Method __init__

selfpatch_vision_transformer.py:118–128

(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, Attention_block = Class_Attention,
                 Mlp_block=Mlp)

    # taken from https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
    # with slight modifications to add CA and LayerScale
    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
                 drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, Attention_block = Class_Attention,
                 Mlp_block=Mlp):
        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)

    def forward(self, x, x_cls, attention=False, mask=None):
        u = torch.cat((x_cls,x),dim=1)