for ex: I have four classes class 1: 200 samples class 2: 100 samples class 3: 20 samples class 4: 10 samples so during predictions, most of my samples are predicting class 1 or 2 because samples are high even I have unlabeled samples of class3 and class4. How can I overcome this in HF? is it…

How to give equal importance of all labels while dealing with unbalanced samples

marshmellow77 January 28, 2022, 6:37am 5

Topic		Replies	Views
How can I use class_weights when training? 🤗Transformers	19	29797	December 29, 2022
The Best Approach for Weighted Multilabel Classification 🤗Transformers	1	50	January 24, 2025
How to dealing with Data Imbalance 🤗Datasets	2	6273	July 28, 2020
Multi label classification with large number of labels and sparse data 🤗Transformers	1	1475	July 15, 2023
Matching alphabetic labels with indices in a fine-tuned model Beginners	1	180	October 4, 2023