train_CNN_network_save.py

# import libraries
import torch
import numpy as np
from torchvision import datasets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import torch.nn as nn
import torch.nn.functional as F

# how many samples per batch to load
batch_size = 20

# number of epochs to train the model
n_epochs = 100 # suggest training between 20-50 epochs

# convert data to torch.FloatTensor
transform = transforms.ToTensor()

# choose the training and test datasets
train_data = datasets.MNIST(root='data', train=True,
                                   download=True, transform=transform)
test_data = datasets.MNIST(root='data', train=False,
                                  download=True, transform=transform)

# prepare data loaders
train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size)


class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        # `nn.Conv2d`
        # nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0)
        # stride 默认是 1， padding 默认是 0
        self.conv1 = nn.Conv2d(in_channels = 1, out_channels = 6, kernel_size = 5)
        self.conv2 = nn.Conv2d(in_channels = 6, out_channels = 16, kernel_size = 5)
        self.fc1 = nn.Linear(256, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        y = F.relu(self.conv1(x))
        # torch.nn.functional.MaxPool2d(input, kernel_size, stride=None)
        # `kernel_size` – the size of the window to take a max over
        # `stride` – the stride of the window. Default value is `kernel_size`
        y = F.max_pool2d(y, 2)
        y = F.relu(self.conv2(y))
        y = F.max_pool2d(y, 2)
        y = y.view(y.shape[0], -1)
        y = F.relu(self.fc1(y))
        y = F.relu(self.fc2(y))
        y = F.relu(self.fc3(y))
        return y

# initialize the NN
model = LeNet()
print(model)

## Specify loss and optimization functions

# specify loss function
criterion = nn.CrossEntropyLoss()

# specify optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)


model.train() # prep model for training

for epoch in range(n_epochs):
    # monitor training loss
    train_loss = 0.0
    
    ###################
    # train the model #
    ###################
    for data, target in train_loader:
        # clear the gradients of all optimized variables
        optimizer.zero_grad()
        # forward pass: compute predicted outputs by passing inputs to the model
        output = model(data)
        # calculate the loss
        loss = criterion(output, target)
        # backward pass: compute gradient of the loss with respect to model parameters
        loss.backward()
        # perform a single optimization step (parameter update)
        optimizer.step()
        # update running training loss
        train_loss += loss.item()*data.size(0)
        
    # print training statistics 
    # calculate average loss over an epoch
    train_loss = train_loss/len(train_loader.dataset)

    print('Epoch: {} \tTraining Loss: {:.6f}'.format(
        epoch+1, 
        train_loss
        ))


# initialize lists to monitor test loss and accuracy
test_loss = 0.0
class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))

torch.save(model.state_dict(), './model/cnn.pth')