{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/9"}],"enrichment":{"capability":"Wraps PyTorch models to apply test-time augmentation\u2014running augmented versions of input images through a model and merging predictions to improve robustness.","skillfed_tags":["test-time-augmentation","model-inference","computer-vision"],"use_cases":["Improve segmentation model accuracy on medical images by averaging predictions across rotations and flips.","Boost classification confidence on edge cases by merging predictions from multiple scaled and cropped versions of the input.","Refine keypoint detection by applying TTA with geometric transformations and reversing them before merging.","Ensemble inference without training multiple models\u2014apply TTA to a single model for a quick accuracy boost.","Benchmark model robustness by testing how predictions vary across different augmentations."],"what_it_does":"TTAch is a PyTorch wrapper library that implements test-time augmentation (TTA)\u2014a technique where multiple augmented versions of an input image are passed through a trained model, and the resulting predictions are merged (averaged, max-pooled, etc.) to produce a final output. Instead of showing a model one clean image, TTA shows it many transformed versions and combines their predictions, often improving accuracy and robustness at the cost of inference time.\n\nThe library provides pre-built wrappers for segmentation, classification, and keypoint detection models, along with a composable transform system (flips, rotations, scaling, crops, etc.) and multiple merge strategies (mean, geometric mean, max, min, temperature sharpening). You can wrap an existing model in one line and immediately use TTA, or build custom augmentation pipelines for specialized workflows.","worth_installing":"No\u2014the package is abandoned (last release 2020-07-09, last commit 2023-07-28) with no maintenance or compatibility updates. While it has low install friction and permissive licensing, the lack of active maintenance poses a significant risk for compatibility with current PyTorch and Python versions. For active TTA support, consider maintained alternatives or implementing TTA directly in your training framework."},"id":"ttach","links":{"html":"https://skillfed.io/packages/ttach","md":"https://skillfed.io/packages/ttach.md","pypi":"https://pypi.org/project/ttach/"},"maintenance":{"status":"abandoned"},"meta":{"latest_release":"2020-07-09","license_spdx":null,"license_treatment":"permissive","name":"ttach","python_support":"supports_current","summary":"Images test time augmentation with PyTorch."},"popularity":{"monthly_downloads":140340,"position":11274,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.0.3"}