Updated app

app.py

@@ -23,7 +23,7 @@ def get_output_figure(pil_img, scores, labels, boxes):
     plt.imshow(pil_img)
     ax = plt.gca()
     colors = COLORS * 100
-    for score, label, (xmin, ymin, xmax, ymax), c in zip (scores.tolist(), labels.tolist(), boxes.tolist(), colors):
+    for score, label, (xmin, ymin, xmax, ymax), c in zip(scores.tolist(), labels.tolist(), boxes.tolist(), colors):
         ax.add_patch(plt.Rectangle((xmin, ymin), xmax - xmin, ymax - ymin, fill=False, color=c, linewidth=3))
         text = f'{model.config.id2label[label]}: {score:0.2f}'
         ax.text(xmin, ymin, text, fontsize=15, 
@@ -89,12 +89,10 @@ def detect(image):
     with torch.no_grad():
         outputs = model(**encoding)
 
-    #print(outputs)
     width, height = image.size
     postprocessed_outputs = processor.post_process_object_detection(outputs, target_sizes=[(height, width)], threshold=0.9)
     results = postprocessed_outputs[0]
 
-    #print(results)
 
     output_figure = get_output_figure(image, results['scores'], results['labels'], results['boxes'])
 
@@ -110,15 +108,24 @@ def detect(image):
     buf.seek(0)
     output_pil_img_attn = Image.open(buf)
 
-    #print(output_pil_img)
-
     return output_pil_img, output_pil_img_attn
 
-demo = gr.Interface(
-    fn=detect, 
-    inputs=gr.Image(label="Input image", type="pil"), 
-    outputs=[
-        gr.Image(label="Output image predictions", type="pil"),
-        gr.Image(label="Output attention weights", type="pil")
-        ])
-demo.launch()
+with gr.Blocks() as demo:
+    gr.Markdown("# Object detection with DETR")
+    gr.Markdown(
+        """
+        This applciation uses DETR (DEtection TRansformers) to detect objects on images.
+        You can load an image and see the predictions for the objects detected along with the attention weights.
+        """
+    )
+    
+    gr.Interface(
+        fn=detect, 
+        inputs=gr.Image(label="Input image", type="pil"), 
+        outputs=[
+            gr.Image(label="Output prediction", type="pil"),
+            gr.Image(label="Attention weights", type="pil")
+        ]
+    ).launch()
+
+demo.launch()