cait_models.py [62:83]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        super().__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention_block(
            dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp_block(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
        self.gamma_1 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)
        self.gamma_2 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)

    
    def forward(self, x, x_cls):
        
        u = torch.cat((x_cls,x),dim=1)
        
        
        x_cls = x_cls + self.drop_path(self.gamma_1 * self.attn(self.norm1(u)))
        
        x_cls = x_cls + self.drop_path(self.gamma_2 * self.mlp(self.norm2(x_cls)))
        
        return x_cls 
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



patchconvnet_models.py [119:135]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        super().__init__()
        self.norm1 = norm_layer(dim)
        self.attn = Attention_block(
            dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp_block(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
        self.gamma_1 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)
        self.gamma_2 = nn.Parameter(init_values * torch.ones((dim)),requires_grad=True)

    def forward(self, x, x_cls):
        u = torch.cat((x_cls,x),dim=1)
        x_cls = x_cls + self.drop_path(self.gamma_1 * self.attn(self.norm1(u)))
        x_cls = x_cls + self.drop_path(self.gamma_2 * self.mlp(self.norm2(x_cls)))
        return x_cls
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -