Update app.py

app.py

@@ -1,12 +1,11 @@
 import streamlit as st
 import numpy as np
-import cv2
 from tensorflow.keras.models import load_model
 from PIL import Image
 import requests
 
 # Load the model from Hugging Face
-@st.cache(allow_output_mutation=True)
+@st.cache_resource
 def load_model_from_hf():
     url = "https://huggingface.co/krishnamishra8848/Devanagari_Character_Recognition/resolve/main/saved_model.keras"
     response = requests.get(url)
@@ -17,7 +16,7 @@ def load_model_from_hf():
 
 model = load_model_from_hf()
 
-# Label mapping
+# Nepali characters mapping
 label_mapping = [
     "क", "ख", "ग", "घ", "ङ", "च", "छ", "ज", "झ", "ञ",
     "ट", "ठ", "ड", "ढ", "ण", "त", "थ", "द", "ध", "न",
@@ -35,15 +34,11 @@ uploaded_file = st.file_uploader("Choose a file", type=["jpg", "png", "jpeg"])
 
 if uploaded_file is not None:
     # Load and preprocess the image
-    img = Image.open(uploaded_file)
-    img = img.convert("L")  # Convert to grayscale
+    img = Image.open(uploaded_file).convert("L")  # Convert to grayscale
     img_resized = img.resize((32, 32))  # Resize to 32x32
     img_array = np.array(img_resized).astype("float32") / 255.0  # Normalize
     img_input = img_array.reshape(1, 32, 32, 1)  # Reshape for the model
 
-    # Display uploaded image
-    st.image(img, caption="Uploaded Image", use_column_width=True)
-
     # Make prediction
     prediction = model.predict(img_input)
     predicted_class_index = np.argmax(prediction)