JSnobody

@aloyschen By the way, I want to train COCO dataset on the project, tensorflow-yolo3. For training, will it be slower than darknet? Could you share your experience of training on...

@aloyschen @DW1HH can we communicate by mail? My address is [email protected]. Thanks!

@aloyschen hi, that looks like much better than inference.

楼主可以建个群，大家可以多交流交流噢

@cjzz，hello，请问有回复你吗

了解了，我从代码上看是keras用的numpy fp32转到fp16，想了解numpy是如何转换的，是否存在计算时溢出的问题。谢谢

请问一下tensorflow的量化工具是否有研究过呢？

@huangshenneng 做量化，再做反量化是必须的啊，因为下一个量化的算子缩放范围是不一样的了。除非所有的缩放是一个因子，那么可以中间不做反量化，最后输出fp32的时候再做反量化。