Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import cv2
 import torch
 import numpy as np
+from PIL import Image
 
 # Load the YOLOv5 model
 model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
@@ -18,7 +19,7 @@ def run_inference(image):
     annotated_image = results.render()[0]
     annotated_image = cv2.cvtColor(annotated_image, cv2.COLOR_BGR2RGB)
 
-    return annotated_image
+    return Image.fromarray(annotated_image)
 
 # Function to generate a summary for the detected objects
 def generate_summary(image):
@@ -29,76 +30,95 @@ def generate_summary(image):
         summary += f"- {obj['name']} with confidence {obj['confidence']:.2f}\n"
     return summary
 
+# Function to generate a scene description based on the summary
+def generate_scene_description(summary):
+    if "person" in summary.lower():
+        return "This scene might involve people interacting or a social gathering."
+    elif "car" in summary.lower() or "truck" in summary.lower():
+        return "This could be a street scene or a transportation-related scenario."
+    elif "dog" in summary.lower() or "cat" in summary.lower():
+        return "This appears to involve pets or animals, possibly in a domestic or outdoor setting."
+    else:
+        return "This scene involves various objects. It could be a dynamic or static environment."
+
 # Create the Gradio interface with improved UI
 with gr.Blocks(css="""
     body {
         font-family: 'Poppins', sans-serif;
-        background-color: #2B3D41;
-        color: #F9B9D2;
+        margin: 0;
+        background: linear-gradient(135deg, #3D52A0, #7091E6, #8697C4, #ADBBDA, #EDE8F5);
+        background-size: 400% 400%;
+        animation: gradient-animation 15s ease infinite;
+        color: #FFFFFF;
+    }
+    @keyframes gradient-animation {
+        0% { background-position: 0% 50%; }
+        50% { background-position: 100% 50%; }
+        100% { background-position: 0% 50%; }
     }
-    header {
-        background-color: #83A0A0;
-        padding: 20px;
+    h1 {
         text-align: center;
-        border-radius: 10px;
-        color: white;
-        box-shadow: 0 4px 10px rgba(0, 0, 0, 0.3);
+        color: #FFFFFF;
+        font-size: 2.5em;
+        font-weight: bold;
+        margin-bottom: 0.5em;
+        text-shadow: 2px 2px 5px rgba(0, 0, 0, 0.3);
     }
     footer {
-        background-color: #4C5F6B;
-        padding: 10px;
         text-align: center;
-        border-radius: 10px;
-        color: white;
         margin-top: 20px;
-        box-shadow: 0 4px 10px rgba(0, 0, 0, 0.3);
+        padding: 10px;
+        font-size: 1em;
+        color: #FFFFFF;
+        background: rgba(61, 82, 160, 0.8);
+        border-radius: 8px;
     }
-    .btn-primary {
-        background-color: #BCA0BC;
-        color: #2B3D41;
-        padding: 10px 20px;
-        border-radius: 5px;
-        font-weight: bold;
+    .gr-button {
+        font-size: 1em;
+        padding: 12px 24px;
+        background-color: #7091E6;
+        color: #FFFFFF;
         border: none;
-        cursor: pointer;
-        transition: all 0.3s;
+        border-radius: 5px;
+        transition: all 0.3s ease-in-out;
     }
-    .btn-primary:hover {
-        background-color: #F9B9D2;
-        color: #2B3D41;
+    .gr-button:hover {
+        background-color: #8697C4;
+        transform: scale(1.05);
+        box-shadow: 0 5px 15px rgba(0, 0, 0, 0.2);
     }
     .gr-box {
-        background-color: #4C5F6B;
+        background: rgba(255, 255, 255, 0.1);
+        border: 1px solid rgba(255, 255, 255, 0.3);
         border-radius: 10px;
-        padding: 20px;
-        color: #F9B9D2;
+        padding: 15px;
         box-shadow: 0 4px 10px rgba(0, 0, 0, 0.3);
-    }
-    .gr-input {
-        background-color: #BCA0BC;
-        border-radius: 5px;
-        border: none;
-        padding: 10px;
-        color: #2B3D41;
+        color: #FFFFFF;
     }
 """) as demo:
     with gr.Row():
-        gr.Markdown("<h1 style='text-align:center; color:#D8D8F6;'>✨ InsightVision: Detect, Analyze, Summarize ✨</h1>")
-    
+        gr.Markdown("<h1>✨ InsightVision: Detect, Analyze, Summarize ✨</h1>")
+
     with gr.Row():
         with gr.Column(scale=2):
-            image_input = gr.Image(label="Upload Image", type="pil", elem_classes="gr-input")
-            with gr.Row():
-                detect_button = gr.Button("Run Detection", elem_classes="btn-primary")
+            image_input = gr.Image(label="Upload Image", type="pil", elem_classes="gr-box")
+            detect_button = gr.Button("Run Detection", elem_classes="gr-button")
         with gr.Column(scale=3):
             annotated_image_output = gr.Image(label="Detected Image", type="pil", elem_classes="gr-box")
             summary_output = gr.Textbox(label="Detection Summary", lines=10, interactive=False, elem_classes="gr-box")
+            scene_description_output = gr.Textbox(label="Scene Description", lines=5, interactive=False, elem_classes="gr-box")
     
     # Actions for buttons
+    def detect_and_process(image):
+        annotated_image = run_inference(image)
+        summary = generate_summary(np.array(image))
+        scene_description = generate_scene_description(summary)
+        return annotated_image, summary, scene_description
+    
     detect_button.click(
-        fn=lambda image: (run_inference(image), generate_summary(np.array(image))),
+        fn=detect_and_process,
         inputs=[image_input],
-        outputs=[annotated_image_output, summary_output]
+        outputs=[annotated_image_output, summary_output, scene_description_output]
     )
 
     gr.Markdown("<footer>Made with ❤️ using Gradio and YOLOv5 | © 2024 InsightVision</footer>")