We recommend to divide the entire range of data into strata to later sample images from these strata. The procedure for data split generation is provided in the folder binning.

We explored two methods of sampling images from strata.

1. Round Robin sampling
2. Random sampling For a simple visualisation of the procedure you can refer to the folder sampling.

Add details of how to add the loss function ( the loss function defined file should be placed in this folder)

Add a notebook that takes the model and architecture loads it returns the mean and std and if a dataset name and its bins are provided generates the bin level plots (like our website) and plots that shows its performance sample wise across the count range.