From 1ead4d896c6012c77a42ea710a7a735a3654a222 Mon Sep 17 00:00:00 2001 From: "zhangbin.zhu" Date: Tue, 17 Oct 2023 17:15:16 +0800 Subject: [PATCH] add OC_SORT PaddlePaddle link #I85WEC add OC_SORT PaddlePaddle Signed-off-by: zhangbin.zhu --- cv/detection/oc_sort/paddlepaddle/README.md | 59 +++++++++++++++++++++ 1 file changed, 59 insertions(+) create mode 100644 cv/detection/oc_sort/paddlepaddle/README.md diff --git a/cv/detection/oc_sort/paddlepaddle/README.md b/cv/detection/oc_sort/paddlepaddle/README.md new file mode 100644 index 00000000..01a7c6da --- /dev/null +++ b/cv/detection/oc_sort/paddlepaddle/README.md @@ -0,0 +1,59 @@ +# OC_SORT + +## Model description +Observation-Centric SORT (OC-SORT) is a pure motion-model-based multi-object tracker. It aims to improve tracking robustness in crowded scenes and when objects are in non-linear motion. It is designed by recognizing and fixing limitations in Kalman filter and SORT. It is flexible to integrate with different detectors and matching modules, such as appearance similarity. It remains, Simple, Online and Real-time. + +## Step 1: Installing +```bash +git clone https://github.com/PaddlePaddle/PaddleDetection.git +``` + +```bash +cd PaddleDetection +yum install mesa-libGL -y + +pip3 install -r requirements.txt +pip3 install protobuf==3.20.1 +pip3 install urllib3==1.26.6 +pip3 install certifi==2018.8.13 + +``` + +## Step 2: Prepare Datasets + +Download [MOT17](https://motchallenge.net/), [MOT20](https://motchallenge.net/), [CrowdHuman](https://www.crowdhuman.org/), [Cityperson](https://github.com/Zhongdao/Towards-Realtime-MOT/blob/master/DATASET_ZOO.md), [ETHZ](https://github.com/Zhongdao/Towards-Realtime-MOT/blob/master/DATASET_ZOO.md) and put them under /datasets in the following structure: + +```bash +datasets + |——————mot + | └——————train + | └——————test + └——————crowdhuman + | └——————Crowdhuman_train + | └——————Crowdhuman_val + | └——————annotation_train.odgt + | └——————annotation_val.odgt + └——————MOT20 + | └——————train + | └——————test + └——————Cityscapes + | └——————images + | └——————labels_with_ids + └——————ETHZ + └——————eth01 + └——————... + └——————eth07 +``` + +## Step 3: Training + +```bash +cd PaddleDetection + +python3 -m paddle.distributed.launch --log_dir=ppyoloe --gpus 0,1,2,3,4,5,6,7 tools/train.py -c configs/mot/bytetrack/detector/yolox_x_24e_800x1440_mix_mot_ch.yml --eval --amp +``` + +## Step 4: result + +## Reference +- [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) -- Gitee