reminisce commented on issue #9552: [REQUEST FOR REVIEW | DO NOT MERGE] Model Quantization with Calibration URL: https://github.com/apache/incubator-mxnet/pull/9552#issuecomment-360964778 @jinhuang415 1. The parameters are quantized offline, which means the min/max values were pre-calculated before inference. 2. In theory, if the calibration dataset is representative enough of the real inference image sets, more examples used for calibration should lead to less accuracy loss. The purpose of using entropy calibration is to keep the accuracy loss stable with respect to the number of examples used for calibration. The naive calibration approach suffers from more calibration examples leads to bigger accuracy loss as you can see the trend in the last two tables. My guess is that if the calibration dataset contains examples that are not similar to real inference images, the quantization thresholds might be biased by those examples and result in a little drop down of accuracy.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
