Yash Anchaliya

@harindra2002 so adaboost will always give poor results if classes are higher if we use decision stump as weak learner?

This is due to mask_blur Set mask_blur to zero Try to increase the masked padding pixels till 100

@priyanshu7401 can you share your work mine accuracy is also around 34%I tried 2d cnn Training data accuracy is 99% but testing data is around 33%