Create app.py

app.py

@@ -0,0 +1,43 @@
+from transformers import pipeline
+from transformers.utils import logging
+from helper import load_image_from_url, render_results_in_image
+from PIL import Image
+import gradio as gr
+import os
+
+# Reduce the verbosity of transformers and suppress warnings
+logging.set_verbosity_error()
+
+# Load the object detection pipeline
+od_pipe = pipeline("object-detection", "facebook/detr-resnet-50")
+
+def get_pipeline_prediction(pil_image):
+    # Perform object detection
+    pipeline_output = od_pipe(pil_image)
+    # Render results on the image
+    processed_image = render_results_in_image(pil_image, pipeline_output)
+    return processed_image
+
+# Custom CSS to improve the interface
+css = """
+body { font-family: Arial, sans-serif; }
+button { background-color: #4CAF50; color: white; border: none; padding: 10px 20px; }
+"""
+
+# Set up the Gradio Blocks interface
+with gr.Blocks(css=css) as demo:
+    gr.Markdown("## Object Detection Service")
+    gr.Markdown("Upload an image and see the object detection results rendered on the image.")
+    with gr.Row():
+        image_input = gr.Image(label="Upload Image", type="pil", tool="editor")
+        submit_button = gr.Button("Detect Objects")
+    output_image = gr.Image(label="Detected Objects")
+
+    submit_button.click(
+        get_pipeline_prediction,
+        inputs=[image_input],
+        outputs=[output_image]
+    )
+
+# Launch the Gradio app
+demo.launch(share=True, server_port=int(os.environ.get('PORT1', 7860)))  # Default port 7860 if PORT1 is not set