Update app.py

app.py

@@ -8,7 +8,7 @@ from PIL import Image
 import numpy as np
 import config.configure as config
 from src.pipelines.predict import predict_mask
-
+import os
 model = UNet(3, 1, [64, 128, 256, 512])
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
@@ -22,10 +22,29 @@ transform =  A.Compose([
     ])
 # Streamlit app
 def main():
+    page_bg_img = '''
+    <style>
+        .stApp {
+    background-image: url("https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcQ5xTkOsu0UGhx3csUXvFKBPn0LdyvWjALhiw&usqp=CAU");
+    background-size: cover;
+    }
+    .stSelectbox {
+                background-color:white; /* Replace with the desired background color */
+                color:white; /* Replace with the desired text color */
+            }
+    .stsubheader {
+                background-color:white;
+                color:white;
+    }
+    </style>
+    '''
+        
+    st.markdown(page_bg_img, unsafe_allow_html=True)
+
     st.title("MRI segmenation App")
 
     # Upload image through Streamlit
-    uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+    uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png", "tiff"])
 
     if uploaded_image is not None:
         # Display the uploaded and processed images side by side
@@ -40,7 +59,7 @@ def main():
 
         # Display the processed image in the second column
         col2.header("Processed Image")
-        col2.image(processed_image, caption="Segmented Image", use_column_width=True)
+        col2.image(processed_image, caption="Processed Image", use_column_width=True)
 
 # Function to generate an image using the PyTorch model
 def generate_image(uploaded_image):