Identify species/breeds of birds and dogs detected by frigate
4.9K
https://github.com/ljmerza/FrigateClassifier
Identify breeds/species of dogs and birds detected by blakeblackshear/frigate. This will try to identify a bird or dog and add a Frigate sublabel to that event.
Create a config.yml file in your docker volume with the following contents:
frigate:
frigate_url: http://127.0.0.1:5000
mqtt_server: 127.0.0.1
mqtt_auth: false
mqtt_username: username
mqtt_password: password
main_topic: frigate
camera:
- birdcam
bird_classification:
threshold: 0.7
dog_classification:
threshold: 0.7
logger_level: INFO
Update your frigate url, mqtt server settings. If you are using mqtt authentication, update the username and password. Update the camera name(s) to match the camera name in your frigate config.
docker run -v /path/to/config:/config -e TZ=America/New_York -it --rm --name frigate_classifier lmerza/frigate_classifier:latest
or using docker-compose:
services:
frigate_classifier:
image: lmerza/frigate_classifier:latest
container_name: frigate_classifier
volumes:
- /path/to/config:/config
restart: unless-stopped
environment:
- TZ=America/New_York
https://hub.docker.com/r/lmerza/frigateclassifier
set logger_level in your config to DEBUG to see more logging information:
...
logger_level: DEBUG
Logs will be in /config/frigateclassifier.log
The dog model was trained by Stanford Dogs Dataset
Code was adapted from mmcc-xx/WhosAtMyFeeder
Content type
Image
Digest
sha256:e01a6e6fb…
Size
982.6 MB
Last updated
about 2 months ago
docker pull lmerza/frigateclassifier