evaluate.py文件中有一个问题 about lsqplus HOT 5 CLOSED

If you train a quantized model with lsq or lsq+, when you inference a image, you don't need lsqprepareV1, lsqprepareV2. s lsqplusprepareV1 or lsqplusprepareV2, because the model' s params had been quantized while training.

so evaluate.py h "Floatmodel = True" #QAT or float-32 train ole

from lsqplus.

If you train a quantized model with lsq or lsq+, when you inference a image, you don't need lsqprepareV1, lsqprepareV2. s lsqplusprepareV1 or lsqplusprepareV2, because the model' s params had been quantized while training.

so evaluate.py h "Floatmodel = True" #QAT or float-32 train ole

还有一个问题就是，发现s会出现负数，但这显然是不合理的，请问有什么方式可以避免么？

from lsqplus.

You need training the lsq+ network to get high accuracy, then the weight or ccale will converge to >0, it need training not by setting

from lsqplus.

so, just training the network, you will find the last result will better

from lsqplus.

so, just training the network, you will find the last result will better

实时上，我使用LSQ+V1训练了VGG，精度达到90.481，但s值仍然有大量负值。这个现象好像很容易出现。

from lsqplus.