Deep Learning Practical
How to deal with highly imbalanced data?
- Data -
- undersampling
- oversampling
- SMOTE
- synthetic samples
- Model -
- class-weights proportional to number of samples
- large batches so that each batch contains at least a few positive samples
- monitor precision and recall, not accuracy
- focal loss
References
How to handle imbalance data
Handling imbalance dataset in deep learning
Keras Notebook by F. Chollet\