Hi,
I quantized a DLC using snpe-dlc-quantize with --axis_quant flag and without it. I got two different results, but no evidence of per-axis
quantization actually happening. For instance, with axis_quant:
[INFO] Setting activation for layer: StatefulPartitionedCall/model/expanded_conv_depthwise/depthwise and buffer: StatefulPartitionedCall/model/expanded_conv_depthwise_BN/FusedBatchNormV3:0
[INFO] bw: 8, min: -11.527022, max: 21.499841, delta: 0.129517, offset: -89.000000
without:
[INFO] Setting activation for layer: StatefulPartitionedCall/model/expanded_conv_depthwise/depthwise and buffer: StatefulPartitionedCall/model/expanded_conv_depthwise_BN/FusedBatchNormV3:0
[INFO] bw: 8, min: -13.750229, max: 25.646496, delta: 0.154497, offset: -89.000000
Clearly, min and max values are different. However, shouldn't there be [min, max] values per axis of the conv layer?
Dear customer,
What's SNPE version you have used? The option of --axis_quant is for per axis or channel quantization. That behavior will impact the final dlc encodings.
BR.
Wei
I've used SNPE version 1.59, the latest version at this time.
How can I see what are the min, max delta and offset values per axis of some layer? Is there a way to input the per-axis values manually?
Thanks
Dear customer,
SNPE supported the per-channel quantization. You can quantized the model with options of --axis_quant