diff --git a/.gitattributes b/.gitattributes deleted file mode 100644 index f8ff2b5..0000000 --- a/.gitattributes +++ /dev/null @@ -1 +0,0 @@ -*.mp4 filter=lfs diff=lfs merge=lfs -text diff --git a/.gitignore b/.gitignore index e257658..5317a8c 100644 --- a/.gitignore +++ b/.gitignore @@ -32,3 +32,4 @@ *.out *.app +*.mp4 \ No newline at end of file diff --git a/Docs/2024-10-11/README.md b/Docs/2024-10-11/README.md index 6635bca..c9ce724 100644 --- a/Docs/2024-10-11/README.md +++ b/Docs/2024-10-11/README.md @@ -18,4 +18,4 @@ 2. 目前存在问题: 1. 跟踪精度低,存在严重的id switch问题 2. 行人重识别模型推理速度慢,占推理总流程时间的90%以上,需要再优化一下![alt text](image/image.png) -3. 尝试解决的方向是根据github上的[原项目](https://github.com/linghu8812/yolov5_fastreid_deepsort_tensorrt)进行优化,因为整个流程基本是根据这个项目来的,我估计应该是缺了一些设置导致上述的问题,使用原项目进行目标跟踪还是非常流畅的,[跟踪结果](video/object_track.mp4) +3. 尝试解决的方向是根据github上的[原项目](https://github.com/linghu8812/yolov5_fastreid_deepsort_tensorrt)进行优化,因为整个流程基本是根据这个项目来的,我估计应该是缺了一些设置导致上述的问题,使用原项目进行目标跟踪还是非常流畅的,[跟踪结果](video/video0.mp4) diff --git a/Docs/2024-10-11/video/object_track.mp4 b/Docs/2024-10-11/video/object_track.mp4 deleted file mode 100644 index 98ea369..0000000 --- a/Docs/2024-10-11/video/object_track.mp4 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7bd681d99333a0785a203312e70dc96a9fa06b9cc22671ad26f3500a4a55673c -size 17779447