GroupNorm¶
-
class
torch.nn.quantized.GroupNorm(num_groups, num_channels, weight, bias, scale, zero_point, eps=1e-05, affine=True, device=None, dtype=None)[source]¶ This is the quantized version of
GroupNorm.- Additional args:
scale - quantization scale of the output, type: double.
zero_point - quantization zero point of the output, type: long.
