evaluate.py support other data format?

[peacherwu]

Is there a way I can run evaluate.py on a separate test set with trained models? It appears it doesn't support oid and a couple of other formats where train.py does.

[hgaiser]

Those datasets, like OID, have been added later via community contributions. If you want to make a PR to add them to evaluate.py then it would be much appreciated.