Your browser does not seem to support JavaScript. As a result, your viewing experience will be diminished, and you may not be able to execute some actions.
Please download a browser that supports JavaScript, or enable it if it's disabled (i.e. NoScript).
用 H7 Plus 跑一个自己训练的 TFLite 的人脸识别模型,只有 12M 的大小。运行正常,但是每次推理的时候延时很严重,能到30秒左右的帧缓冲区卡住。XDJM 们有什么优化的方法吗?试过转化为量化 TFLite,可以压缩到 4M 左右,但跑不起来,报错。目测 OpenMV 目前固件还不支持。