Update app.py

app.py

@@ -63,13 +63,13 @@ def predict2(image_np,Threshold):
         category_index,
         use_normalized_coordinates=True,
         max_boxes_to_draw=20,
-        min_score_thresh=Threshold,#0.38,
+        min_score_thresh=0.38,
         agnostic_mode=False,
         line_thickness=2)
 
     result_pil_img2 = tf.keras.utils.array_to_img(image_np_with_detections[0])
     
-    return result_pil_img2
+    return result_pil_img2,Threshold
 
 
 def predict3(image_np,Threshold):
@@ -90,13 +90,13 @@ def predict3(image_np,Threshold):
         category_index,
         use_normalized_coordinates=True,
         max_boxes_to_draw=20,
-        min_score_thresh=Threshold,#.38,
+        min_score_thresh=.38,
         agnostic_mode=False,
         line_thickness=2)
 
     result_pil_img4 = tf.keras.utils.array_to_img(image_np_with_detections[0])
     
-    return result_pil_img4
+    return result_pil_img4,Threshold
 
 # def detect_video(video):
 #     # Create a video capture object
@@ -173,7 +173,7 @@ test12 = os.path.join(os.path.dirname(__file__), "data/test12.jpeg")
 base_image = gr.Interface(
     fn=predict,
 #    inputs=[gr.Image(type="pil"),gr.Slider(minimum=0.01, maximum=1, value=0.38 ,label="Threshold",info="[not in used]to set prediction confidence threshold")],
-    inputs=[gr.Image(type="pil"),gr.Textbox(value=threshold_d ,label="To change default 0.38 prediction confidence Threshold",info="Select image with 0.38 threshold to start, you may amend threshold after each first image inference")],
+    inputs=[gr.Image(type="pil"),gr.Slider(minimum=0.01, maximum=1,value=threshold_d ,label="[WIP]To change default 0.38 prediction confidence Threshold",info="[not in used]Select image with 0.38 threshold to start, you may amend threshold after each first image inference")],
 
     outputs=[gr.Image(type="pil",label="Base Model Inference"),gr.Image(type="pil",label="Tuned Model Inference"),gr.Textbox(label="Both images inferenced threshold")],
     title="Luffy and Chopper Head detection. SSD mobile net V2 320x320",