Update app.py

app.py

@@ -11,15 +11,39 @@ mtcnn = MTCNN(keep_all=True, device=device)
 learn = load_learner('export.pkl')
 
 labels = learn.dls.vocab
+
+def scatter_plot_fn(emotions):
+    return gr.ScatterPlot.update(
+        value=emotions,
+        x="x",
+        y="y",
+        color="Origin",
+        tooltip="Name",
+        title="Class Heat Map",
+        color_legend_title="State",
+        caption="Class Monitor",
+    )
+
+emotions = {"x": [], "y": [], "State": []}
+plot = gr.ScatterPlot()
+
 def predict(img):
     img = PILImage.create(img)
     boxes, _ = mtcnn.detect(img)
-    pred,pred_idx,probs = learn.predict(img.crop(tuple(boxes[0].tolist())))
-    return {labels[i]: float(probs[i]) for i in range(len(labels))}
+    for box in boxes:
+        coords = tuple(box.tolist())
+        pred,pred_idx,probs = learn.predict(img.crop(coords))
+        emotions["x"].append((coords[0] + coords[2])/2)
+        emotions["y"].append((coords[1] + coords[3])/2)
+        emotions["State"].append(pred)
+    emotions_df = pd.DataFrame(emotions)
+    scatter_plot.load(fn=scatter_plot_fn, inputs=emotions_df, outputs=plot)
+    return plot
  
 title = "Students emotion classifer"
 description = "A students emotion classifer trained with fastai. Created as a demo for Gradio and HuggingFace Spaces."
 interpretation='default'
 enable_queue=True
 
-gr.Interface(fn=predict,inputs=gr.Image(source="webcam",shape=(512, 512)),outputs=gr.outputs.Label(num_top_classes=3),title=title,description=description,interpretation=interpretation,enable_queue=enable_queue).launch()
+#gr.Interface(fn=predict,inputs=gr.Image(source="webcam",shape=(512, 512)),outputs=gr.outputs.Label(num_top_classes=3),title=title,description=description,interpretation=interpretation,enable_queue=enable_queue).launch()
+gr.Interface(fn=predict,inputs=gr.Image(source="webcam",shape=(512, 512)),outputs=plot,title=title,description=description,interpretation=interpretation,enable_queue=enable_queue).launch()