lab-11-2-mnist_deep_cnn.py

# Lab 11 MNIST and Deep learning CNN
import torch
from torch.autograd import Variable
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import torch.nn.init

torch.manual_seed(777)  # reproducibility

# parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
keep_prob = 0.7

# 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)

# dataset loader
data_loader = torch.utils.data.DataLoader(dataset=mnist_train,
                                          batch_size=batch_size,
                                          shuffle=True)

# CNN Model


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),
            torch.nn.Dropout(p=1 - keep_prob))
        # 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),
            torch.nn.Dropout(p=1 - keep_prob))
        # L3 ImgIn shape=(?, 7, 7, 64)
        #    Conv      ->(?, 7, 7, 128)
        #    Pool      ->(?, 4, 4, 128)
        self.layer3 = torch.nn.Sequential(
            torch.nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
            torch.nn.ReLU(),
            torch.nn.MaxPool2d(kernel_size=2, stride=2, padding=1),
            torch.nn.Dropout(p=1 - keep_prob))

        # L4 FC 4x4x128 inputs -> 625 outputs
        self.fc1 = torch.nn.Linear(4 * 4 * 128, 625, bias=True)
        torch.nn.init.xavier_uniform(self.fc1.weight)
        self.layer4 = torch.nn.Sequential(
            self.fc1,
            torch.nn.ReLU(),
            torch.nn.Dropout(p=1 - keep_prob))
        # L5 Final FC 625 inputs -> 10 outputs
        self.fc2 = torch.nn.Linear(625, 10, bias=True)
        torch.nn.init.xavier_uniform(self.fc2.weight)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = out.view(out.size(0), -1)   # Flatten them for FC
        out = self.fc1(out)
        out = self.fc2(out)
        return out


# instantiate CNN model
model = CNN()

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

# train my model
print('Learning started. It takes sometime.')
for epoch in range(training_epochs):
    avg_cost = 0
    total_batch = len(mnist_train) // batch_size

    for i, (batch_xs, batch_ys) in enumerate(data_loader):
        X = Variable(batch_xs)    # image is already size of (28x28), no reshape
        Y = Variable(batch_ys)    # label is not one-hot encoded

        optimizer.zero_grad()
        hypothesis = model(X)
        cost = criterion(hypothesis, Y)
        cost.backward()
        optimizer.step()

        avg_cost += cost.data / total_batch

    print("[Epoch: {:>4}] cost = {:>.9}".format(epoch + 1, avg_cost[0]))

print('Learning Finished!')

# Test model and check accuracy
model.eval()    # set the model to evaluation mode (dropout=False)

X_test = Variable(mnist_test.test_data.view(len(mnist_test), 1, 28, 28).float())
Y_test = Variable(mnist_test.test_labels)

prediction = model(X_test)
correct_prediction = (torch.max(prediction.data, 1)[1] == Y_test.data)
accuracy = correct_prediction.float().mean()
print('Accuracy:', accuracy)