op/fused_act_cpu.py

import os

import torch
from torch import nn
from torch.autograd import Function
from torch.nn import functional as F


module_path = os.path.dirname(__file__)


class FusedLeakyReLU(nn.Module):
    def __init__(self, channel, negative_slope=0.2, scale=2 ** 0.5):
        super().__init__()

        self.bias = nn.Parameter(torch.zeros(channel))
        self.negative_slope = negative_slope
        self.scale = scale

    def forward(self, input):
        return fused_leaky_relu(input, self.bias, self.negative_slope, self.scale)

def fused_leaky_relu(input, bias=None, negative_slope=0.2, scale=2 ** 0.5):
    if input.device.type == "cpu":
        if bias is not None:
            rest_dim = [1] * (input.ndim - bias.ndim - 1)
            return (
                F.leaky_relu(
                    input + bias.view(1, bias.shape[0], *rest_dim), negative_slope=0.2
                )
                * scale
            )

        else:
            return F.leaky_relu(input, negative_slope=0.2) * scale

    else:
        return FusedLeakyReLUFunction.apply(
            input.contiguous(), bias, negative_slope, scale
        )