model performance on cerulean cloud deployment differs from local inference

[rbavery]

Once @jonaraphael returns from leave we should review the model inferencing steps within the cerulean deployment and new Mask R-CNN model and compare how they match with local inference for the same test images we've been looking at locally. Jona noted that after resolving deployment and predict endpoint issues, there are no tracebacks but performance is low, with 0 out of 100 slicks inferenced. I think it's possible we are missing the multi class NMS step (and potentially other steps) on cerulean cloud since Jona recently added this.