evaluate.py文件中有一个问题

[yobuwen]

evaluate.py中没有lsqprepare函数，如果把其改为lsqprepareV1然后加载训练好的模型进行评估，发现精度会非常低。 请问，在仅进行推断时，加载的模型和量化操作是不是和训练时有什么不同？

[ZouJiu1]

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

[yobuwen]

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？

[ZouJiu1]

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

[ZouJiu1]

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

[yobuwen]

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。