Downloads · 30 days
0
0% of all-time downloads
AAT-JPEG-Artefact-Detection
LoliRimuru/AAT-JPEG-Artefact-Detection
AAT-JPEG-Artefact-Detection is a image classification model from LoliRimuru. Use it when you need a label for an image. It is set up for tf-keras. The card lists the license as creativeml-openrail-m.
Autodetects JPEG artefacts in categories of C100 (no artefacts), C95, C90, C85, C80, C70, C60, C40 and C20 (really terrible artefacts). The input is a 1024x1024 large image. The image is converted to gray scale to omi…
All-time downloads
6
Public
Repo size
172 KB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.data-00000-of-00001258 KB · 49%
At a glance
- Task
- Image Classification
- Library
- tf-keras
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Jul 29, 2023
- Updated
- Dec 19, 2025
- SHA
- 3f6ec1b8
Model card
From the Hugging Face model README
AAT JPEG Artefact Detection (OUTDATED use https://huggingface.co/LoliRimuru/AAL-Plus_Image_Quality_Assessment)
Autodetects JPEG artefacts in categories of C100 (no artefacts), C95, C90, C85, C80, C70, C60, C40 and C20 (really terrible artefacts). The input is a 1024x1024 large image. The image is converted to gray scale to omit redundant informations and reduce overall training and inference time. Model is standalone.
Training stats
Around 60k of images was used during training.
<img src="https://huggingface.co/JosefJilek/AAT-JPEG-Artefact-Detection/resolve/main/v1.0-stats.png"></img>
- Task
- Image Classification
- Library
- tf-keras
- License
- creativeml-openrail-m
- Created
- Jul 29, 2023
- Updated
- Dec 19, 2025