robust-deep-learning
PublicA project to train your model from scratch or fine-tune a pretrained model using the losses provided in this library to improve out-of-distribution detection and uncertainty estimation performances. Calibrate your model to produce enhanced uncertainty estimations. Detect out-of-distribution data using the defined score type and threshold.
anomaly-detectionclassificationdeep-learningdeep-neural-networksmachine-learningnovelty-detectionood-detectionopen-setopen-set-recognitionout-of-distribution
Creat：2022-08-28T00:50:44
Update：2024-12-18T15:59:40
17
Stars
0
Stars Increase