vision transformer实战

vision transformer是一种基于self-attention机制的图像分类算法。它采用了transformer的框架，将输入的图像通过一系列的transformer模块，最终输出分类结果。下面是一个简单的vision transformer实战流程：

1. 导入必要的库和数据集

import torch
import torch.nn as nn
from torch.utils.data import DataLoader
from torchvision.datasets import CIFAR10
from torchvision import transforms

transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

train_dataset = CIFAR10(root='./data', train=True, transform=transform, download=True)
test_dataset = CIFAR10(root='./data', train=False, transform=transform, download=True)

train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=64, shuffle=False)

2. 定义vision transformer模型

class VisionTransformer(nn.Module):
    def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=10, embed_dim=768, depth=12,
                 num_heads=12, mlp_ratio=4.0):
        super(VisionTransformer, self).__init__()
        self.patch_size = patch_size
        self.num_patches = (img_size // patch_size) ** 2
        self.patch_embed = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)
        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
        self.pos_embed = nn.Parameter(torch.zeros(1, self.num_patches + 1, embed_dim))
        self.pos_drop = nn.Dropout(p=0.5)
        self.transformer = nn.TransformerEncoder(
            nn.TransformerEncoderLayer(d_model=embed_dim, nhead=num_heads, dim_feedforward=int(embed_dim * mlp_ratio)),
            num_layers=depth)
        self.norm = nn.LayerNorm(embed_dim)
        self.fc = nn.Linear(embed_dim, num_classes)

    def forward(self, x):
        B = x.size(0)
        x = self.patch_embed(x).flatten(2).transpose(1, 2)
        cls_tokens = self.cls_token.expand(B, -1, -1)
        x = torch.cat((cls_tokens, x), dim=1)
        x += self.pos_embed[:, :(self.num_patches + 1)]
        x = self.pos_drop(x)
        x = self.transformer(x)
        x = self.norm(x)
        cls_tokens = x[:, 0]
        x = self.fc(cls_tokens)
        return x

3. 定义损失函数和优化器

model = VisionTransformer(num_classes=10).cuda()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)

4. 训练模型

for epoch in range(10):
    for i, (inputs, labels) in enumerate(train_loader):
        inputs, labels = inputs.cuda(), labels.cuda()
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
    if epoch % 2 == 0:
        print('Epoch [{}/{}], Loss: {:.4f}'
              .format(epoch+1, 10, loss.item()))

5. 测试模型

with torch.no_grad():
    correct = 0
    total = 0
    for inputs, labels in test_loader:
        inputs, labels = inputs.cuda(), labels.cuda()
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the network on the 10000 test images: %d %%' % (
            100 * correct / total))