added code for gesture recognition

.gitattributes

@@ -0,0 +1 @@
+*.task filter=lfs diff=lfs merge=lfs -text

app.py

@@ -4,37 +4,66 @@ import gradio as gr
 import mediapipe as mp
 import numpy as np
 
-mp_drawing = mp.solutions.drawing_utils
-mp_selfie_segmentation = mp.solutions.selfie_segmentation
 
-seg = mp_selfie_segmentation.SelfieSegmentation()
-
-BG_COLOR = (0, 0, 0)
+seg = mp.solutions.selfie_segmentation.SelfieSegmentation()
+options = mp.tasks.vision.GestureRecognizerOptions(
+    base_options=mp.tasks.BaseOptions(
+        model_asset_path="models/gesture_recognizer.task"
+    ),
+    running_mode=mp.tasks.vision.RunningMode.IMAGE,
+)
+recognizer = mp.tasks.vision.GestureRecognizer.create_from_options(options)
 
 
 def close_segmentation_model():
-    print("Closing segmentation model")
+    print("Closing Models")
     seg.close()
+    recognizer.close()
 
 
-def snap(video):
+def process_selfie(video):
     image = cv2.cvtColor(video, cv2.COLOR_RGB2BGR)
     results = seg.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
     condition = np.stack((results.segmentation_mask,) * 3, axis=-1) > 0.5
 
     bg_image = np.zeros(image.shape, dtype=np.uint8)
-    bg_image[:] = BG_COLOR
+    bg_image[:] = (0, 0, 0)
     output_image = np.where(condition, video, bg_image)
 
     return output_image
 
 
-demo = gr.Interface(
-    fn=snap,
+def process_gesture(video):
+    mp_image = mp.Image(
+        image_format=mp.ImageFormat.SRGB, data=cv2.cvtColor(video, cv2.COLOR_BGR2RGB)
+    )
+    result = recognizer.recognize(mp_image)
+    print(result.gestures)
+    if not result.gestures:
+        gesture_labels = {"None": 1.0}
+    else:
+        gesture_labels = {i.category_name: i.score for i in result.gestures[0]}
+
+    return gesture_labels
+
+
+selfie_interface = gr.Interface(
+    fn=process_selfie,
     inputs=gr.Image(sources=["webcam"], streaming=True),
     outputs="image",
     live=True,
 )
 
+gesture_interface = gr.Interface(
+    fn=process_gesture,
+    inputs=gr.Image(sources=["webcam"], streaming=True),
+    outputs="label",
+    live=True,
+)
+
+interface = gr.TabbedInterface(
+    [selfie_interface, gesture_interface], ["Selfie", "Gesture"]
+)
+
 if __name__ == "__main__":
-    demo.launch()
+    interface.launch()

models/gesture_recognizer.task

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97952348cf6a6a4915c2ea1496b4b37ebabc50cbbf80571435643c455f2b0482
+size 8373440