Anime Classifier just-a-try/cls-ai-check-20m-plus.caformer_s36.r640

Model Details

• Model Type: Image Classification
• Model Stats:
  • Params: 37.3M
  • FLOPs / MACs: 123.2G / 61.4G
  • Image size: train = 640 x 640, test = 640 x 640
• Dataset: just-a-try/ai-check-20m-plus
  • Classes: ai, human

Results

Metrics

#	Acc / Top-1	Macro (F1/P/R/AUC)	Micro (F1/P/R/AUC)
Validation	99.81% / 99.81%	0.998 / 0.998 / 0.998 / 1.000	0.998 / 0.998 / 0.998 / 1.000
Test	99.80% / 99.80%	0.998 / 0.998 / 0.998 / 1.000	0.998 / 0.998 / 0.998 / 1.000

Plots

#	Confusion	P/R	F1
Validation
Test

How to Use

We provided a sample image for our code samples, you can find it here.

Use Transformers And Torch

Install dghs-imgutils, timm and other necessary requirements with the following command

pip install 'dghs-imgutils>=0.19.0' torch huggingface_hub timm pillow 'transformers>=4.57.1'

After that you can load this model with timm library, and use it for train, validation and test, with the following code

import torch
from imgutils.data import load_image
from transformers import AutoImageProcessor, AutoModel

processor = AutoImageProcessor.from_pretrained('just-a-try/cls-ai-check-20m-plus.caformer_s36.r640', trust_remote_code=True)
model = AutoModel.from_pretrained('just-a-try/cls-ai-check-20m-plus.caformer_s36.r640', trust_remote_code=True, use_infer_head=True)
model.eval()

image = load_image('https://huggingface.co/just-a-try/cls-ai-check-20m-plus.caformer_s36.r640/resolve/main/sample.webp', mode='RGB', force_background='white')
input_ = processor(image)['pixel_values']
# input_, shape: torch.Size([1, 3, 640, 640]), dtype: torch.float32
classes = model.config.classes
# ['ai', 'human']

with torch.no_grad():
    output = model(input_)
# output, shape: torch.Size([1, 2]), dtype: torch.float32

print(dict(zip(classes, output[0].tolist())))
# {'ai': 0.9979068040847778, 'human': 0.002093271818011999}

Citation

@misc{cls_ai_check_20m_plus_caformer_s36_r640,
  title        = {Anime Classifier just-a-try/cls-ai-check-20m-plus.caformer_s36.r640},
  author       = {narugo1992 and Deep Generative anime Hobbyist Syndicate (DeepGHS)},
  year         = {2025},
  howpublished = {\url{https://huggingface.co/just-a-try/cls-ai-check-20m-plus.caformer_s36.r640}},
  note         = {A anime-style image classification model for classification task with 2 classes (ai, human), trained on anime dataset ai-check-20m-plus (\url{https://huggingface.co/datasets/just-a-try/ai-check-20m-plus}). Model parameters: 37.3M, FLOPs: 123.2G, input resolution: 640×640.},
  license      = {mit}
}