refining the results screen

app.py

@@ -3,6 +3,7 @@ import numpy as np
 import tensorflow as tf
 from PIL import Image
 import efficientnet.tfkeras as efn 
+import random # <-- Added import for the random adjustment
 
 # ==========================================
 # 1. MRI Model Setup (Your Existing Model)
@@ -25,7 +26,19 @@ def predict_mri(image):
     
     # Predict
     predictions = mri_model.predict(img_array)[0]
-    confidences = {mri_class_names[i]: float(predictions[i]) for i in range(len(mri_class_names))}
+    
+    # Apply the 3% to 7% random reduction
+    confidences = {}
+    for i in range(len(mri_class_names)):
+        original_conf = float(predictions[i])
+        random_drop = random.uniform(0.03, 0.07) # Random value between 3% and 7%
+        
+        # Ensure it doesn't drop below 0
+        adjusted_conf = max(0.0, original_conf - random_drop)
+        
+        # Rounding to 4 decimal places gives 2 decimal digits as a percentage (e.g., 0.9345 -> 93.45%)
+        confidences[mri_class_names[i]] = round(adjusted_conf, 4)
+        
     return confidences
 
 # ==========================================
@@ -40,8 +53,6 @@ xray_class_names = [
 ]
 
 def build_xray_model():
-    # Use the 'efn' library instead of tf.keras.applications
-    # This guarantees the architecture has exactly 437 weights as expected.
     base_model = efn.EfficientNetB1(
         input_shape=(128, 128, 3), 
         weights=None, 
@@ -55,7 +66,6 @@ def build_xray_model():
         tf.keras.layers.Dense(len(xray_class_names), activation='sigmoid')
     ])
     
-    # Load weights should now perfectly match 437 to 437
     model.load_weights("xray.h5")
     return model
 
@@ -73,14 +83,23 @@ def predict_xray(image):
     img_array = np.array(img)
     img_array = np.expand_dims(img_array, axis=0)
     
-    # Use the library's built-in preprocessing to match training conditions
     img_array = efn.preprocess_input(img_array)
     
     # Predict
     predictions = xray_model.predict(img_array)[0]
     
-    # Map probabilities
-    confidences = {xray_class_names[i]: float(predictions[i]) for i in range(len(xray_class_names))}
+    # Apply the 3% to 7% random reduction
+    confidences = {}
+    for i in range(len(xray_class_names)):
+        original_conf = float(predictions[i])
+        random_drop = random.uniform(0.03, 0.07) # Random value between 3% and 7%
+        
+        # Ensure it doesn't drop below 0
+        adjusted_conf = max(0.0, original_conf - random_drop)
+        
+        # Rounding to 4 decimal places gives 2 decimal digits as a percentage
+        confidences[xray_class_names[i]] = round(adjusted_conf, 4)
+        
     return confidences
 
 # ==========================================
@@ -109,7 +128,6 @@ with gr.Blocks(title="Medical Scan Classification") as interface:
                     xray_input = gr.Image(label="Upload Chest X-Ray")
                     xray_button = gr.Button("Classify X-Ray", variant="primary")
                 with gr.Column():
-                    # CHANGE APPLIED HERE: num_top_classes changed to 2, and label updated
                     xray_output = gr.Label(num_top_classes=2, label="Top 2 Predicted Conditions")
                     
             xray_button.click(fn=predict_xray, inputs=xray_input, outputs=xray_output)