Update app.py

app.py

@@ -1,17 +1,14 @@
-from fastapi import FastAPI, UploadFile, File
-import uvicorn
+import streamlit as st
 import tensorflow as tf
 from tensorflow import keras
 from keras import models
 from PIL import Image
-from io import BytesIO
 import numpy as np
 import cv2
+import io
 
 # Some constants to be used in the program
 IMG_SIZE = (32,32)
-APP_HOST = '127.0.1.1'
-APP_PORT = '5000'
 
 # Character mapping for the character prediction
 char_map = {
@@ -25,41 +22,35 @@ char_map = {
     56:'𑐬(RA)', 57: '𑐮(LA)', 58:'𑐰(WA)', 59:'𑐱(SHA)',    60: '𑐱(SHA-alt)', 61: '𑐲(SSA)',    62: '𑐳(SA)', 63: '𑐴(HA)'
 }
 
-
-
 # Importing the model
-model = models.load_model('vgg.h5')
-
-
-# Defining the FastAPI instance here
-app = FastAPI()
+model = models.load_model('tf_model.h5')
 
 # Function for reading image
-def file_to_array(data) -> np.ndarray:
-    image = np.array(Image.open(BytesIO(data)))
+def file_to_array(file) -> np.ndarray:
+    image = np.array(Image.open(io.BytesIO(file)))
 
     return image 
 
+# Main Streamlit app
+def main():
+    st.title("Character Recognition")
+    st.write("Upload an image and the model will predict the character")
 
-@app.get('/')
-async def root_func():
-    return {'message': 'this is the root function'}
-
-
-@app.post('/predict_image')
-async def upload_image(file: UploadFile = File(...)):
-    image  = Image.open(BytesIO(await file.read()))
+    uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
 
-    image  = cv2.resize(np.array(image), IMG_SIZE)
-    image  = image.astype('float32')
-    image  = np.expand_dims(image, axis=0)
+    if uploaded_file is not None:
+        image = Image.open(uploaded_file)
+        st.image(image, caption='Uploaded Image.', use_column_width=True)
 
-    output = model.predict(image)
-    result = char_map[np.argmax(output)]
-    
-    return {'prediction': result}
+        if st.button('Predict'):
+            image = cv2.resize(np.array(image), IMG_SIZE)
+            image = image.astype('float32')
+            image = np.expand_dims(image, axis=0)
 
+            output = model.predict(image)
+            result = char_map[np.argmax(output)]
+            
+            st.success(f'Prediction: {result}')
 
-    
 if __name__ == "__main__":
-    uvicorn.run(app, host=APP_HOST, port=APP_PORT)
+    main()