github dbro/frigate-detector-edgetpu-yolo9 v1.0-prerelease

latest releases: v1.7, v1.6, v1.5...
pre-releaseone month ago

THIS RELEASE SHOULD NOT BE USED.

The model file here is NOT COMPATIBLE with the current version of edgetpu_tfl.py and it runs slower than the current version of the model from release v1.0

yolov9-s-relu6-10epoch-17class_320_int8_edgetpu.zip
Then unzip the file to get the TFLite file that Frigate can work with.

Model weights file for YOLO v9 "s" with resolution 320x320 compiled to run on Google Coral using the modified edgetpu detector plug-in code

17 classes of objects can be detected (a subset of COCO's 80 classes)

Model performance after 10 epochs of fine-tuning.
epoch, train/box_loss, train/cls_loss, train/dfl_loss, metrics/precision, metrics/recall, metrics/mAP_0.5,metrics/mAP_0.5:0.95, val/box_loss, val/cls_loss, val/dfl_loss, x/lr0, x/lr1, x/lr2
9, 1.47, 1.3719, 1.649, 0.75295, 0.65368, 0.72426, 0.54616, 0, 0, 0, 0.00208, 0.00208, 0.00208

Additional epochs might improve the performance, and lead to future updated releases here.

Don't miss a new frigate-detector-edgetpu-yolo9 release

NewReleases is sending notifications on new releases.