Install YOLOV from source.

git clone [email protected]:YuHengsss/YOLOV.git
cd YOLOV

Create conda env.

conda create -n yolov python=3.7

conda activate yolov

pip install -r requirements.txt

pip3 install -v -e .

Step1. Download a pretrained weights.

Step2. Run yolov demos. For example:

python tools/vid_demo.py -f [path to your yolov exp files] -c [path to your yolov weights] --path /path/to/your/video --conf 0.25 --nms 0.5 --tsize 576 --save_result 

For online mode, exampled with yolov_l, you can run:

python tools/yolov_demo_online.py -f ./exp/yolov/yolov_l_online.py -c [path to your weights] --path /path/to/your/video --conf 0.25 --nms 0.5 --tsize 576 --save_result 

For yolox models, please use python tools/demo.py for inferencing.

Step1. Download datasets and weights:

Download ILSVRC2015 DET and ILSVRC2015 VID dataset from IMAGENET and organise them as follows:

path to your datasets/ILSVRC2015/
path to your datasets/ILSVRC/

Download our COCO-style annotations for training, FGFA version training annotation and video sequences. Then, put them in these two directories:

YOLOV/annotations/vid_train_coco.json
YOLOV/annotations/ILSVRC_FGFA_COCO.json
YOLOV/yolox/data/dataset/train_seq.npy

Change the data_dir in exp files to [path to your datasets] and Download our weights.

Step2. Generate predictions and convert them to IMDB style for evaluation.

python tools/val_to_imdb.py -f exps/yolov/yolov_x.py -c path to your weights/yolov_x.pth --fp16 --output_dir ./yolov_x.pkl

Evaluation process:

python tools/REPPM.py --repp_cfg ./tools/yolo_repp_cfg.json --predictions_file ./yolov_x.pkl --evaluate --annotations_filename ./annotations/annotations_val_ILSVRC.txt --path_dataset [path to your dataset] --store_imdb --store_coco  (--post)

(--post) indicates involving post-processing method. Then you will get:

{'mAP_total': 0.8758871720817065, 'mAP_slow': 0.9059275666099181, 'mAP_medium': 0.8691557352372217, 'mAP_fast': 0.7459511040452989}

Training example

python tools/vid_train.py -f exps/yolov/yolov_s.py -c weights/yoloxs_vid.pth --fp16

Roughly testing

python tools/vid_eval.py -f exps/yolov/yolov_s.py -c weights/yolov_s.pth --tnum 500 --fp16

tnum indicates testing sequence number.

Training base detector

The train_coco.json is a COCO format annotation file. When trainig the base detector on your own dataset, try to convert the annotation to COCO format.

Training YOLOV Series

The train_seq.npy and val_seq.npy files are numpy arrays of lists. They can be loaded using the following command:

numpy.load('./yolox/data/datasets/train_seq.npy',allow_pickle=True)

Each list contains the paths to all images in a video. The specific annotations(xml annotation in VID dataset) are loaded via these image paths, refer to

1. Finetuing the base detector(YOLOX) on your custom dataset with COCO format annotation. You need to modify the YOLOX experiment file. For instance, the experiment file for the Imagenet VID dataset is modified as this example. Initialized weights with COCO pretraining is essential for the performance, you can find these coco pretrained weights in YOLOX official repo (YOLOX-S~YOLOX-X) and this huggingface repo (YOLOX-SwinTiny and SwinBase).

2. Construct your dataset in the COCO format. Here is a template for the dataset structure (sourced from OVIS):

   {
   "info" : info,
   "videos" : [video],
   "annotations" : [annotation] or None,
   "categories" : [category],
   }
   video{
       "id" : int,
       "width" : int,
       "height" : int,
       "length" : int,
       "file_names" : [file_name],
   }
   annotation{
       "id" : int, 
       "video_id" : int, 
       "category_id" : int, 
       "areas" : [float or None], 
       "bboxes" : [[x,y,width,height] or None], 
       "iscrowd" : 0 or 1,
   }
   category{
       "id" : int, 
       "name" : str, 
       "supercategory" : str,
   }

   After preparing the COCO format dataset, we provide code which converts the COCO format annotation for video object detection. You can construct your experiment file of YOLOV such as YOLOVs_OVIS. For YOLOV , you can combine the this dataloader with the default experiment file for training on the custom dataset.

3. Initialize the YOLOV or YOLOV with finetuned weights obtained by Step 1. Note that you may adjust the hyperparameters such as proposal numbers according to your dataset for getting better performance.

• https://github.com/Megvii-BaseDetection/YOLOX
• https://github.com/AlbertoSabater/Robust-and-efficient-post-processing-for-video-object-detection