Update app.py

app.py

@@ -2,19 +2,7 @@ import gradio as gr
 from deepface import DeepFace
 from PIL import Image
 import numpy as np
-import base64
 
-# Function to encode images in base64
-def encode_image(image_path):
-    with open(image_path, "rb") as image_file:
-        encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
-    return f"data:image/jpeg;base64,{encoded_string}"
-
-# Example images as base64 strings (You need to download the images first)
-example_image_1 = encode_image("e.jpeg")  # Replace with your local image path
-example_image_2 = encode_image("k.jpeg")  # Replace with your local image path
-
-# Analyze the uploaded image
 def analyze_face(image):
     analysis_result = DeepFace.analyze(img_path=np.array(image), actions=['age', 'gender', 'race', 'emotion'])[0]
 
@@ -24,12 +12,10 @@ def analyze_face(image):
     race = analysis_result['dominant_race']
     emotion = analysis_result['dominant_emotion']
 
-    # Format emotion breakdown as a string
     emotions_detail = ', '.join([f"{k}: {v:.2f}%" for k, v in analysis_result['emotion'].items()])
 
     return age, f"{gender} ({gender_prob})", race, emotion, emotions_detail
 
-# Define the Gradio interface
 iface = gr.Interface(
     fn=analyze_face,
     inputs=gr.Image(type="pil"),
@@ -37,9 +23,7 @@ iface = gr.Interface(
              gr.Text(label="Gender Probability"), 
              gr.Text(label="Race"), 
              gr.Text(label="Dominant Emotion"),
-             gr.Text(label="Emotion Breakdown")],
-    examples=[[example_image_1], [example_image_2]]  # Adding example images
+             gr.Text(label="Emotion Breakdown")]
 )
 
-# Launch the Gradio app
 iface.launch()