Instructions to use jacoballessio/ai-image-detect with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jacoballessio/ai-image-detect with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="jacoballessio/ai-image-detect") 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("jacoballessio/ai-image-detect") model = AutoModelForImageClassification.from_pretrained("jacoballessio/ai-image-detect") - Notebooks
- Google Colab
- Kaggle
Model Accuracy
#1
by Aviselvakumar1 - opened
Hello, I would like to know what dataset was used to arrive at the 98% accuracy figure. Was it CIFAKE or another dataset? I got the following metrics using the CIFAKE Test set.
Accuracy: 0.6239
F1 Score: 0.7262
Recall: 0.9977