XiongshiDeng
XiongshiDeng
## 我正在使用ncnn2mem转换的id.h和mem.h头文件进行加密处理,打包成so动态库 当我使用load_param()和load_model()从mem.h中加载字节数组时,使用cmake编译,显示virtual memory exhausted: Cannot allocate memory报错,我使用的是虚拟机ubuntu20,海思交叉编译环境是hisix200或者hisix400,下面是错误显示 `dxs@dxs-ubuntu:~/nfsroot/yolov5/build$ cmake ..` -- YOLOV5_VERSION_STRING = 1.0.20220902 -- Found OpenMP_C: -fopenmp -- Found OpenMP_CXX: -fopenmp OPENMP FOUND -- Found OpenMP_C: -fopenmp --...
@RangiLyu, can you give me an example. Thank you!
@ZhangPHEngr 你好,请问视频中只有一个目标,进行追踪,程序还有效吗
你好,我把你的代码进行了部分更改,部署到hi3521dv200上,在进行模型推理的时候报错: [Level]:Error,[Func]:NNIE_Forward [Line]:203 [Info]:Error,HI_MPI_SVP_NNIE_Forward failed! [Level]:Error,[Func]:NNIE_Forward_From_Data [Line]:331 [Info]:Error,SAMPLE_SVP_NNIE_Forward failed! 能请教下是哪方面出现问题了吗
运行train.py时出现RecursionError: maximum recursion depth ,按照网上的修改 import sys sys.setrecursionlimit(100000) #设置递归深度 也没用 `Traceback (most recent call last): File "D:\Anaconda3\envs\py36\lib\code.py", line 91, in runcode exec(code, self.locals) File "", line 1, in File "D:\Program...
@HonglinChu 你好,我想下载coco数据,但是您给的百度云链接失效,能否重新更新下,谢谢
@HonglinChu 你好,我在虚拟机上运行提供的程序,把ncnn替换成我自己编译好的静态库和头文件,opencv是4.6版本。当我进行测试跟踪车时,出现上面说的情况,下面是我保存的跟踪视频: https://cowtransfer.com/s/4492e82b4e704d 点击链接查看 [ output_video.mp4 ] ,或访问奶牛快传 cowtransfer.com 输入传输口令 1piat6 查看;
你好,我把你的代码进行了部分更改,部署到hi3521dv200上,在进行模型推理的时候报错: [Level]:Error,[Func]:NNIE_Forward [Line]:203 [Info]:Error,HI_MPI_SVP_NNIE_Forward failed! [Level]:Error,[Func]:NNIE_Forward_From_Data [Line]:331 [Info]:Error,SAMPLE_SVP_NNIE_Forward failed! 能请教下是哪方面出现问题了吗
@Gumpest 你好,支持把yolov5s-pruning.yaml中的nn.Upsample替换成nn.ConvTranspose2d进行prune吗?我进行替换后,按照给的文档训练一遍模型后,运行pruneEagleEye.py报错: ``` File "/root/.pycharm_helpers/pydev/pydevd.py", line 1491, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "/root/.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile exec(compile(contents+"\n", file, 'exec'), glob, loc) File "/data/yolov5/pruneEagleEye.py", line...