FusedBiasLeakyReLU¶
- class mmcv.ops.FusedBiasLeakyReLU(num_channels: int, negative_slope: float = 0.2, scale: float = 1.4142135623730951)[source]¶
Fused bias leaky ReLU.
This function is introduced in the StyleGAN2: Analyzing and Improving the Image Quality of StyleGAN
The bias term comes from the convolution operation. In addition, to keep the variance of the feature map or gradients unchanged, they also adopt a scale similarly with Kaiming initialization. However, since the \(1+{alpha}^2\) is too small, we can just ignore it. Therefore, the final scale is just \(\sqrt{2}\). Of course, you may change it with your own scale.
TODO: Implement the CPU version.
- Parameters
- forward(input: torch.Tensor) → torch.Tensor[source]¶
Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.