Added score and docs

README.md

@@ -50,6 +50,16 @@ image2 = cv2.imread("test/kobe2.jpg")
 image_comparer.is_similar(image, image2, threshold=0.5)
 ```
 
+## API
+
+### Methods
+
+`is_similar(image1: Union[Image.Image, np.ndarray], image2: Union[Image.Image, np.ndarray], threshold=0.5)`: Checks if the two images are similar based on the reshold passed
+
+
+`calculate_score(image1: Union[Image.Image, np.ndarray], image2: Union[Image.Image, np.ndarray])`: Calculates the score between the two images. The higher the score, the more closely the two images are related.
+
+
 ## Development
 
 ### Installation

image_comparer/__init__.py

@@ -1,3 +1,3 @@
 from .compare import is_similar
 
-__version__ = "1.0.1"
+__version__ = "1.1.0"

image_comparer/compare.py

@@ -31,12 +31,17 @@
 def _pil_image_(image: ImageType) -> Image:
     return Image.fromarray(np.array(image)).resize(DEFAULT_IMAGE_SIZE)
 
-def is_similar(image1: ImageType, image2: ImageType, threshold=0.5):
+
+def is_similar(image1: ImageType, image2: ImageType, threshold=0.5) -> bool:
+    return calculate_score(image1, image2) > threshold
+
+
+def calculate_score(image1: ImageType, image2: ImageType) -> float:
     pil_image1 = _pil_image_(image1)
     pil_image2 = _pil_image_(image2)
 
     image_tensor1 = transformer(pil_image1).unsqueeze(0)
     image_tensor2 = transformer(pil_image2).unsqueeze(0)
 
     results = model(image_tensor1, image_tensor2)
-    return results.detach().cpu().numpy()[0][0] > threshold
+    return results.detach().cpu().numpy()[0][0]