adds uncertainty sampling

[naxatra2]

Adds #13

This PR adds uncertainty sampling and Query by Committee (QBC) method for sampling images. Both of them have a very basic implementation as of now. I am planning to add more sampling techniques and improve the ones already present.

[naxatra2]

I used binary-focused uncertainty rather than multi-class methods (like entropy sampling) since:

Our model outputs single confidence scores, not multi-class probabilities. But I am confused on whether I should also add the multi-class functionalities. Binary margin sampling is computationally efficient and better for our use case.

Entropy sampling would yield nearly identical results for binary classification but it will add unnecessary complexity
The most uncertain samples (scores closest to 0.5) get prioritized for annotation, which should help improve model performance around the decision boundary where it's currently struggling.

I am currently also exploring a new sampling technique "MC Dropout"

[bw4sz]

This is great, and I welcome it. But to be clear, the GSOC project should contribute to the DeepForest repo, but maybe you are just also adding this. The BOEM repo isn't really ready for outside use, the data comes from internal, the tests aren't stable.