Classification.py

# -*- coding: utf-8 -*-
"""
Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1N1S8ROzSKeUhb1tI_8LKG2r2CWjMz0sT
"""

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))])

trainset = torchvision.datasets.CIFAR10(root='.', train = True, download = True, transform = transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size = 4, shuffle = True, num_workers = 8)
testset = torchvision.datasets.CIFAR10(root='.', train = False, download = True, transform = transform)
testloader = torch.utils.data.DataLoader(testset, batch_size = 4, shuffle = False, num_workers = 8)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

import matplotlib.pyplot as plt
import numpy as np

def imshow(img):
    img = img/2+0.5   # Denormalize
    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(' '.join('%5s' % classes[labels[j]] for j in range(4)))

# Define a CNN
import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.pool = nn.MaxPool2d(2, 2)
        self.conv1 = nn.Conv2d(3, 8, 3)
        self.conv2 = nn.Conv2d(8, 32, 2)
        self.conv3 = nn.Conv2d(32, 64, 2)
        self.fc1 = nn.Linear(64*3*3, 256)
        self.fc2 = nn.Linear(256, 84)
        self.fc3 = nn.Linear(84, 10)
        self.drop = nn.Dropout2d(p=0.5)
    
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = self.pool(F.relu(self.conv3(x)))
        x = x.view(-1, 64*3*3)
        x = self.drop(x)
        x = F.relu(self.fc1(x))
        x = self.drop(x)
        x = F.relu(self.fc2(x))
        x = self.drop(x)
        x = self.fc3(x)
        return x

net = Net()

# Define the loss function: classification cross-entropy loss
# Define the SGD with momentum as optimizer
import torch.optim as optim
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr = 0.001, momentum = 0.9)

# Train the network
for epoch in range(50):
    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()
        if epoch==5:
            optimizer = optim.SGD(net.parameters(), lr = 0.0001, momentum = 0.9)
        elif epoch==20:
            optimizer = optim.SGD(net.parameters(), lr = 0.00001, momentum = 0.9)
        optimizer.step()

        # Print statistics
        running_loss += loss.item()
        if i%2000 == 1999:    # Print every 2000 mini-patches
            print('[%d, %5d] loss: %0.3f' %(epoch+1, i+1, running_loss/2000))
            running_loss = 0.0

print('Finished Training.')

# Save the network
## Don't forget to change the name of the PATH!!!
# PATH = './cifar_net.pth'                          # default CNN structure
# PATH = './cifar_net_epoch20.pth'                  # default CNN structure, epoch=20
# PATH = './cifar_net_dropout_epoch20.pth'          # add dropout, epoch=20
# PATH = './cifar_net_dropout2_epoch20.pth'         # less dropout, epoch=20
# PATH = './cifar_net_dropout_6layer_epoch30.pth'   # 6 layers, epoch=30
# PATH = './cifar_net_dropout_5layer_epoch20.pth'   # 5 layers, epoch=20, feature=32*5*5
# PATH = './cifar_net_changed_rl.pth'               # rl=0.001 when epoch<5, =0.0001 when epoch>=5, no dropout, epoch=20
PATH = './cifar_net_changed_rl_epoch50.pth'         # rl=0.001 (<5), 0.0001 (5-20), 0.00001 (>20), epoch=50 
torch.save(net.state_dict(), PATH)

# Reload the network
net = Net()
net.load_state_dict(torch.load(PATH))

# Test the network on the test data
dataiter = iter(testloader)
images, labels = dataiter.next()

# Show the test images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))

# Predicted results
outputs = net(images)
_, predicted = torch.max(outputs, 1)
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]] for j in range(4)))

# To see the performance of the network on the whole training dataset
correct = 0
total = 0
with torch.no_grad():
    for data in trainloader:
        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 %d training images is: %0.2f %%' % (total, 100*correct/total))

# To see the performance of the network on the whole test dataset
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 %d test images is: %0.2f %%' % (total, 100*correct/total))

# Performace of the network on each class
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]))