uda and UDA_pytorch

The PyTorch implementation is a community reimplementation of the original TensorFlow-based research codebase, making them competitors offering the same UDA algorithm in different deep learning frameworks rather than complementary tools.

uda
48
Emerging
UDA_pytorch
48
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 22/25
Stars: 2,202
Forks: 312
Downloads: —
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 278
Forks: 59
Downloads: —
Commits (30d): 0
Language: Python
License: Apache-2.0
Stale 6m No Package No Dependents
Stale 6m No Package No Dependents

About uda

google-research/uda

Unsupervised Data Augmentation (UDA)

Combines consistency regularization with task-specific augmentation strategies—back-translation for text and RandAugment for images—to enforce prediction invariance on unlabeled data. Implements dual loss objectives weighting labeled and unlabeled examples, with confidence-based masking to filter low-confidence predictions. Supports both TensorFlow on GPUs and Google Cloud TPU, with pre-built implementations for BERT text classification and vision tasks (CIFAR-10, SVHN, ImageNet).

About UDA_pytorch

SanghunYun/UDA_pytorch

UDA(Unsupervised Data Augmentation) implemented by pytorch

Scores updated daily from GitHub, PyPI, and npm data. How scores work