Returns a new tensor with the data in input
fake quantized per channel using scale
, zero_point
, quant_min
and quant_max
, across the channel specified by axis
.
output = ( m i n ( quant_max , m a x ( quant_min , std::nearby_int ( input / scale ) + zero_point ) ) − zero_point ) × scale \text{output} = ( min( \text{quant\_max}, max( \text{quant\_min}, \text{std::nearby\_int}(\text{input} / \text{scale}) + \text{zero\_point} ) ) - \text{zero\_point} ) \times \text{scale} output=(min(quant_max,max(quant_min,std::nearby_int(input/scale)+zero_point))−zero_point)×scale
>>> x = torch.randn(2, 2, 2) >>> x tensor([[[-0.2525, -0.0466], [ 0.3491, -0.2168]], [[-0.5906, 1.6258], [ 0.6444, -0.0542]]]) >>> scales = (torch.randn(2) + 1) * 0.05 >>> scales tensor([0.0475, 0.0486]) >>> zero_points = torch.zeros(2).to(torch.int32) >>> zero_points tensor([0, 0]) >>> torch.fake_quantize_per_channel_affine(x, scales, zero_points, 1, 0, 255) tensor([[[0.0000, 0.0000], [0.3405, 0.0000]], [[0.0000, 1.6134], [0.6323, 0.0000]]])
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4