rknn-toolkit2
rknn-toolkit2 copied to clipboard
rockchip-linux
I am using Luckfox RV1103 board and trying to run yolov5. I successfully build rknn_yolov5_demo and push it on the board, following the instructions in the readme. When running the...
使用yolov8训练出一个检测的模型，P2-P4导出的onnx，对应的stride是{4,8,16}。在RK3588盒子上使用C++推理不准确(与python端对不上)，而使用P3-P5导出的onnx模型，推理结果正常，请问是什么原因？
we are trying to run the simple resnet18 model on aarch64 platform and get the following error. ```D target set by user is: None D Starting ntp or adb, target...
问题描述： 使用香橙派5推理yolov7_tiny的rknn模型，单核推理时，推理正常；双核推理时出现 failed to submit!, op name: concat错误，频率约400帧/次；三核推理也会出现同样的错误，频率50帧/次。 猜测：yolov7_tiny中的报错concat位于主干网络ELAN模块，是否由于三核未设置同步导致？
E RKNN: failed to submit! Op id:3 , op name: conv:inputs.3_Conv_pads_conv, flags: 0x5, task start:0,task number:218,run task number:218 , run task counter: 146 int status: 0 这个模型我在PC上RKNN的仿真里面是跑通了的，没有failed to submit，但是在3588的板子上面用rknn-toolkit-lite跑就会出问题 RKNN...
### 模型 [ch_ppstructure_mobile_v2.0_SLANet](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) ### 转换过程 paddle->onnx->rknn ### 转换工具 paddle->onnx工具版本 : Paddle2ONNX Version:1.1.0 Paddle2ONNX now only support opset version in range of [7, 17]. onnx->rknn工具版本: rknn_toolkit2-1.5.3b21+11d8562a-cp38-cp38-linux_x86_64.whl rknn_toolkit2-1.6.0+81f21f4d-cp38-cp38-linux_x86_64.whl rknn_toolkit2-1.6.1b16+e3c0774a-cp38-cp38-linux_x86_64.whl rknn_toolkit2-1.6.2b3+eeda9fd5-cp38-cp38-linux_x86_64.whl 这几个toolkit都试过报一样的错误 ###...
RK3588板环境 系统版本：ubuntu 22.04 rknpu2-dev: 1.5.2 PC环境： 系统版本：ubuntu 22.04 python: 3.8 rknn-toolkit2: 1.5.2+b642f30c 问题描述： 1）YOLOv8-seg模型量化精度异常 2）rknn-toolkit2配置未生效 复现步骤： 模型：官方yolov8s-seg.pt模型https://github.com/ultralytics/assets/releases/download/v8.1.0/yolov8s-seg.pt 转换脚本： ``` from rknn.api import RKNN # COCO ONNX_MODEL = './yolov8s-seg.onnx' RKNN_MODEL =...
build rknn model from yolox, have a build error: E build: Catch exception when building RKNN model! E build: Traceback (most recent call last): E build: File "rknn/api/rknn_base.py", line 1549,...
can anyone explain the following code functionality ```python3 -m rknn.api.rknn_convert -t rk3568 -i ./model_config.yml -o ./ ``` how to execute .rknn (file which is output for running python test.py )...
RT，报错日志如下: ```log firefly@zt-firefly ~/r/n/1.6.2b3> sudo cp ./librknnrt.so /usr/lib/;sudo ./rknn_server start rknn server, version:1.6.0 (535b468 build@2023-12-11T17:05:07) I NPUTransfer: Starting NPU Transfer Server, Transfer version 2.1.0 (b5861e7@2020-11-23T11:50:51) arm_release_ver: g13p0-01eac0, rk_so_ver: 6 E...
