Low accuracy for MS COCO dataset in tao maskrcnn model training

[Morganh]

@adithya.ajith

can you also explain how training config changes between running training on a single GPU vs multiple GPUs.

You can refer to Poor metric results after retraining maskrcnn using TLT notebook - #6 by Morganh.

@adithya.ajith

I have in the dataset is 16,270 compared to 118,287 in the original coco dataset.

You can use the same spec file.