Toybrick

标题: 错误: ElementwiseLogical: unsupported output type:3 [打印本页]

作者: ImmanuelLee    时间: 2024-1-30 09:53
标题: 错误: ElementwiseLogical: unsupported output type:3
问题背景:
我的目的是将,线性判别分析算法(一种机器学习算法)部署在香橙派5B的NPU上,让算法在NPU上运行。
过程,用pytorch库写LDA算法,转换为pt模型,pt模型转onnx模型,onnx模型转rknn模型,对rknn模型进行仿真运行,将rknn模型在香橙派5B中运行。
rknn模型的仿真运行,程序为:https://gitee.com/collisionandco ... RKNN_Lee20240126.py
rknn模型的仿真运行,conda环境为:https://gitee.com/collisionandco ... ist_Lee20240130.txt
rknn模型的仿真运行,onnx模型为:https://gitee.com/collisionandco ... ne_Lee20240122.onnx


rknn模型在香橙派5B的运行,程序为:https://gitee.com/collisionandco ... rknn_Lee20240124.py
rknn模型在香橙派5B的运行,conda环境为:https://gitee.com/collisionandco ... ist_Lee20240130.txt
rknn模型在香橙派5B的运行,rknn模型为:https://gitee.com/collisionandco ... .6_Lee20240126.rknn

问题现象:

仿真运行的分类输出结果为:1。

香橙派5B运行的分类输出出结果为:0。

香橙派5B运行报错为:
W Query dynamic range failed. Ret code: RKNN_ERR_MODEL_INVALID. (If it is a static shape RKNN model, please ignore the above warning message.)
E RKNN: [09:08:59.706] ElementwiseLogical: unsupported output type:3
E RKNN: [09:08:59.706] Op type:Greater, name: Greater:Greater_7, fallback cpu failed. please try updating to the latest version of the toolkit2 and runtime from: https://console.zbox.filez.com/l/I00fc3 (PWD: rknn)
E RKNN: [09:08:59.707] output dtype is undefine!


求助,如何解决。






作者: ImmanuelLee    时间: 2024-2-25 18:16
顶~!
跪求大佬帮忙。




欢迎光临 Toybrick (https://t.rock-chips.com/) Powered by Discuz! X3.3