def forward()

in point_e/models/transformer.py [0:0]

• 12 lines of code
• 1 McCabe index (conditional complexity)

    def forward(self, qkv):
        bs, n_ctx, width = qkv.shape
        attn_ch = width // self.heads // 3
        scale = 1 / math.sqrt(math.sqrt(attn_ch))
        qkv = qkv.view(bs, n_ctx, self.heads, -1)
        q, k, v = torch.split(qkv, attn_ch, dim=-1)
        weight = torch.einsum(
            "bthc,bshc->bhts", q * scale, k * scale
        )  # More stable with f16 than dividing afterwards
        wdtype = weight.dtype
        weight = torch.softmax(weight.float(), dim=-1).type(wdtype)
        return torch.einsum("bhts,bshc->bthc", weight, v).reshape(bs, n_ctx, -1)