Transformer实战-系列教程4:Vision Transformer 源码解读2

Transformer实战-系列教程总目录

有任何问题欢迎在下面留言
本篇文章的代码运行界面均在Pycharm中进行
本篇文章配套的代码资源已经上传

Vision Transformer 源码解读1
Vision Transformer 源码解读2
Vision Transformer 源码解读3
Vision Transformer 源码解读4

4、Embbeding类------构造函数

self.embeddings = Embeddings(config, img_size=img_size)
class Embeddings(nn.Module):
    """Construct the embeddings from patch, position embeddings.
    """
    def __init__(self, config, img_size, in_channels=3):
        super(Embeddings, self).__init__()
        self.hybrid = None
        img_size = _pair(img_size)

        if config.patches.get("grid") is not None:
            grid_size = config.patches["grid"]
            patch_size = (img_size[0] // 16 // grid_size[0], img_size[1] // 16 // grid_size[1])
            n_patches = (img_size[0] // 16) * (img_size[1] // 16)
            self.hybrid = True
        else:
            patch_size = _pair(config.patches["size"])
            n_patches = (img_size[0] // patch_size[0]) * (img_size[1] // patch_size[1])
            self.hybrid = False

        if self.hybrid:
            self.hybrid_model = ResNetV2(block_units=config.resnet.num_layers,
                                         width_factor=config.resnet.width_factor)
            in_channels = self.hybrid_model.width * 16
        self.patch_embeddings = Conv2d(in_channels=in_channels,
                                       out_channels=config.hidden_size,
                                       kernel_size=patch_size,
                                       stride=patch_size)
        self.position_embeddings = nn.Parameter(torch.zeros(1, n_patches+1, config.hidden_size))
        self.cls_token = nn.Parameter(torch.zeros(1, 1, config.hidden_size))

        self.dropout = Dropout(config.transformer["dropout_rate"])

    def forward(self, x):
        # print(x.shape)
        B = x.shape[0]
        cls_tokens = self.cls_token.expand(B, -1, -1)
        # print(cls_tokens.shape)
        if self.hybrid:
            x = self.hybrid_model(x)
        x = self.patch_embeddings(x)#Conv2d: Conv2d(3, 768, kernel_size=(16, 16), stride=(16, 16))
        # print(x.shape)
        x = x.flatten(2)
        # print(x.shape)
        x = x.transpose(-1, -2)
        # print(x.shape)
        x = torch.cat((cls_tokens, x), dim=1)
        # print(x.shape)

        embeddings = x + self.position_embeddings
        # print(embeddings.shape)
        embeddings = self.dropout(embeddings)
        # print(embeddings.shape)
        return embeddings

接上前面的debug模式,在构造模型部分一直步入到Embbeding类中:

  1. 构造函数,传入了图像大小224*224,通道数3,以及配置参数
  2. patch_size=[16,16],16*16的区域选出一份特征,这个参数自己定义
  3. n_patches,224224的图像能够切分出1616的格子数量,(224/16)(224/16)=1414=196个
  4. 196就是我们要定义的序列的长度了
  5. patch_embeddings,是一个二维卷积,输入通道为3,输出通道为768,卷积核为patch_size=1616,步长为1616,步长为1616就表明原本224224的图像卷积后的长宽就为14*14了
  6. position_embeddings,初始化参数全部为0 ,形状为[1,197,768],197=196+1,加一的原因是在Transformer模型中,通常会在序列的开始添加一个可学习的类标记(class token),它在训练过程中帮助模型捕获全局信息以用于分类任务。position_embeddings是用来记录位置信息的
  7. cls_token,初始化参数全部为0,形状为[1,1,768]
  8. 因为要涉及到全连接层,所以加上Dropout

5、Encoder类------构造函数

self.encoder = Encoder(config, vis)
class Encoder(nn.Module):
    def __init__(self, config, vis):
        super(Encoder, self).__init__()
        self.vis = vis
        self.layer = nn.ModuleList()
        self.encoder_norm = LayerNorm(config.hidden_size, eps=1e-6)
        for _ in range(config.transformer["num_layers"]):
            layer = Block(config, vis)
            self.layer.append(copy.deepcopy(layer))

    def forward(self, hidden_states):
        # print(hidden_states.shape)
        attn_weights = []
        for layer_block in self.layer:
            hidden_states, weights = layer_block(hidden_states)
            if self.vis:
                attn_weights.append(weights)
        encoded = self.encoder_norm(hidden_states)
        return encoded, attn_weights

接上前面的debug模式,在构造模型部分步入到Encoder类中:

  1. 构造函数传进配置参数
  2. vis,设置可视化
  3. layer,设置PyTorch的一个列表
  4. encoder_norm,LayerNorm,Batch Normalization是对Batch做归一化,LayerNorm对层
  5. 循环添加Block:循环config.transformer["num_layers"]次,每次都创建一个Block实例并添加到self.layer中。这里的Block是一个定义了Transformer编码器层的类,它包括自注意力机制和前馈网络。copy.deepcopy(layer)确保每次都是向ModuleList添加一个新的、独立的Block副本

之前ConvNet的任务中,都是使用Batch 做归一化,为什么Transformer是对Layer做归一化呢,Transformer是在NLP任务中提出来的,每一句话的单词个数都不一样,太长的阶段,短的补0,如果是对batch做归一化,长句子的后面一些地方要和短句子补0的地方做归一化,改用Layer归一化实现显著提升效果的情况。

Vision Transformer 源码解读1
Vision Transformer 源码解读2
Vision Transformer 源码解读3
Vision Transformer 源码解读4

你可能感兴趣的:(Transformer实战,transformer,深度学习,vit,计算机视觉,pytorch,视觉Transformer)