Update app.py

app.py

@@ -91,9 +91,9 @@ def gen_grad_img_single(weights, img, alpha = 0.4):
     grad_model = Model(input, [x, output])
     heatmaps, y_pred = create_heatmap(grad_model, img)
     
-    for i in range(len(y_pred)):
-      if y_pred[i] > 0.5: y_pred[i] = 1
-      else: y_pred[i] = 0
+    # for i in range(len(y_pred)):
+    #   if y_pred[i] > 0.5: y_pred[i] = 1
+    #   else: y_pred[i] = 0
     
     img = superimpose_single(heatmaps, img[0])
     return np.array(img).astype('uint8'), y_pred
@@ -104,14 +104,19 @@ weights = "weights.h5"
 
 def get_grad(img):
     img = img_pros(img)
-    a = gen_grad_img_single(weights, img)
-    return a
+    grad_img, y_pred = gen_grad_img_single(weights, img)
+    
+    if y_pred[0] > 0.5: y_pred[0] = "cat"
+    else: y_pred[0] = "dog"
+        
+    text = "Raw Score: " + str(y_pred) + "\nClassification: " + y_pred[0]
+    return grad_img, text
 
 demo = gr.Interface(
   fn = get_grad,
   inputs = gr.Image(type = "pil", shape = (224,224)),
   # outputs = [gr.outputs.Label(num_top_classes = 2, label = 'Classifiaction'), gr.Textbox('infer_time', label = 'Inference Time(ms)')]
-  outputs = [gr.Image(type = "numpy"), gr.Textbox('y_pred', label = 'Prediction')]
+  outputs = [gr.Image(type = "numpy"), gr.Textbox(label = 'Prediction (threshold: 0.5)')]
    )
 demo.launch()