【摘要】 为了提高训练后量化模型的性能,提出一种基于离群值去除的模型训练后量化预处理方法。该方法仅通过排序、比较等简易的操作,实现权重、激活值的离群值去除,使模型在量化时仅损失少量的信息,从而提升量化模型的精度。实验结果表明,在使用不同的量化方法前,采用所提方法进行预处理,可显著地提升性能。更多还原

【Abstract】 In order to improve the performance of post training quantization model, a quantization preprocessing method based on outlier removal is proposed. This method is simple and easy to use. The outliers of weight and activation value are removed only through simple operations such as sorting and comparison, so that the quantization model loses only a small amount of information and improves the accuracy. The experimental results show that the performance can be significantly improved by preprocessing with this method before using different quantization methods.更多还原