Pytorch神经网络标准基础模板

%matplotlib inline
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda, Compose
import matplotlib.pyplot as plt
# Importing Python Libraries
import numpy as np
from torchsummary import summary
from sklearn.metrics import confusion_matrix
import pandas as pd
import seaborn as sn

# Download training data from open datasets.
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# Download test data from open datasets.
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

batch_size = 64

# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

for X, y in test_dataloader:
    print("Shape of X [N, C, H, W]: ", X.shape)
    print("Shape of y: ", y.shape, y.dtype)
    break
    
# Display sample data
figure = plt.figure(figsize=(10, 8))
cols, rows = 5, 5
for i in range(1, cols * rows + 1):
    idx = torch.randint(len(test_data), size=(1,)).item()
    img, label = test_data[idx]
    figure.add_subplot(rows, cols, i)
    plt.title(label)
    plt.axis("off")
    plt.imshow(img.squeeze(), cmap="gray")
plt.show()

loss_fn = nn.CrossEntropyLoss()
learning_rate = 1e-3
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)
        
        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)
        
        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {
      
      loss:>7f}  [{
      
      current:>5d}/{
      
      size:>5d}]")

def test(dataloader, model):
    size = len(dataloader.dataset)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= size
    correct /= size
    print(f"Test Error: \n Accuracy: {
      
      (100*correct):>0.1f}%, Avg loss: {
      
      test_loss:>8f} \n")

epochs = 15
for t in range(epochs):
    print(f"Epoch {
      
      t+1}\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model)
print("Done!")

torch.save(model.state_dict(), "data/model.pth")
print("Saved PyTorch Model State to model.pth")

model = NeuralNetwork()
model.load_state_dict(torch.load("data/model.pth"))

classes = [
    "T-shirt/top",
    "Trouser",
    "Pullover",
    "Dress",
    "Coat",
    "Sandal",
    "Shirt",
    "Sneaker",
    "Bag",
    "Ankle boot",
]

model.eval()
x, y = test_data[0][0], test_data[0][1]
with torch.no_grad():
    pred = model(x)
    predicted, actual = classes[pred[0].argmax(0)], classes[y]
    print(f'Predicted: "{
      
      predicted}", Actual: "{
      
      actual}"')


# draw confusion matrix
device = 'cuda:0' if torch.cuda.is_available() else 'cpu'
model = Model()
model.load_state_dict(torch.load('retrained.pt', map_location=device))
model.to(device)
y_true = []
y_pred = []
batch_size = 64
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
test_dataloader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False)

# iterate over test data
for inputs, labels in test_dataloader:
        inputs, labels = inputs.to(device), labels.to(device)
        output = model(inputs) # Feed Network

        labels = labels.data.cpu().numpy()
        y_true.extend(labels) # Save Truth

        output = (torch.max(torch.exp(output), 1)[1]).data.cpu().numpy()
        y_pred.extend(output) # Save Prediction
        

# WRITE YOUR CODE TO PLOT THE CONFUSION MATRIX HERE
# constant for classes
classes = ['Label 1', 'Label 2', 'Label 3', 'Label 4', 'Label 5',
        'Label 6', 'Label 7', 'Label 8', 'Label 9', 'Label 10']

# Build confusion matrix
cf_matrix = confusion_matrix(y_true, y_pred)
df_cm = pd.DataFrame(cf_matrix/np.sum(cf_matrix) * len(classes), index = [i+'(True)' for i in classes],
                     columns = [i+'(Pred)' for i in classes])
plt.figure(figsize = (14,9))
sn.heatmap(df_cm, annot=True)

来源：微软教程