Update README.md

README.md

@@ -9,7 +9,8 @@ tags:
 
 
 An embedding model to classify images into FLUX generated images and non-flux photographs.
-The embeddings are 128 dimensional and can be used in another classifier to classify.
+The embeddings are 128 dimensional and can be used in another classifier to classify. Current classifiers can classify up to 83% accuracy.
+XGBoost has an F1 = 0.83 and KNN F1 = 0.87
 
 The model can load Fourier transformed images of size 512x512 which are then fed into the model and a 128 length output vector is produced.
 The steps to create the embeddings can be described as:
@@ -18,10 +19,10 @@ The steps to create the embeddings can be described as:
 3. Input the images into the model using predict.
 4. The output will be a 128-length vector for use in classification models.
 
-The preprocessing code along with the predict can calculate the embeddings for classification.
+The preprocessing code along with predict can calculate the embeddings for classification.
 
 ```python
-# load an image and apply the fourier transform
+# load an image and apply the Fourier transform
 
 import numpy as np
 from PIL import Image