Pytorch CNN with Mnist

In [5]:

import torch
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.init

In [2]:

# gpu 사용이 가능한지 ??? 
device = 'cuda' if torch.cuda.is_available() else 'cpu'

# gpu 사용설정 후 , random_value 를 위한 seed 설정
# for reproducibility
torch.manual_seed(777)
if device == 'cuda':
    torch.cuda.manual_seed_all(777)

In [3]:

# cnn 학습 parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100

In [9]:

# MNIST dataset
mnist_train = dsets.MNIST(root='MNIST_data/',
                          train=True,
                          transform=transforms.ToTensor(),
                          download=True)

mnist_test = dsets.MNIST(root='MNIST_data/',
                         train=False,
                         transform=transforms.ToTensor(),
                         download=True)

In [11]:

# batch_size 와 dataset 을 통해 dataLoader 로딩
data_loader = torch.utils.data.DataLoader(dataset=mnist_train,
                                          batch_size=batch_size,
                                          shuffle=True,
                                          drop_last=True)

In [13]:

# CNN Model (2 conv layers)
class CNN(torch.nn.Module):

    def __init__(self):
        super(CNN, self).__init__()
        # L1 ImgIn shape=(?, 28, 28, 1)
        #    Conv     -> (?, 28, 28, 32)
        #    Pool     -> (?, 14, 14, 32)
        self.layer1 = torch.nn.Sequential(
            torch.nn.Conv2d(1, 32, kernel_size=3, stride=1, padding=1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(kernel_size=2, stride=2))
        # L2 ImgIn shape=(?, 14, 14, 32)
        #    Conv      ->(?, 14, 14, 64)
        #    Pool      ->(?, 7, 7, 64)
        self.layer2 = torch.nn.Sequential(
            torch.nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(kernel_size=2, stride=2))
        # Final FC 7x7x64 inputs -> 10 outputs
        self.fc = torch.nn.Linear(7 * 7 * 64, 10, bias=True)
        torch.nn.init.xavier_uniform_(self.fc.weight)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.view(out.size(0), -1)   # Flatten them for FC
        out = self.fc(out)
        return out

In [15]:

# GPU 사용이 가능한가???
model = CNN().to(device)

In [16]:

# define cost/loss & optimizer
criterion = torch.nn.CrossEntropyLoss().to(device)    # Softmax is internally computed.
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

In [17]:

total_batch = len(data_loader)
print('Learning started')
for epoch in range(training_epochs):
    avg_cost = 0
    for X,Y in data_loader: # X = image, Y=Label
        X = X.to(device)
        Y = Y.to(device)
        optimizer.zero_grad()
        hypothesis = model(X)
        cost = criterion(hypothesis,Y)
        cost.backward()
        optimizer.step()
        
        avg_cost+= cost/total_batch
    print('[Epoch: {:>4}] cost = {:>.9}'.format(epoch + 1, avg_cost))
print("Learning Finished")

Learning started
[Epoch:    1] cost = 0.230441451
[Epoch:    2] cost = 0.0588737279
[Epoch:    3] cost = 0.0437557586
[Epoch:    4] cost = 0.0344327986
[Epoch:    5] cost = 0.0283598024
[Epoch:    6] cost = 0.0232713353
[Epoch:    7] cost = 0.0193091519
[Epoch:    8] cost = 0.0167574845
[Epoch:    9] cost = 0.0143606402
[Epoch:   10] cost = 0.0120671066
[Epoch:   11] cost = 0.0107910205
[Epoch:   12] cost = 0.00846360531
[Epoch:   13] cost = 0.00608973531
[Epoch:   14] cost = 0.00732062757
[Epoch:   15] cost = 0.00569137093
Learning Finished

In [18]:

with torch.no_grad():
    X_test = mnist_test.test_data.view(len(mnist_test), 1, 28, 28).float().to(device)
    Y_test = mnist_test.test_labels.to(device)
    prediction = model(X_test)
    correct_prediction = torch.argmax(prediction,1) == Y_test # 1 이면 같냐 아니면 0 
    accuracy = correct_prediction.float().mean()
    print('Accuracy:', accuracy.item())

Accuracy: 0.9828999638557434

C:\Users\sangi\Anaconda3\envs\pytorch\lib\site-packages\torchvision\datasets\mnist.py:63: UserWarning: test_data has been renamed data
  warnings.warn("test_data has been renamed data")
C:\Users\sangi\Anaconda3\envs\pytorch\lib\site-packages\torchvision\datasets\mnist.py:53: UserWarning: test_labels has been renamed targets
  warnings.warn("test_labels has been renamed targets")