snowzach / doods2

API for detecting objects in images and video streams using Tensorflow
MIT License
232 stars 30 forks source link

yolov7 #86

Closed rgogada closed 1 year ago

rgogada commented 1 year ago

any plans to include yolov7? thanks.

snowzach commented 1 year ago

I almost got it working... I'm no pytorch expert... But using this for model file almost got it working WongKinYiu/yolov7,yolov7

rgogada commented 1 year ago

I really want to try this but if I pass config file like this, it is complaining about file not found.

docker-compose

doods: container_name: doods image: snowzach/doods2:amd64 environment:

config.yaml

doods: detectors:

docker logs

Traceback (most recent call last): File "main.py", line 75, in main() File "main.py", line 43, in main with open(config_file, 'r') as stream: FileNotFoundError: [Errno 2] No such file or directory: '/root/docker/doods/config.yaml'

snowzach commented 1 year ago

You're not actually mapping your config file into the container... Remove the CONFIG_FILE line from your docker compose. Instead, add a volumes field...

    volumes:
      - /root/docker/doods/config.yaml:/opt/doods/config.yaml
rgogada commented 1 year ago

volumes:

  • /root/docker/doods/config.yaml:/opt/doods/config.yaml

this is how I used to run the DOODS1. but surprisingly when I tried to run DOODS2 this way couple of months ago it didn't work. Anyway it now works. Thanks.