pytorch基础实战——FashionMNIST时装分类

 

 我们通过一个基础实战案例，将所涉及的PyTorch入门知识串起来，便于加深理解。同时为后续的进阶学习打好基础。

import os
import numpy as np
import pandas as pd
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from torchvision import datasets
import matplotlib.pyplot as plt


os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"       #environment variables

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(1, 32, 5),
            nn.ReLU(),
            nn.MaxPool2d(2, stride=2),
            nn.Dropout(0.3),
            nn.Conv2d(32, 64, 5),
            nn.ReLU(),
            nn.MaxPool2d(2, stride=2),
            nn.Dropout(0.3)
        )
        self.fc = nn.Sequential(
            nn.Linear(64*4*4, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )
        
    def forward(self, x):
        x = self.conv(x)
        x = x.view(-1, 64*4*4)
        x = self.fc(x)
        x = nn.functional.normalize(x)
        return x


device = "cuda:0" if torch.cuda.is_available() else "cpu"

batch_size = 256
num_workers = 0   # 对于Windows用户，这里应设置为0，否则会出现多线程错误
lr = 1e-4
epochs = 20

image_size = 28

data_transform = transforms.Compose([
    #transforms.ToPILImage(),  
     # 这一步取决于后续的数据读取方式，如果使用内置数据集读取方式则不需要
    transforms.Resize(image_size),
    transforms.ToTensor()])

train_data = datasets.FashionMNIST(root='./', train=True, download=True, transform=data_transform)
test_data = datasets.FashionMNIST(root='./', train=False, download=True, transform=data_transform)



train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=num_workers, drop_last=True)
test_loader = DataLoader(test_data, batch_size=batch_size, shuffle=False, num_workers=num_workers)

image, label = next(iter(train_loader))
print(image.shape, label.shape)
plt.imshow(image[0][0], cmap="gray")



model = Net()
print(model.to(device)) 

criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)


def train(epoch):
    model.train()
    train_loss = 0
    for data, label in train_loader:
        #data, label = data.cuda(), label.cuda()
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, label)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()*data.size(0)
    train_loss = train_loss/len(train_loader.dataset)
    print('Epoch: {} \tTraining Loss: {:.6f}'.format(epoch, train_loss))

def val(epoch):       
    model.eval()
    val_loss = 0
    gt_labels = []
    pred_labels = []
    with torch.no_grad():
        for data, label in test_loader:
            #data, label = data.cuda(), label.cuda()
            output = model(data)
            preds = torch.argmax(output, 1)
            gt_labels.append(label.cpu().data.numpy())
            pred_labels.append(preds.cpu().data.numpy())
            loss = criterion(output, label)
            val_loss += loss.item()*data.size(0)
    val_loss = val_loss/len(test_loader.dataset)
    gt_labels, pred_labels = np.concatenate(gt_labels), np.concatenate(pred_labels)
    acc = np.sum(gt_labels==pred_labels)/len(pred_labels)
    print('Epoch: {} \tValidation Loss: {:.6f}, Accuracy: {:6f}'.format(epoch, val_loss, acc))

if __name__ == "__main__":
    for epoch in range(1, epochs+1):
        train(epoch)
        val(epoch)