Get real model’s params for getting regressor score
Model used : densenet, MobileNet from tflite model zoo, and hair segmentation, face detection from mediapipe github
total : 245 samples
But it seems worse…
I think it would be better to include some of benchamrks of the real model in the train set. Not all, but adding about 20% would be good.
Analyse Regressors
What is XGBoost?
eXtreame Gradient Boosting
It is an implementation of gradient boosting machines. It is a decision-tree based ensemble Machine learning algorithm that uses a gradient boosting framework. When it comes to small-to-medium structured/tabular data, decision tree based algorithm are considered best-in-class right now.