Anime Rating
Image rating (safe, r15, r18) prediction model.
Source du modèle
- Type
- Other
- Taille du fichier
- 16,0–382 MB
- Version
- vRevision be15808
- Mis à jour
- 28 sept. 2026
- Téléchargements
- 0
- Source
- Hugging Face
Description de la source
Image rating (safe, r15, r18) prediction model.
Please note that due to the often unclear boundaries between safe, r15 and r18 levels, there is no objective ground truth for this task, and the data is scraped without any manual filtering. Therefore, the models trained on this dataset can only provide rough judgments. If you require an accurate solution for classifying R18 images, it is recommended to consider a solution based on keypoint object detection.
| Model | FLOPs | Accuracy | Confusion Matrix | Description |
|---|---|---|---|---|
| caformer_s36_plus | 22.10G | 74.26% | Confusion Matrix | Model: caformer_s36.sail_in22k_ft_in1k_384 pratrained from timm |
| mobilenetv3 | 0.63G | 64.77% | Confusion Matrix | Model: mobilenetv3_large_100 from timm |
| mobilenetv3_sce | 0.63G | 66.27% | Confusion Matrix | Model: mobilenetv3_large_100 from timm, use SCELoss as loss function |
| mobilenetv3_sce_dist | 0.63G | 69.49% | Confusion Matrix | Distillated from caformer_s36_plus, using mobilenetv3_large_100 |
Sources
1 source
Sources
1 sourceVérifié 28 sept.
Artefacts du modèle
14 artefacts
Artefacts du modèle
14 artefactscaformer_b36_v1_pruned_ls0.1/model.ckpt
ckpt · 382 MB · SHA-256 3232531fdf85…f4d5 · Hugging Face
Téléchargercaformer_b36_v1_pruned_ls0.1/model.onnx
onnx · 366 MB · SHA-256 b3dd4b62e477…cc7d · Hugging Face
Téléchargercaformer_s36_v1_pruned_ls0.1/model.ckpt
ckpt · 159 MB · SHA-256 5a665cca6a39…77f1 · Hugging Face
Téléchargercaformer_s36_v1_pruned_ls0.1/model.onnx
onnx · 143 MB · SHA-256 020d981e27ab…7f60 · Hugging Face
Téléchargermobilenetv3_v1_pruned_ls0.1/model.ckpt
ckpt · 32,8 MB · SHA-256 ecab5f4b176b…41e4 · Hugging Face
Téléchargermobilenetv3_v1_pruned_ls0.1/model.onnx
onnx · 16,0 MB · SHA-256 76e5c4470442…544d · Hugging Face
TéléchargerExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: mit datasets: - deepghs/anime_rating metrics: - accuracy pipeline_tag: image-classification tags: - art --- Image rating (`safe`, `r15`, `r18`) prediction model. Please note that due to the often unclear boundaries between `safe`, `r15` and `r18` levels, there is no objective ground truth for this task, and the data is scraped without any manual filtering. Therefore, the models trained on this dataset can only provide rough judgments. If you require an accurate solution for classifying `R18` images, it is recommended to consider a solution based on keypoint object detection. | Model | FLOPs | Accuracy | Confusion Matrix | Description | |:--------------------:|:------:|:--------:|:-----------------------------------------------------------------------------------------------------------------:|----------------------------------------------------------------------| | caformer_s36_plus | 22.10G | 74.26% | [Confusion Matrix](https://huggingface.co/deepghs/anime_rating/blob/main/caformer_s36_plus/plot_confusion.png) | Model: caformer_s36.sail_in22k_ft_in1k_384 pratrained from timm | | mobilenetv3 | 0.63G | 64.77% | [Confusion Matrix](https://huggingface.co/deepghs/anime_rating/blob/main/mobilenetv3/plot_confusion.png) | Model: mobilenetv3_large_100 from timm | | mobilenetv3_sce | 0.63G | 66.27% | [Confusion Matrix](https://huggingface.co/deepghs/anime_rating/blob/main/mobilenetv3_sce/plot_confusion.png) | Model: mobilenetv3_large_100 from timm, use SCELoss as loss function | | mobilenetv3_sce_dist | 0.63G | 69.49% | [Confusion Matrix](https://huggingface.co/deepghs/anime_rating/blob/main/mobilenetv3_sce_dist/plot_confusion.png) | Distillated from caformer_s36_plus, using mobilenetv3_large_100 |
Source context: 0 downloads · 0 likes · Pipeline image-classification · Repo Library-Mutsumi/anime_rating
