Update README.md

README.md

@@ -64,11 +64,12 @@ image = Image.open("image_path.jpg").convert("RGB")
 
 # Preprocess and predict
 def IQA_preprocess():
+    random.seed(3407)
     transform = transforms.Compose([
-        transforms.Resize(224),
-        transforms.CenterCrop(size=(224, 224)),  
-        transforms.ToTensor(),
-        transforms.Normalize(mean=(0.48145466, 0.4578275, 0.40821073), 
+      transforms.Resize((512,384)),
+      transforms.RandomCrop(size=(224,224)),  
+      transforms.ToTensor(),
+      transforms.Normalize(mean=(0.48145466, 0.4578275, 0.40821073), 
                              std=(0.26862954, 0.26130258, 0.27577711))
     ])
     return transform
@@ -78,4 +79,13 @@ image = IQA_preprocess()(image).unsqueeze(0).to(device)
 with torch.no_grad():
     iqa_score = model(image).item()
 
+# maps the predicted score from the model's range [min_pred, max_pred] 
+# to the actual range [min_score, max_score] using min-max scaling.
+
+min_pred =
+max_pred =
+max_score =
+min_score =
+
+normalized_score = ((iqa_score - min_pred) / (max_pred - min_pred)) * (max_score - min_score) + min_score
 print(f"Predicted quality Score: {iqa_score:.4f}")