|
|
--- |
|
|
license: agpl-3.0 |
|
|
pipeline_tag: image-classification |
|
|
--- |
|
|
|
|
|
A small 2M param CNN classifier to predict the quality factor of lossy image codecs. Covers JPEG, JXL, AVIF and WEBP. Dataset (45k) included RAW photography and PNG illustrations. |
|
|
|
|
|
Overall accuracy was 95.3% on train, 96.6% on val (7% split). Take the predictions with a large grain of salt, its not yet ready for production. |
|
|
|
|
|
This model will *not* work properly in the following scenarios: |
|
|
|
|
|
- Really small images (sub 512px) |
|
|
- Mutiple resize and/or compression loops (would have ballooned training time for first iteration) |
|
|
- `<insert lossy format>` renamed to PNG's |
|
|
- Mixed media; low quality JPEG background with an overlaid illustration. |
|
|
|
|
|
Motivated by research suggesting image models finetuned on many <= q=75 JPEGS had negative outcomes. |
|
|
|
|
|
Credit: Rimuru original implementation |
