Class QKVAttention

improved_diffusion/unet.py:233–275

A module which performs QKV attention.

class QKVAttention(nn.Module):
    """
    A module which performs QKV attention.
    """

    def forward(self, qkv):
        """
        Apply QKV attention.

        :param qkv: an [N x (C * 3) x T] tensor of Qs, Ks, and Vs.
        :return: an [N x C x T] tensor after attention.
        """
        ch = qkv.shape[1] // 3
        q, k, v = th.split(qkv, ch, dim=1)
        scale = 1 / math.sqrt(math.sqrt(ch))
        weight = th.einsum(
            "bct,bcs->bts", q * scale, k * scale
        )  # More stable with f16 than dividing afterwards
        weight = th.softmax(weight.float(), dim=-1).type(weight.dtype)
        return th.einsum("bts,bcs->bct", weight, v)

    @staticmethod
    def count_flops(model, _x, y):
        """
        A counter for the `thop` package to count the operations in an
        attention operation.

        Meant to be used like:

            macs, params = thop.profile(
                model,
                inputs=(inputs, timestamps),
                custom_ops={QKVAttention: QKVAttention.count_flops},
            )

        """
        b, c, *spatial = y[0].shape
        num_spatial = int(np.prod(spatial))
        # We perform two matmuls with the same number of ops.
        # The first computes the weight matrix, the second computes
        # the combination of the value vectors.
        matmul_ops = 2 * b * (num_spatial ** 2) * c
        model.total_ops += th.DoubleTensor([matmul_ops])


class UNetModel(nn.Module):