FakeQuantizePerChannelAffine¶

Simulates quantization per channel.

Abstract Signature:

FakeQuantizePerChannelAffine(input: Tensor, scale: Tensor, zero_point: Tensor, axis: int, quant_min: int, quant_max: int)

API: torch.fake_quantize_per_channel_affine

Strategy: Direct Mapping

API: tf.quantization.fake_quant_with_min_max_vars_per_channel

Strategy: Plugin (fake_quant_adapter)