Training doesn't converge for Mapillary Vistas Dataset training with MaskRCNN

[edit_or]

Let me retrain with 125 classes.
Here in the original post said 124 classes.

Mapillary

Then he also train with 124 classes.

But in my python code for MapillarytoCOCO conversion, I have only 18 classes as shown in main.py
main.py (9.6 KB)

Original is 37+1 classes