Update app.py

changed helped funcs and imported copy

app.py

@@ -5,7 +5,7 @@ from flax.training.common_utils import shard
 from PIL import Image
 from argparse import Namespace
 import gradio as gr
-
+import copy # added
 import numpy as np
 import mediapipe as mp
 from mediapipe import solutions
@@ -18,39 +18,54 @@ from diffusers import (
     FlaxControlNetModel,
     FlaxStableDiffusionControlNetPipeline,
 )
+right_style_lm = copy.deepcopy(solutions.drawing_styles.get_default_hand_landmarks_style())
+left_style_lm = copy.deepcopy(solutions.drawing_styles.get_default_hand_landmarks_style())
+right_style_lm[0].color=(251, 206, 177)
+left_style_lm[0].color=(255, 255, 225)
+
+def draw_landmarks_on_image(rgb_image, detection_result, overlap=False, hand_encoding=False):
+    hand_landmarks_list = detection_result.hand_landmarks
+    handedness_list = detection_result.handedness
+    if overlap:
+        annotated_image = np.copy(rgb_image)
+    else:
+        annotated_image = np.zeros_like(rgb_image)
+
+    # Loop through the detected hands to visualize.
+    for idx in range(len(hand_landmarks_list)):
+        hand_landmarks = hand_landmarks_list[idx]
+        handedness = handedness_list[idx]
+        # Draw the hand landmarks.
+        hand_landmarks_proto = landmark_pb2.NormalizedLandmarkList()
+        hand_landmarks_proto.landmark.extend([
+                landmark_pb2.NormalizedLandmark(x=landmark.x, y=landmark.y, z=landmark.z) for landmark in hand_landmarks
+        ])
+        if hand_encoding:
+            if handedness[0].category_name == "Left":
+                solutions.drawing_utils.draw_landmarks(
+                        annotated_image,
+                        hand_landmarks_proto,
+                        solutions.hands.HAND_CONNECTIONS,
+                        left_style_lm,
+                        solutions.drawing_styles.get_default_hand_connections_style())
+            if handedness[0].category_name == "Right":
+                solutions.drawing_utils.draw_landmarks(
+                        annotated_image,
+                        hand_landmarks_proto,
+                        solutions.hands.HAND_CONNECTIONS,
+                        right_style_lm,
+                        solutions.drawing_styles.get_default_hand_connections_style())
+        else:
+            solutions.drawing_utils.draw_landmarks(
+                    annotated_image,
+                    hand_landmarks_proto,
+                    solutions.hands.HAND_CONNECTIONS,
+                    solutions.drawing_styles.get_default_hand_landmarks_style(),
+                    solutions.drawing_styles.get_default_hand_connections_style())
 
+    return annotated_image
 
-# mediapipe annotation
-MARGIN = 10  # pixels
-FONT_SIZE = 1
-FONT_THICKNESS = 1
-HANDEDNESS_TEXT_COLOR = (88, 205, 54) # vibrant green
-
-def draw_landmarks_on_image(rgb_image, detection_result):
-  hand_landmarks_list = detection_result.hand_landmarks
-  handedness_list = detection_result.handedness
-  annotated_image = np.zeros_like(rgb_image)
-
-  # Loop through the detected hands to visualize.
-  for idx in range(len(hand_landmarks_list)):
-    hand_landmarks = hand_landmarks_list[idx]
-    handedness = handedness_list[idx]
-
-    # Draw the hand landmarks.
-    hand_landmarks_proto = landmark_pb2.NormalizedLandmarkList()
-    hand_landmarks_proto.landmark.extend([
-      landmark_pb2.NormalizedLandmark(x=landmark.x, y=landmark.y, z=landmark.z) for landmark in hand_landmarks
-    ])
-    solutions.drawing_utils.draw_landmarks(
-      annotated_image,
-      hand_landmarks_proto,
-      solutions.hands.HAND_CONNECTIONS,
-      solutions.drawing_styles.get_default_hand_landmarks_style(),
-      solutions.drawing_styles.get_default_hand_connections_style())
-
-  return annotated_image
-
-def generate_annotation(img):
+def generate_annotation(img, overlap=False, hand_encoding=False):
     """img(input): numpy array
        annotated_image(output): numpy array
     """
@@ -68,7 +83,7 @@ def generate_annotation(img):
     detection_result = detector.detect(image)
 
     # STEP 5: Process the classification result. In this case, visualize it.
-    annotated_image = draw_landmarks_on_image(image.numpy_view(), detection_result)
+    annotated_image = draw_landmarks_on_image(image.numpy_view(), detection_result, overlap=overlap, hand_encoding=hand_encoding)
     return annotated_image
 
 args = Namespace(