4 open source projects by cgnorthcutt

The standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.

✭ 2,526

python shell machine-learning machine-learning-algorithms unsupervised-learning semi-supervised-learning data-cleaning weak-supervision clean-data learning-with-confident-examples noisy-data data-centric confident-learning latent-estimation robust-machine-learning learning-with-noisy-labels

2. Hypopt

⏸ Parallelized hyper-param optimization with validation set, not crossval

✭ 68

python

3. Benchmarking Keras Pytorch

🔥 Reproducibly benchmarking Keras and PyTorch models

✭ 346

python deep-learning pytorch keras cnn imagenet benchmarking pytorch-tutorial cnn-keras keras-tutorials

4. rankpruning

🧹 Formerly for binary classification with noisy labels. Replaced by cleanlab.

✭ 81

Jupyter Notebook python training machine-learning machine-learning-algorithms ranking semi-supervised-learning binary-classification denoising learning-with-errors rank-pruning-algorithm noise-rates noisy-learning mislabeling learning-with-confident-examples

1-4 of 4 user projects