Piq

Latest version: v0.8.0

Safety actively analyzes 683322 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 3 of 3

0.2.0

New features

- Visual Information Fidelity (VIF) and corresponding loss are implemented (47)
- Inception Score (IS) is implemented (42)
- TVLoss is changed. Now it is based on only predicted image, as it's [used as a regularizer](https://arxiv.org/abs/1603.08155) applied to the predicted images during NN training (#58)

Enchancements

- Purely PyTorch-based computation of KID score (27)
- Assertion of minimal image resolution for MS-SSIM (38)
- Scipy-free computation of FID score (32)
- Fast InceptionNet initialization (45)

Other

- More strict formatting rules via workflow with flake8 checks
- CI pipeline corrections: now workflows are triggered for PRs and merges into master
- PR templates
- API description and examples
- Small fixes and refactoring

**Contributors**: denproc, zakajd, snk4tr, smikhai1

0.1.1

data_range` argument was moved to the class initializer.

0.1.0

This release includes new measures:
- FID
- KID
- MSID
- TV

It also includes more extensive testing and documentation.

0.0.2

0.0.1

Pretrained


Pretrained

Page 3 of 3

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.