Update app.py

app.py

@@ -15,7 +15,7 @@ from langchain.tools import StructuredTool
 IMG_HEIGHT = 256
 IMG_WIDTH = 256
 
-# === Download model if not exists ===
+
 model_path = "unet_model.h5"
 if not os.path.exists(model_path):
     hf_url = "https://huggingface.co/rishirajbal/UNET_plus_plus_Brain_segmentation/resolve/main/unet_model.h5"
@@ -30,7 +30,7 @@ print("Loading model...")
 model = tf.keras.models.load_model(model_path, compile=False)
 
 
-# === Segmentation + Stats + Overlay ===
+
 def classify_image_and_stats(image_input):
     img = tf.image.resize(image_input, [IMG_HEIGHT, IMG_WIDTH])
     img_norm = img / 255.0
@@ -46,7 +46,7 @@ def classify_image_and_stats(image_input):
     total_area = IMG_HEIGHT * IMG_WIDTH
     tumor_ratio = tumor_area / total_area
 
-    tumor_label = "Tumor Detected" if tumor_ratio > 0.005 else "No Tumor Detected"
+    tumor_label = "Tumor Detected" if tumor_ratio > 0.00385 else "No Tumor Detected"
 
     overlay = np.array(img)
     red_mask = np.zeros_like(overlay)
@@ -64,7 +64,7 @@ def classify_image_and_stats(image_input):
     return overlay_img, stats
 
 
-# === Gradio handler with typing effect ===
+
 def rishigpt_handler(image_input, groq_api_key):
     os.environ["GROQ_API_KEY"] = groq_api_key
 
@@ -110,14 +110,14 @@ def rishigpt_handler(image_input, groq_api_key):
     chain = prompt | llm
     final_text = chain.invoke({"result": classification}).content.strip()
 
-    # === Yield mask and typing chunks ===
+
     displayed_text = ""
     for char in final_text:
         displayed_text += char
         time.sleep(0.015)
         yield overlay_img, displayed_text
 
-# === Gradio UI ===
+
 inputs = [
     gr.Image(type="numpy", label="Upload Brain MRI Slice"),
     gr.Textbox(type="password", label="Groq API Key")