timm/models/mvitv2.py [248:300]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if kernel_q:
                self.pool_q = nn.Conv2d(
                    dim_conv,
                    dim_conv,
                    kernel_q,
                    stride=stride_q,
                    padding=padding_q,
                    groups=dim_conv,
                    bias=False,
                )
                self.norm_q = norm_layer(dim_conv)
            if kernel_kv:
                self.pool_k = nn.Conv2d(
                    dim_conv,
                    dim_conv,
                    kernel_kv,
                    stride=stride_kv,
                    padding=padding_kv,
                    groups=dim_conv,
                    bias=False,
                )
                self.norm_k = norm_layer(dim_conv)
                self.pool_v = nn.Conv2d(
                    dim_conv,
                    dim_conv,
                    kernel_kv,
                    stride=stride_kv,
                    padding=padding_kv,
                    groups=dim_conv,
                    bias=False,
                )
                self.norm_v = norm_layer(dim_conv)
        else:
            raise NotImplementedError(f"Unsupported model {mode}")

        # relative pos embedding
        self.rel_pos_type = rel_pos_type
        if self.rel_pos_type == 'spatial':
            assert feat_size[0] == feat_size[1]
            size = feat_size[0]
            q_size = size // stride_q[1] if len(stride_q) > 0 else size
            kv_size = size // stride_kv[1] if len(stride_kv) > 0 else size
            rel_sp_dim = 2 * max(q_size, kv_size) - 1

            self.rel_pos_h = nn.Parameter(torch.zeros(rel_sp_dim, self.head_dim))
            self.rel_pos_w = nn.Parameter(torch.zeros(rel_sp_dim, self.head_dim))
            trunc_normal_tf_(self.rel_pos_h, std=0.02)
            trunc_normal_tf_(self.rel_pos_w, std=0.02)

        self.residual_pooling = residual_pooling

    def forward(self, x, feat_size: List[int]):
        B, N, _ = x.shape
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



timm/models/mvitv2.py [416:468]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if kernel_q:
                self.pool_q = nn.Conv2d(
                    dim_conv,
                    dim_conv,
                    kernel_q,
                    stride=stride_q,
                    padding=padding_q,
                    groups=dim_conv,
                    bias=False,
                )
                self.norm_q = norm_layer(dim_conv)
            if kernel_kv:
                self.pool_k = nn.Conv2d(
                    dim_conv,
                    dim_conv,
                    kernel_kv,
                    stride=stride_kv,
                    padding=padding_kv,
                    groups=dim_conv,
                    bias=False,
                )
                self.norm_k = norm_layer(dim_conv)
                self.pool_v = nn.Conv2d(
                    dim_conv,
                    dim_conv,
                    kernel_kv,
                    stride=stride_kv,
                    padding=padding_kv,
                    groups=dim_conv,
                    bias=False,
                )
                self.norm_v = norm_layer(dim_conv)
        else:
            raise NotImplementedError(f"Unsupported model {mode}")

        # relative pos embedding
        self.rel_pos_type = rel_pos_type
        if self.rel_pos_type == 'spatial':
            assert feat_size[0] == feat_size[1]
            size = feat_size[0]
            q_size = size // stride_q[1] if len(stride_q) > 0 else size
            kv_size = size // stride_kv[1] if len(stride_kv) > 0 else size
            rel_sp_dim = 2 * max(q_size, kv_size) - 1

            self.rel_pos_h = nn.Parameter(torch.zeros(rel_sp_dim, self.head_dim))
            self.rel_pos_w = nn.Parameter(torch.zeros(rel_sp_dim, self.head_dim))
            trunc_normal_tf_(self.rel_pos_h, std=0.02)
            trunc_normal_tf_(self.rel_pos_w, std=0.02)

        self.residual_pooling = residual_pooling

    def forward(self, x, feat_size: List[int]):
        B, N, _ = x.shape
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -