Update app.py

app.py

@@ -373,26 +373,26 @@ def inference(image, task, *args, **kwargs):
 
 class ImageMask(gr.components.Image):
     """
-    Sets: source="canvas", tool="sketch"
+    Custom Image component with sketch tool enabled
     """
 
     is_template = True
 
     def __init__(self, **kwargs):
-        super().__init__(source="upload", tool="sketch", interactive=True, **kwargs)
+        super().__init__(tool="sketch", interactive=True, **kwargs)
 
     def preprocess(self, x):
         return super().preprocess(x)
 
 class Video(gr.components.Video):
     """
-    Sets: source="canvas", tool="sketch"
+    Custom Video component
     """
 
     is_template = True
 
     def __init__(self, **kwargs):
-        super().__init__(source="upload", **kwargs)
+        super().__init__(interactive=True, **kwargs)
 
     def preprocess(self, x):
         return super().preprocess(x)
@@ -423,18 +423,24 @@ description = f"""
 """
 
 article = "SEEM Demo" + (" (Simplified Interface)" if not model_loaded else "")
-inputs = [ImageMask(label="[Stroke] Draw on Image",type="pil"), gr.inputs.CheckboxGroup(choices=["Stroke", "Example", "Text", "Audio", "Video", "Panoptic"], type="value", label="Interative Mode"), ImageMask(label="[Example] Draw on Referring Image",type="pil"), gr.Textbox(label="[Text] Referring Text"), gr.Audio(label="[Audio] Referring Audio", source="microphone", type="filepath"), gr.Video(label="[Video] Referring Video Segmentation",format="mp4",interactive=True)]
+inputs = [
+    ImageMask(label="[Stroke] Draw on Image", type="pil"), 
+    gr.CheckboxGroup(choices=["Stroke", "Example", "Text", "Audio", "Video", "Panoptic"], label="Interactive Mode"), 
+    ImageMask(label="[Example] Draw on Referring Image", type="pil"), 
+    gr.Textbox(label="[Text] Referring Text"), 
+    gr.Audio(label="[Audio] Referring Audio", type="filepath", sources=["microphone"]), 
+    gr.Video(label="[Video] Referring Video Segmentation", format="mp4")
+]
+
+outputs = [
+    gr.Image(type="pil", label="Segmentation Results (COCO classes as label)"),
+    gr.Video(label="Video Segmentation Results (COCO classes as label)", format="mp4")
+]
+
 gr.Interface(
     fn=inference,
     inputs=inputs,
-    outputs=[
-        gr.outputs.Image(
-        type="pil",
-        label="Segmentation Results (COCO classes as label)"),
-        gr.Video(
-        label="Video Segmentation Results (COCO classes as label)", format="mp4"
-        ),
-    ],
+    outputs=outputs,
     examples=[
     ["examples/corgi1.webp", ["Text"], "examples/corgi2.jpg", "The corgi.", None, None],
     ["examples/river1.png", ["Text", "Audio"], "examples/river2.png", "The green trees.", "examples/river1.wav", None],