Delete app_old2.py

app_old2.py

@@ -1,57 +0,0 @@
-from keras.models import load_model
-from numpy.random import randint
-import numpy as np
-import cv2
-from matplotlib import pyplot as plt
-from PIL import Image
-import streamlit as st
-
-def load_and_preprocess_image(image, target_shape=(256, 256)):
-    image = np.array(image)
-    custom_image = cv2.resize(image, target_shape)
-    custom_image = cv2.cvtColor(custom_image, cv2.COLOR_RGB2BGR)
-    if custom_image.max() > 1.0:
-        custom_image = (custom_image.astype(np.float32)-127.5) / 127.50
-    custom_image = np.expand_dims(custom_image, axis=0)
-    return custom_image
-
-# Streamlit UI
-st.title("Image Processing with Keras Model")
-
-uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
-
-
-if uploaded_file is not None:
-    # Load and preprocess image
-    image = Image.open(uploaded_file).convert('RGB')
-    st.image(image, caption='Original Image', use_column_width=True)
-
-    custom_image = load_and_preprocess_image(image)
-    
-    # Define and load model
-    model = load_model('model_016950.h5')
-    
-    # Generate image
-    gen_image = model.predict(custom_image)
-    gen_image = np.squeeze(gen_image, axis=0) # remove the batch dimension
-    gen_image = ((gen_image + 1) * 127.5).astype(np.uint8)
-    gen_image = cv2.cvtColor(gen_image, cv2.COLOR_BGR2RGB)
-    gen_image_pil = Image.fromarray(gen_image)
-    st.image(gen_image_pil, caption='Generated Image', use_column_width=True)
-
-
-
-    # Plotting results
-    fig, ax = plt.subplots(1, 2, figsize=(10, 5))
-
-    ax[0].imshow(image)
-    ax[0].set_title("Original Image")
-    ax[0].axis('off')
-
-    ax[1].imshow(gen_image_pil)
-    ax[1].set_title("Generated Image")
-    ax[1].axis('off')
-
-    st.pyplot(fig)
-
-