Rate this Page
★★★★★

InstanceNorm2d#

classtorch.ao.nn.quantized.InstanceNorm2d(num_features,weight,bias,scale,zero_point,eps=1e-05,momentum=0.1,affine=False,track_running_stats=False,device=None,dtype=None)[source]#

This is the quantized version ofInstanceNorm2d.

Additional args:

  • scale - quantization scale of the output, type: double.

  • zero_point - quantization zero point of the output, type: long.