Polished interface a bit.

.gitignore

@@ -1,2 +1,3 @@
 .vscode/launch.json
-*.pyc
+*.pyc
+gradio_cached_examples/*

app.py

@@ -6,37 +6,41 @@ from backend import Infer
 DEBUG = True
 
 infer = Infer(DEBUG)
-
+example_image_path = ["assets/example_1.jpg", "assets/example_2.jpg", "assets/example_3.jpg"]
 
 with gr.Blocks(analytics_enabled=False, title="DeepNAPSI") as demo:
+    outputs = []
     with gr.Column():
         gr.Markdown("## Welcome to the DeepNAPSI application!")
         gr.Markdown("Upload an image of the one hand and click **Predict NAPSI** to see the output.\n" \
                     "> Note: Make sure there are no identifying information present in the image. The prediction can take up to 1 minute.")
         with gr.Column():
             with gr.Row():
-                image_input = gr.Image()
-                example_images = gr.Examples(["assets/example_1.jpg", "assets/example_2.jpg", "assets/example_3.jpg"], image_input)
-            with gr.Row():
-                image_button = gr.Button("Predict NAPSI")
-            outputs = []
-            with gr.Row():
-                outputs.append(gr.Number(label="DeepNAPSI Sum"))
-                with gr.Column():
-                    outputs.append(gr.Image())
-                    outputs.append(gr.Number(label="DeepNAPSI Thumb"))
                 with gr.Column():
-                    outputs.append(gr.Image())
-                    outputs.append(gr.Number(label="DeepNAPSI Index"))
-                with gr.Column():
-                    outputs.append(gr.Image())
-                    outputs.append(gr.Number(label="DeepNAPSI Middle"))
-                with gr.Column():
-                    outputs.append(gr.Image())
-                    outputs.append(gr.Number(label="DeepNAPSI Ring"))
-                with gr.Column():
-                    outputs.append(gr.Image())
-                    outputs.append(gr.Number(label="DeepNAPSI Pinky"))
+                    with gr.Row():
+                        image_input = gr.Image()
+                    with gr.Row():
+                        image_button = gr.Button("Predict NAPSI")
+                    with gr.Row():
+                        with gr.Column():
+                            outputs.append(gr.Image(label="Thumb"))
+                            outputs.append(gr.Number(label="DeepNAPSI Thumb", precision=0))
+                        with gr.Column():
+                            outputs.append(gr.Image(label="Index"))
+                            outputs.append(gr.Number(label="DeepNAPSI Index", precision=0))
+                        with gr.Column():
+                            outputs.append(gr.Image(label="Middle"))
+                            outputs.append(gr.Number(label="DeepNAPSI Middle", precision=0))
+                        with gr.Column():
+                            outputs.append(gr.Image(label="Ring"))
+                            outputs.append(gr.Number(label="DeepNAPSI Ring", precision=0))
+                        with gr.Column():
+                            outputs.append(gr.Image(label="Pinky"))
+                            outputs.append(gr.Number(label="DeepNAPSI Pinky", precision=0))
+                        outputs.append(gr.Number(label="DeepNAPSI Sum", precision=0))
+
+                example_images = gr.Examples(example_image_path, image_input, outputs,
+                                    fn=infer.predict, cache_examples=True)
         image_button.click(infer.predict, inputs=image_input, outputs=outputs)
 
 demo.launch(share=True)

backend.py

@@ -17,17 +17,17 @@ class Infer():
         nails = get_nails(cv2.cvtColor(data, cv2.COLOR_RGB2BGR))
         predictions = []
         if nails is None:
-            predictions.append(-1)
             for _ in range(5):
                 predictions.append(np.zeros((64, 64, 3)))
                 predictions.append(-1)
+            predictions.append("-1")
         else:
             model_prediction, uncertainty = self.model(nails)
             model_prediction = model_prediction[0]
             napsi_predictions = torch.argmax(model_prediction, 1)
             napsi_sum = int(napsi_predictions.sum().detach().cpu())
-            predictions.append(napsi_sum)
             for napsi_prediction, nail in zip(napsi_predictions, nails):
                 predictions.append(nail)
-                predictions.append(napsi_prediction)
+                predictions.append(int(napsi_prediction.detach().cpu()))
+        predictions.append(napsi_sum)
         return predictions