Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,10 @@ The four datasets I trained on:
|
|
| 21 |
|
| 22 |
I sampled approximated 50,000 real and 50,000 AI generated images. I was able to achieve 97.5% validation accuracy
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
# Thanks
|
| 25 |
The model design is inspired by https://arxiv.org/abs/2311.12397 and https://arxiv.org/abs/2003.01826.
|
| 26 |
Used code from https://github.com/hridayK/Detection-of-AI-generated-images and https://github.com/cc-hpc-itwm/UpConv
|
|
|
|
| 21 |
|
| 22 |
I sampled approximated 50,000 real and 50,000 AI generated images. I was able to achieve 97.5% validation accuracy
|
| 23 |
|
| 24 |
+
# Training Suggestion
|
| 25 |
+
First run preprocess.py and save the preprocessed data as .h5 files in disk. Then run train.py for model training.
|
| 26 |
+
Preprocessing takes a long time (probably longer than training). It's not a good idea to preprocess while you train, because preprocessing will max out the CPU and leave the GPU idle.
|
| 27 |
+
|
| 28 |
# Thanks
|
| 29 |
The model design is inspired by https://arxiv.org/abs/2311.12397 and https://arxiv.org/abs/2003.01826.
|
| 30 |
Used code from https://github.com/hridayK/Detection-of-AI-generated-images and https://github.com/cc-hpc-itwm/UpConv
|