Update app.py

app.py

@@ -1,56 +1,42 @@
 #############################################################################################################################
 # Filename   : app.py
 # Description: A Streamlit application to detect facial expressions from images and provide responses.
-# Author     : [Your Name]
+# Author     : Lucas Yao
 #
-# Copyright © 2024 by [Your Name]
+# Copyright © 2024 by Lucas Yao
 #############################################################################################################################
 
 # Import libraries.
 import os  # Load environment variable(s).
-import requests  # Send HTTP GET request to Hugging Face models for inference.
 import streamlit as st  # Build the GUI of the application.
 from PIL import Image  # Handle image operations.
 from dotenv import load_dotenv  # Load environment variables.
-import torch  # For tensor operations.
-from transformers import AutoProcessor, AutoModelForImageClassification  # Hugging Face models.
+from fer import FER  # Import the FER model for facial expression recognition.
 import openai  # OpenAI API for generating text responses.
 
 #############################################################################################################################
 # Load environment variable(s).
 load_dotenv()
 
-# Set up the Hugging Face API for emotion detection.
-HUGGINGFACE_API_TOKEN = os.getenv("HUGGINGFACE_API_TOKEN")
 # Set up OpenAI API key.
 openai.api_key = os.getenv('OPENAI_API_KEY')
 
-# Load the processor and model for facial expression recognition.
-processor = AutoProcessor.from_pretrained("trpakov/vit-face-expression")
-model = AutoModelForImageClassification.from_pretrained("trpakov/vit-face-expression")
-
 #############################################################################################################################
-# Function to query the facial expression recognition model.
+# Function to query the facial expression recognition model using FER.
 def query_emotion(image):
-    # Preprocess the image.
-    inputs = processor(images=image, return_tensors="pt")
-
-    # Perform inference.
-    with torch.no_grad():
-        outputs = model(**inputs)
-
-    # Get predicted class index (the class with the highest logit).
-    logits = outputs.logits
-    predicted_class_idx = torch.argmax(logits, dim=-1).item()
-
-    # Retrieve the label names from the model.
-    label_names = model.config.id2label  # Mapping of indices to emotion labels.
-    predicted_label = label_names[predicted_class_idx]  # Get the predicted label.
-
-    return predicted_label
+    detector = FER()
+    emotions = detector.detect_emotions(image)
+    
+    if emotions:
+        # Get the emotion with the highest score.
+        dominant_emotion = max(emotions[0]['emotions'], key=emotions[0]['emotions'].get)
+        return dominant_emotion
+    else:
+        st.error("Could not detect any emotion.")
+        return None
 
 #############################################################################################################################
-# Function to generate a response using OpenAI based on detected emotion and user preference.
+# Function to generate a response using OpenAI based on detected emotion.
 def generate_text_based_on_mood(emotion, response_type):
     try:
         if response_type == "Joke":
@@ -103,23 +89,24 @@ def main():
 
         # Detect facial expression.
         emotion = query_emotion(image)
-        st.write(f"Detected emotion: {emotion}")
+        if emotion:
+            st.write(f"Detected emotion: {emotion}")
 
-        # Dropdown for selecting response type.
-        response_type = st.selectbox("Select the type of response:", ["Joke", "Motivational Message"])
+            # Dropdown for selecting response type.
+            response_type = st.selectbox("Select the type of response:", ["Joke", "Motivational Message"])
 
-        # Generate text based on detected emotion and user preference.
-        if st.button("Get Response"):
-            message = generate_text_based_on_mood(emotion, response_type)
-            st.write("Here's your response:")
-            st.write(message)
+            # Generate text based on detected emotion and user preference.
+            if st.button("Get Response"):
+                message = generate_text_based_on_mood(emotion, response_type)
+                st.write("Here's your response:")
+                st.write(message)
 
-            # Convert the generated message to audio.
-            audio_file = text_to_speech(message)
+                # Convert the generated message to audio.
+                audio_file = text_to_speech(message)
 
-            # Provide an audio player in the Streamlit app if audio file exists.
-            if audio_file:
-                st.audio(audio_file)  # Streamlit will handle playback.
+                # Provide an audio player in the Streamlit app if audio file exists.
+                if audio_file:
+                    st.audio(audio_file)  # Streamlit will handle playback.
 
 #############################################################################################################################
 # Run the application.