ttach

library0.0.3pypypiunverified

Image test time augmentation for PyTorch. Wraps models to apply TTA transforms (flips, rotations, scaling) and aggregate predictions. Current version 0.0.3, last release April 2021. No recent updates; library is in maintenance mode.

ai-ml

pip install ttach

github ↗package ↗

INSTALL

IMPORT

SIG · TTACH

ttach

ai-mlpythonv0.0.3

Install

1.5s avg

Import

—

Disk

16MB

Pass rate

10/ 10

Env Coverage10 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.0.3 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

installs and imports cleanly · install 0.0s · import 0.000s · 17.9MB

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 1.5s · import 0.000s · 18MB

16MB installed

● package 16MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

Compose

✓ from ttach import Compose

✗ from ttach import Compose

Basic TTA example: wrap a model with horizontal flip, 90° rotation, and scaling. Merge predictions by mean.

import torch import ttach as tta model = torch.nn.Linear(10, 2) # dummy model model.eval() transforms = tta.Compose([ tta.HorizontalFlip(), tta.Rotate90(angles=[0, 90]), tta.Scale(scales=[1.0, 1.5]), ]) tta_model = tta.SegmentationTTAWrapper(model, transforms, merge_mode='mean') input_tensor = torch.randn(1, 10) output = tta_model(input_tensor) print(output.shape)

Debug

Known issues

deprecatedThe library has not been updated since April 2021. It may not work with newer PyTorch versions without issues.

fix

Consider alternatives like kornia's kornia.augmentation.TTA or torchvision's test-time augmentation utilities.

affects: >=0.0.3

gotchaThe 'd4' transform alias was fixed in v0.0.2 to remove duplicated augmentations. If using older version, you might get unintended duplicates.

fix

Upgrade to >=0.0.2 or manually define the D4 transform using Compose.

affects: <0.0.2

breakingKeypoints support was added in v0.0.3. If you rely on keypoints, ensure version >=0.0.3 or use a workaround.

fix

Upgrade to 0.0.3 or handle keypoints manually.

affects: <0.0.3

Upgrade

Version history

0.0.3latest on PyPI · released Jul 9, 2020

Audit

Dependencies

torchrequiredCore dependency for PyTorch tensors and models.

Agent activity

20 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/qubvel/ttach ↗

packagehttps://pypi.org/project/ttach/ ↗