Incosistent Accuracy Between Python and C Implementation about nnom HOT 2 CLOSED

I dont know your training setting, such as epoch number.

I recommend setting lower epoch number because unaware-quantization training can lead to extreme weights and data which cause 8 bit quantization out of effective ranges. For example, the majority of data are laying around +-8 but some data goes up to -1000 for the input of some activations. When it comes to quantization, it needs to cover the range of 1000, set Q number to -2, then most of the data are down sampled.

You may try

• add batchnorm after conv. This constrains the data range.
• reduce epoch number to 10 to see if it improves. Lower epoch number
• enable "KLD" quantisation method instead of the default "max-min". KLD deletes extreme values. but sometime reduce affect the result.

from nnom.

I dont know your training setting, such as epoch number.

I recommend setting lower epoch number because unaware-quantization training can lead to extreme weights and data which cause 8 bit quantization out of effective ranges. For example, the majority of data are laying around +-8 but some data goes up to -1000 for the input of some activations. When it comes to quantization, it needs to cover the range of 1000, set Q number to -2, then most of the data are down sampled.

You may try

• add batchnorm after conv. This constrains the data range.
• reduce epoch number to 10 to see if it improves. Lower epoch number
• enable "KLD" quantisation method instead of the default "max-min". KLD deletes extreme values. but sometime reduce affect the result.

Thank you for the help @majianjia.

We ended up modifying our data preprocessing and input layer and that seemed to help for quantization. Simply having more neurons in our input layer seemed to mitigate the issue. Thank you again.

from nnom.