Spaces:
Runtime error
Runtime error
Merge remote-tracking branch 'origin/main' into main
Browse files
README.md
CHANGED
@@ -1 +1,21 @@
|
|
1 |
# GAN-image-detection
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# GAN-image-detection
|
2 |
+
|
3 |
+
## Prerequisite
|
4 |
+
1. Create the conda environment
|
5 |
+
```bash
|
6 |
+
conda env create -f environment.yml
|
7 |
+
```
|
8 |
+
2. Download the model's weights from [here](https://www.dropbox.com/s/g1z2u8wl6srjh6v/weigths.zip?dl=0) and unzip it under the main folder
|
9 |
+
```bash
|
10 |
+
wget https://www.dropbox.com/s/g1z2u8wl6srjh6v/weigths.zip?dl=0
|
11 |
+
unzip weigths.zip
|
12 |
+
```
|
13 |
+
|
14 |
+
## Test the detector on a single image
|
15 |
+
We provide a simple script to obtain the model score for a single image.
|
16 |
+
```bash
|
17 |
+
python gan_vs_real_detector.py --img_path $PATH_TO_TEST_IMAGE
|
18 |
+
```
|
19 |
+
|
20 |
+
## Performances
|
21 |
+
We provide a [notebook](https://github.com/polimi-ispl/GAN-image-detection/blob/main/roc_curves.ipynb) with the script for computing the ROC curve for each dataset.
|