Update app.py

app.py

@@ -1,35 +1,39 @@
 from transformers import (
     AutoModelForSequenceClassification,  # For text emotion detection model
-    AutoTokenizer,
+    AutoTokenizer, 
     pipeline,                           # For creating inference pipeline
-    PreTrainedTokenizerFast            # For processing text input
+
 )
-from WebCam import capture_webcam
 from colorama import Fore, Style        # For colored console output
 import pandas as pd                     # For data handling
 import time
 from datetime import datetime
 import matplotlib.pyplot as plt
 import gradio as gr
+from fer import FER
+import cv2
 
 # Dictionaries to store emotion data over time
 text_dataDict = {"Time": [], "Emotion": [], "Confidence Score": []}
 face_dataDict = {"Time": [], "Emotion": [], "Confidence Score": []}
 
-emotionDetectModel = AutoModelForSequenceClassification.from_pretrained("borisn70/bert-43-multilabel-emotion-detection") #to be replaced with my fine-tuned model once it is ready
-tokenizer = AutoTokenizer.from_pretrained("borisn70/bert-43-multilabel-emotion-detection") #ensure we get correct tokenizer that is compatible with this model by loading it directly from this model
+# Load model and tokenizer directly from HuggingFace
+emotionDetectModel = AutoModelForSequenceClassification.from_pretrained("borisn70/bert-43-multilabel-emotion-detection")
+tokenizer = AutoTokenizer.from_pretrained("borisn70/bert-43-multilabel-emotion-detection")  # Load tokenizer directly from model
 pipe = pipeline(task="text-classification", model=emotionDetectModel, tokenizer=tokenizer)
 
+face_emotion_detector = FER()
+
 localFormat = "%Y-%m-%d %H:%M:%S" #this is how will print the timestamp: year-month-day hour-minutes-seconds (army time)
 #currTime = datetime.now().astimezone().strftime(localFormat) this returns the time in the localFormat
 #current_Time_Tuple = time.strptime(str(currTime), str(localFormat)) #creates a tuple that contains each part of the local format separate
 #current_Time_In_Seconds = time.mktime(current_Time_Tuple) #converts the tuple into the number of seconds
 
-def emotionAnalysis(message):
+def emotionAnalysis(message, face):
     """
     Main function that processes both text and facial emotions
     Args:
-        inp (str): User input text
+        message (str): User input text
     Returns:
         tuple: (str, plt) Contains the emotion results text and the updated plot
     """
@@ -48,7 +52,16 @@ def emotionAnalysis(message):
     text_dataDict["Confidence Score"].append(round(text_score, 2))
     
     # Capture and process facial emotion
-    face_emotion, face_score = capture_webcam()
+    # Load the image using OpenCV (BGR format)
+    img = cv2.imread(face)
+    # Convert the image to RGB (FER uses RGB, OpenCV loads images in BGR format)
+    if img is None:
+        print("Error: Could not load the image. Check the image path.")
+        return
+    
+    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+
+    face_emotion, face_score = face_emotion_detector.top_emotion(img_rgb)
     face_timestamp = datetime.now().astimezone().strftime(localFormat)
     
     # Store facial emotion data for plotting
@@ -86,6 +99,9 @@ def displayResults():
     
     return plt
 
+#with gr.Blocks as demo:
+    #conesnt_radio = gr.Radio(["yes", "no"], label="This app uses your webcam to detect emotions from your face and reads your text inputs to determine emotions from your writing. Do you give consent? ")
+
 # Create Gradio interface with consent notice in the description
 interface = gr.Interface(
     fn=emotionAnalysis,
@@ -93,7 +109,8 @@ interface = gr.Interface(
         gr.Textbox(
             label="Enter your text",
             placeholder="Type your message here. Type 'quit' to see final results."
-        )
+        ),
+        gr.Image(label="Webcam Facial Expression", source="webcam")
     ],
     outputs=[
         gr.Text(label="Emotion Results"),