Image Classification
Transformers
Safetensors
vit
image-detection
ai-image-generation
anime
ai-anime
human-detection
art
Instructions to use legekka/AI-Anime-Image-Detector-ViT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use legekka/AI-Anime-Image-Detector-ViT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="legekka/AI-Anime-Image-Detector-ViT") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("legekka/AI-Anime-Image-Detector-ViT") model = AutoModelForImageClassification.from_pretrained("legekka/AI-Anime-Image-Detector-ViT") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ This model is a proof of concept model of detecting anime styled AI images. Usin
|
|
| 18 |
## Evaluation
|
| 19 |
|
| 20 |
Each checkpoint was evaluated on 500-500 real and AI images.
|
|
|
|
|
|
|
| 21 |
- Training Loss: 0.1009
|
| 22 |
- Eval Loss: 0.1386
|
| 23 |
|
|
|
|
| 18 |
## Evaluation
|
| 19 |
|
| 20 |
Each checkpoint was evaluated on 500-500 real and AI images.
|
| 21 |
+
|
| 22 |
+
Final result:
|
| 23 |
- Training Loss: 0.1009
|
| 24 |
- Eval Loss: 0.1386
|
| 25 |
|