Update app.py

app.py

@@ -1,6 +1,7 @@
 import os
 import pickle
 import numpy as np
+import tensorflow as tf
 import streamlit as st
 from PIL import Image
 from tensorflow.keras.preprocessing import image
@@ -8,8 +9,8 @@ from tensorflow.keras.layers import GlobalMaxPooling2D
 from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
 from sklearn.neighbors import NearestNeighbors
 from numpy.linalg import norm
-from chatbot import Chatbot  # Assuming you have a chatbot module
-import tensorflow as tf  # Make sure this import is included
+from chatbot import Chatbot
+from datasets import load_dataset
 
 # Define function for feature extraction
 def feature_extraction(img_path, model):
@@ -44,12 +45,33 @@ def save_uploaded_file(uploaded_file):
         st.error(f"Error saving file: {e}")
         return None
 
-# Function to show dashboard content
+# Function to show similar images
+def display_similar_images(indices, filenames, images):
+    col1, col2, col3, col4, col5 = st.columns(5)
+    columns = [col1, col2, col3, col4, col5]
+
+    for col, idx in zip(columns, indices[0]):
+        try:
+            img = images[idx]
+            with col:
+                st.image(img)
+        except Exception as e:
+            st.error(f"Error displaying image {idx}: {e}")
+
+# Load the dataset
+def load_image_data():
+    dataset = load_dataset("ashraq/fashion-product-images-small", split="train")
+    images = dataset["image"]
+    product_frame = dataset.remove_columns("image").to_pandas()
+    product_data = product_frame.reset_index(drop=True).to_dict(orient='index')
+    return images, product_data
+
+# Show dashboard content
 def show_dashboard():
     st.header("Fashion Recommender System")
-    chatbot = Chatbot()
-    
-    # Load ResNet model for image feature extraction
+
+    # Load the dataset and models
+    images, product_data = load_image_data()
     model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
     model.trainable = False
     model = tf.keras.Sequential([
@@ -64,59 +86,37 @@ def show_dashboard():
         st.error(f"Error loading pickle files: {e}")
         return
 
-    # Print the filenames to verify
-    st.write("List of filenames loaded:")
-    st.write(filenames)
-
     # File upload section
     uploaded_file = st.file_uploader("Choose an image")
     if uploaded_file is not None:
         file_path = save_uploaded_file(uploaded_file)
         if file_path:
-            # Display the uploaded image
             try:
                 display_image = Image.open(file_path)
                 st.image(display_image)
             except Exception as e:
                 st.error(f"Error displaying uploaded image: {e}")
 
-            # Feature extraction
             try:
                 features = feature_extraction(file_path, model)
             except Exception as e:
                 st.error(f"Error extracting features: {e}")
                 return
 
-            # Recommendation
             try:
                 indices = recommend(features, feature_list)
+                display_similar_images(indices, filenames, images)
             except Exception as e:
                 st.error(f"Error in recommendation: {e}")
                 return
 
-            # Display recommended products
-            col1, col2, col3, col4, col5 = st.columns(5)
-            columns = [col1, col2, col3, col4, col5]
-
-            for col, idx in zip(columns, indices[0]):
-                # Directly access images from the dataset instead of file paths
-                image_data = chatbot.images[idx]
-                if image_data is not None:
-                    try:
-                        with col:
-                            st.image(image_data)
-                    except Exception as e:
-                        st.error(f"Error opening image index {idx}: {e}")
-        else:
-            st.error("Some error occurred in file upload")
-
     # Chatbot section
     user_question = st.text_input("Ask a question:")
     if user_question:
+        chatbot = Chatbot()
         bot_response, recommended_products = chatbot.generate_response(user_question)
         st.write("Chatbot:", bot_response)
 
-        # Display recommended products
         for result in recommended_products:
             pid = result['corpus_id']
             product_info = chatbot.product_data[pid]
@@ -128,14 +128,10 @@ def show_dashboard():
             st.write("Gender:", product_info['gender'])
             st.image(chatbot.images[pid])
 
-# Main Streamlit app
-def main():
-    # Give title to the app
-    st.title("Fashion Recommender System")
-
-    # Show dashboard content directly
-    show_dashboard()
-
-# Run the main app
 if __name__ == "__main__":
-    main()
+    st.set_page_config(
+        page_title="Fashion Recommender System",
+        page_icon="🗣️",
+        menu_items={'About': "# Made by Prathamesh Khade"}
+    )
+    show_dashboard()