Update app.py

app.py

@@ -1,46 +1,24 @@
 import os
-import io
 import cv2
 import numpy as np
 import torch
-import requests
-from PIL import Image
 from ultralytics import YOLO
 import gradio as gr
-from mediapipe.tasks import python
-from mediapipe.tasks.python import vision
-from mediapipe.tasks.python.vision import Image as MPImage
 import traceback
 
 # -----------------------------
-# 1. Paths & URLs
+# 1. YOLO model path
 # -----------------------------
-HAND_MODEL_PATH = "hand_landmarker.task"
-HAND_MODEL_URL = "https://storage.googleapis.com/mediapipe-models/hand_landmarker/hand_landmarker/float16/1/hand_landmarker.task"
 YOLO_MODEL_PATH = "yolov11n_finetuned_ASL.pt"  # Push this small model to HF repo
 
 # -----------------------------
-# 2. Download MediaPipe model if missing
-# -----------------------------
-if not os.path.exists(HAND_MODEL_PATH):
-    print("📥 Downloading MediaPipe hand landmark model...")
-    r = requests.get(HAND_MODEL_URL)
-    with open(HAND_MODEL_PATH, "wb") as f:
-        f.write(r.content)
-    print("✅ Download complete.")
-
-# -----------------------------
-# 3. Load models
+# 2. Load YOLO model
 # -----------------------------
 yolo_model = YOLO(YOLO_MODEL_PATH)
 yolo_model.eval()
 
-base_options = python.BaseOptions(model_asset_path=HAND_MODEL_PATH)
-hand_options = vision.HandLandmarkerOptions(base_options=base_options, num_hands=1)
-detector = vision.HandLandmarker.create_from_options(hand_options)
-
 # -----------------------------
-# 4. Inference function
+# 3. Inference function
 # -----------------------------
 def predict_asl(image):
     try:
@@ -51,36 +29,13 @@ def predict_asl(image):
         h, w, _ = img.shape
         print(f"🔹 Uploaded image shape: {img.shape}, dtype: {img.dtype}")
 
-        # --- MediaPipe annotation ---
-        try:
-            # Convert OpenCV BGR -> RGB
-            img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
-            
-            # PIL + BytesIO to create MediaPipe image
-            pil_img = Image.fromarray(img_rgb)
-            buf = io.BytesIO()
-            pil_img.save(buf, format="PNG")
-            buf.seek(0)
-
-            mp_img = MPImage.create_from_file(buf)
-            
-            detection_result = detector.detect(mp_img)
-            if detection_result.hand_landmarks:
-                for hand_landmarks in detection_result.hand_landmarks:
-                    for landmark in hand_landmarks:
-                        x, y = int(landmark.x * w), int(landmark.y * h)
-                        cv2.circle(img, (x, y), 3, (0, 255, 0), -1)
-        except Exception as e:
-            print("❌ MediaPipe annotation error:", e)
-            traceback.print_exc()
-
         # --- YOLO prediction directly on NumPy array ---
         results = yolo_model.predict(img, imgsz=300, verbose=False)[0]
         pred_idx = results.probs.top1
         pred_label = results.names[pred_idx]
         confidence = results.probs.data[pred_idx].item()
 
-        # Overlay prediction text
+        # Overlay prediction text on original image
         cv2.putText(
             img,
             f"{pred_label} ({confidence:.2f})",
@@ -100,16 +55,16 @@ def predict_asl(image):
         return image, "Error", 0.0
 
 # -----------------------------
-# 5. Gradio Interface
+# 4. Gradio Interface
 # -----------------------------
 title = "🖐️ ASL Letter Classifier"
-description = "Upload a hand sign image and see the predicted letter and confidence.\nMediaPipe landmarks will be annotated automatically."
+description = "Upload a hand sign image and see the predicted letter and confidence."
 
 iface = gr.Interface(
     fn=predict_asl,
     inputs=gr.Image(type="numpy"),
     outputs=[
-        gr.Image(type="numpy", label="Annotated Image"),
+        gr.Image(type="numpy", label="Original Image with Prediction"),
         gr.Textbox(label="Predicted Letter"),
         gr.Textbox(label="Confidence")
     ],