Spaces:
Runtime error
Runtime error
File size: 2,679 Bytes
97069e1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
import os
import platform
import torch
from torch import nn
from torch.autograd import Function
import torch.nn.functional as F
from torch.utils.cpp_extension import load
use_fallback = False
# Try loading precompiled, otherwise use native fallback
try:
import fused
except ModuleNotFoundError as e:
print('StyleGAN2: Optimized CUDA op FusedLeakyReLU not available, using native PyTorch fallback.')
use_fallback = True
class FusedLeakyReLUFunctionBackward(Function):
@staticmethod
def forward(ctx, grad_output, out, negative_slope, scale):
ctx.save_for_backward(out)
ctx.negative_slope = negative_slope
ctx.scale = scale
empty = grad_output.new_empty(0)
grad_input = fused.fused_bias_act(
grad_output, empty, out, 3, 1, negative_slope, scale
)
dim = [0]
if grad_input.ndim > 2:
dim += list(range(2, grad_input.ndim))
grad_bias = grad_input.sum(dim).detach()
return grad_input, grad_bias
@staticmethod
def backward(ctx, gradgrad_input, gradgrad_bias):
out, = ctx.saved_tensors
gradgrad_out = fused.fused_bias_act(
gradgrad_input, gradgrad_bias, out, 3, 1, ctx.negative_slope, ctx.scale
)
return gradgrad_out, None, None, None
class FusedLeakyReLUFunction(Function):
@staticmethod
def forward(ctx, input, bias, negative_slope, scale):
empty = input.new_empty(0)
out = fused.fused_bias_act(input, bias, empty, 3, 0, negative_slope, scale)
ctx.save_for_backward(out)
ctx.negative_slope = negative_slope
ctx.scale = scale
return out
@staticmethod
def backward(ctx, grad_output):
out, = ctx.saved_tensors
grad_input, grad_bias = FusedLeakyReLUFunctionBackward.apply(
grad_output, out, ctx.negative_slope, ctx.scale
)
return grad_input, grad_bias, None, None
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, negative_slope=0.2, scale=2 ** 0.5):
if use_fallback or input.device.type == 'cpu':
return scale * F.leaky_relu(
input + bias.view((1, -1)+(1,)*(input.ndim-2)), negative_slope=negative_slope
)
else:
return FusedLeakyReLUFunction.apply(input, bias, negative_slope, scale)
|