On folder Result ssd7 panel show code (jupyter notebook), weight and result of this model (mAP 89.8%).
On folder Result yolo3 panel weight and result of this model (mAP 86.3%).
On folder Result ssd300 fault 1 show code (jupyter notebook), weight and result of this model (mAP 79.5%).
On folder Result yolo3 fault 1 show history train, weight and result of this model (mAP 73.02%).
On folder Result yolo3 fault 2 show history train, weight and result of this model (mAP 71.93%).
On folder Result yolo3 fault 4 show history train, weight and result of this model (mAP 66.22%).
To use the detector we must only use 'panel_yolo3_disconnect.py' with the previously established form, that is:
python predict_yolo3_disconnect.py -c config_full_yolo_panel_infer.json -i /path/to/image/ -o /path/output/result
To use this model, only the yolo3_panel detector model is needed.
The idea to detect the disconnection is by calculating the luminosity of each panel, to then normalize this data and highlight the panels with a luminosity out of normality.