How to run
download required files
make build_image
make download
Docker version
-
install docker https://docs.docker.com/desktop/mac/install/
-
build image to run object detection
make build_image
- run with docker image
# make run.simple {target-file} {output-file-name}
make run.simple FILENAME=data/kite.jpg OUTPUTFILENAME=kite_observed.jpg
conda version
- install conda
- build conda env
make conda.build.env
- run virtual environment
conda activate yolo_python
- run following commands
image
#python detect_simple.py {image dir} {output-file-name}
python detect_simple.py ./data/kite.jpg kite_observed.jpg
video
#python detect_simple.py {video dir} {output-file-name}
python detect_video_simple.py ./data/mv.mp4 road_detected.mp4
Note for me
How to create conda environment with file
conda env create --name yolo_python --file environment.yaml
How to build conda environment
conda create --name yolo_python python=3.6 pip install -r requirements.txt conda env export > environment.yaml
run with conda environment
References
https://github.com/kairess/tensorflow-yolov4-tflite -> most of codes are from this repository. I just changed it just for testing codes
- YOLOv4: Optimal Speed and Accuracy of Object Detection YOLOv4.
- darknet
- Yolov3 tensorflow
- Yolov3 tf2