78.8 %
Accuracy for class: truck is 68.0 %device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# Assuming that we are on a CUDA machine, this should print a CUDA device:
print(device)cuda:0net.to(device)
inputs, labels = data[0].to(device), data[1].to(device)