Update app.py

app.py

@@ -1,59 +1,41 @@
 import streamlit as st
 from PIL import Image
-import requests
-import io
-import base64
-import os
+from ultralytics import YOLO
+import numpy as np
+import cv2
 
-# --- CONFIGURATION ---
-# Get Groq API key from environment variables (set in Hugging Face Secrets)
-GROQ_API_KEY = os.getenv("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")
-GROQ_API_URL = "https://api.groq.com/v1/inference/yolov8"
+# --- Load YOLOv8 Model ---
+model = YOLO('yolov8n.pt')  # Nano model, fast and small
 
 # --- Streamlit UI ---
-st.title("📸 Object Counter App")
-st.write("Upload an image and count the objects using YOLOv8 + Groq API!")
+st.title("📸 Object Counter App (YOLOv8)")
 
 uploaded_file = st.file_uploader("Upload an Image", type=['jpg', 'jpeg', 'png'])
 
 if uploaded_file is not None:
-    image = Image.open(uploaded_file)
+    image = Image.open(uploaded_file).convert('RGB')
     st.image(image, caption="Uploaded Image", use_column_width=True)
 
-    # Convert image to base64 for API
-    buffered = io.BytesIO()
-    image.save(buffered, format="JPEG")
-    img_str = base64.b64encode(buffered.getvalue()).decode()
-
     st.write("🔎 Detecting objects...")
 
-    # --- Groq API Request ---
-    headers = {
-        "Authorization": f"Bearer {GROQ_API_KEY}",
-        "Content-Type": "application/json"
-    }
+    # Convert PIL image to NumPy array
+    img_array = np.array(image)
 
-    payload = {
-        "model": "yolov8n",  # YOLOv8 Nano version (fast & small)
-        "inputs": {
-            "image": img_str
-        }
-    }
+    # Inference
+    results = model.predict(img_array)
 
-    response = requests.post(GROQ_API_URL, json=payload, headers=headers)
+    # Get number of detected objects
+    num_objects = len(results[0].boxes)
 
-    if response.status_code == 200:
-        result = response.json()
-        detected_objects = result.get("detections", [])
-        count = len(detected_objects)
+    st.success(f"✅ Total objects detected: {num_objects}")
 
-        st.success(f"✅ Total objects detected: {count}")
+    # List detected object classes
+    class_names = [model.names[int(cls)] for cls in results[0].boxes.cls]
+    st.write(f"Detected Items: {class_names}")
 
-        # Show each detected object's class
-        object_names = [obj['class'] for obj in detected_objects]
-        st.write(f"Detected items: {object_names}")
+    # Draw boxes on image
+    result_img = results[0].plot()
 
-    else:
-        st.error(f"Error: {response.status_code} - {response.text}")
+    st.image(result_img, caption='Detected Objects', use_column_width=True)
 
-st.write("Made with ❤️ using YOLOv8 + Groq + Streamlit")
+st.write("Made with ❤️ using YOLOv8 + Streamlit")