Update README.md
Browse files
README.md
CHANGED
|
@@ -15,13 +15,10 @@ Images are first divided into patches and classified as rich texture or poor tex
|
|
| 15 |
The four datasets I trained on:
|
| 16 |
|
| 17 |
|
| 18 |
-
AI Recognition Dataset: https://www.kaggle.com/datasets/superpotato9/dalle-recognition-dataset
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
Dalle-3 Images: https://huggingface.co/datasets/ehristoforu/dalle-3-images
|
| 23 |
-
|
| 24 |
-
130k Images--Universal Image Embeddings: https://www.kaggle.com/datasets/rhtsingh/130k-images-512x512-universal-image-embeddings
|
| 25 |
|
| 26 |
|
| 27 |
I sampled approximated 50,000 real and 50,000 AI generated images. I was able to achieve 97.5% validation accuracy
|
|
|
|
| 15 |
The four datasets I trained on:
|
| 16 |
|
| 17 |
|
| 18 |
+
- AI Recognition Dataset: https://www.kaggle.com/datasets/superpotato9/dalle-recognition-dataset
|
| 19 |
+
- AI ArtBench: https://www.kaggle.com/datasets/ravidussilva/real-ai-art
|
| 20 |
+
- Dalle-3 Images: https://huggingface.co/datasets/ehristoforu/dalle-3-images
|
| 21 |
+
- 130k Images--Universal Image Embeddings: https://www.kaggle.com/datasets/rhtsingh/130k-images-512x512-universal-image-embeddings
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
|
| 24 |
I sampled approximated 50,000 real and 50,000 AI generated images. I was able to achieve 97.5% validation accuracy
|