Toybrick

Meet unsupported MaxPool attribute 'dilations'!

gotta

注册会员

积分
52
发表于 2024-5-30 21:24:20    查看: 594|回复: 2 | [复制链接]    打印 | 显示全部楼层
您好!
在rk3588部署yolov8的过程中,将onnx文件转换为rknn时,出现如下错误:
E RKNN: [08:42:37.957] Meet unsupported MaxPool attribute 'dilations'!

W __init__: rknn-toolkit2 version: 1.4.0-22dcfef4
--> Config model
done
--> Loading model
done
--> Building model
Analysing : 100%|███████████████████████████████████████████████| 161/161 [00:00<00:00, 2693.74it/s]
Quantizating : 100%|██████████████████████████████████████████████| 161/161 [00:08<00:00, 18.17it/s]
W build: The default input dtype of 'images' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of '318' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'onnx::ReduceSum_326' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of '331' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of '338' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'onnx::ReduceSum_346' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of '350' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of '357' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of 'onnx::ReduceSum_365' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!
W build: The default output dtype of '369' is changed from 'float32' to 'int8' in rknn model for performance!
                      Please take care of this change when deploy rknn model with Runtime API!

请问如何解决
回复

使用道具 举报

1569063835

新手上路

积分
30
发表于 2024-7-10 11:53:05 | 显示全部楼层
你好,请问你的问题解决了吗?我也遇到了相同的问题
回复

使用道具 举报

jefferyzhang

版主

积分
13194
发表于 2024-7-10 16:25:24 | 显示全部楼层
1. 参考官方yolov8转好的示例进行
2. drv和api版本请保持一致和最新
3. 转换时候onnx、pt等版本请严格按照rknn的文档要求搭建,太高就会有一些奇怪的属性不支持
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

产品中心 购买渠道 开源社区 Wiki教程 资料下载 关于Toybrick


快速回复 返回顶部 返回列表