DCNv2 CUDA 11.8 compatibility issue
https://github.com/lucasjinreal/DCNv2_latest GitHub - lucasjinreal/DCNv2_latest: DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+)DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+) - lucasjinreal/DCNv2_latestgithub.com
2024.07.01
no image
RuntimeError: DataLoader worker (pid 144028) is killed by signal: Bus error. It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.
Docker 내 공유메모리 공간이 부족해서 난 에러다. 아래는 컨테이너를 실행할 때 공유 메모리 크기를 1GB로 설정하는 예시입니다:docker run --shm-size=1g -it /bin/bash
2024.06.28
no image
ImportError: /lib/aarch64-linux-gnu/libstdc++.so.6: version `GLIBCXX_3.4.29' not found
https://github.com/pybind/pybind11/discussions/3453 libstdc++.so.6: version `GLIBCXX_3.4.29' not found · pybind pybind11 · Discussion #3453I run this in pybind11 mkdir build cd build cmake .. make check -j 4 got ERROR: ...... Traceback (most recent call last): File "/home/shizuku/code/python/pybind11/tests/test_cmake_build/subdirector...github.com
2024.06.27
Terabee ToF sensor 값 읽기
https://github.com/Terabee TerabeeWe digitze movement. Terabee has 36 repositories available. Follow their code on GitHub.github.com 여기 SDK랑 다 있네요,, Python, C/C++ 다 됩니다  하하하하하하 괜히 16진수 값 분석하고 있었네요 하하하
2024.05.13
공유기에 잡히는 Ip 전부 확인하기
nmap -sP 192.168.0.1/24
2024.05.10
TensorRT Jetson
Jetson Dockerfile에서 TensorRT 라이브러리 경로는 /usr/include/aarch64-linux-gnu/ 안에 있음Ubuntu에 있는 것처럼 따로 TensorRT 경로 지정해줄필요 없음
2024.05.10
16진수 표현
ToF센서에서 16진수로 표현안되고 저렇게 받아와지는게 있는데 { ASCII코드로 표현되는건 저렇게 바뀜받은 데이터: b'(\xd5{T\n'
2024.05.10
no image
rtsp 에서 hls 변환할 때 영상이 보이지 않음
Chrome의 방화벽 문제인 것 같음 http형식에서는 비디오, 녹화가 setting에서 보면 막혀있는 것을 볼 수 있음
2024.04.22
no image
Jetson Yolov8 tutorial : ModuleNotFoundError: No module named 'ultralytics.yolo'
https://wiki.seeedstudio.com/YOLOv8-DeepStream-TRT-Jetson/ Deploy YOLOv8 with TensorRT and DeepStream SDK | Seeed Studio Wiki Deploy YOLOv8 on NVIDIA Jetson using TensorRT and DeepStream SDK - Data Label, AI Model Train, AI Model Deploy wiki.seeedstudio.com from ultralytics.YOLO.utils.torch_utils import select_device from ultralytics.YOLO.utils.tal import make_anchors line 4~5 줄을 아래와 같이 바꾸면 됩니다...
2024.04.05