Initial commit for hand detection space

test.py → app.py

@@ -1,106 +1,106 @@
-import cv2
-import mediapipe as mp
-import numpy as np
-import gradio as gr
-import tempfile
-
-# Load model
-MODEL_PATH = "hand_landmarker.task"
-
-BaseOptions = mp.tasks.BaseOptions
-HandLandmarker = mp.tasks.vision.HandLandmarker
-HandLandmarkerOptions = mp.tasks.vision.HandLandmarkerOptions
-VisionRunningMode = mp.tasks.vision.RunningMode
-mp_image = mp.Image
-mp_format = mp.ImageFormat
-
-# Finger connections and colors
-HAND_CONNECTIONS = [
-    (0, 1), (1, 2), (2, 3), (3, 4),
-    (0, 5), (5, 6), (6, 7), (7, 8),
-    (0, 9), (9,10), (10,11), (11,12),
-    (0,13), (13,14), (14,15), (15,16),
-    (0,17), (17,18), (18,19), (19,20)
-]
-
-FINGER_COLORS = {
-    'thumb': (245, 245, 245),
-    'index': (128, 0, 128),
-    'middle': (0, 255, 0),
-    'ring': (0, 165, 255),
-    'pinky': (255, 0, 0),
-    'palm': (100, 100, 100)
-}
-
-def get_finger_color(start_idx):
-    if start_idx in range(0, 5):
-        return FINGER_COLORS['thumb']
-    elif start_idx in range(5, 9):
-        return FINGER_COLORS['index']
-    elif start_idx in range(9, 13):
-        return FINGER_COLORS['middle']
-    elif start_idx in range(13, 17):
-        return FINGER_COLORS['ring']
-    elif start_idx in range(17, 21):
-        return FINGER_COLORS['pinky']
-    else:
-        return FINGER_COLORS['palm']
-
-def process_video(video_path):
-    cap = cv2.VideoCapture(video_path)
-
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
-    out_path = tmp_out.name
-
-    fps = cap.get(cv2.CAP_PROP_FPS)
-    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-    out = cv2.VideoWriter(out_path, fourcc, fps, (w, h))
-
-    options = HandLandmarkerOptions(
-        base_options=BaseOptions(model_asset_path=MODEL_PATH),
-        running_mode=VisionRunningMode.IMAGE,
-        num_hands=2,
-        min_hand_detection_confidence=0.5,
-        min_hand_presence_confidence=0.5,
-        min_tracking_confidence=0.5
-    )
-
-    with HandLandmarker.create_from_options(options) as landmarker:
-        while cap.isOpened():
-            ret, frame = cap.read()
-            if not ret:
-                break
-
-            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-            mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
-            results = landmarker.detect(mp_img)
-
-            if results.hand_landmarks:
-                for hand_landmarks in results.hand_landmarks:
-                    points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
-
-                    for start, end in HAND_CONNECTIONS:
-                        color = get_finger_color(start)
-                        cv2.line(frame, points[start], points[end], color, 2)
-
-                    for i, (x, y) in enumerate(points):
-                        cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
-
-            out.write(frame)
-
-    cap.release()
-    out.release()
-    return out_path
-
-# Gradio interface
-demo = gr.Interface(
-    fn=process_video,
-    inputs=gr.Video(label="Upload Video or Use Webcam"),
-    outputs=gr.Video(label="Hand Landmark Annotated Video"),
-    title="Hand Detection ",
-    description="Upload a video or use webcam to detect hands."
-)
-
-demo.launch()
+import cv2
+import mediapipe as mp
+import numpy as np
+import gradio as gr
+import tempfile
+
+# Load model
+MODEL_PATH = "hand_landmarker.task"
+
+BaseOptions = mp.tasks.BaseOptions
+HandLandmarker = mp.tasks.vision.HandLandmarker
+HandLandmarkerOptions = mp.tasks.vision.HandLandmarkerOptions
+VisionRunningMode = mp.tasks.vision.RunningMode
+mp_image = mp.Image
+mp_format = mp.ImageFormat
+
+# Finger connections and colors
+HAND_CONNECTIONS = [
+    (0, 1), (1, 2), (2, 3), (3, 4),
+    (0, 5), (5, 6), (6, 7), (7, 8),
+    (0, 9), (9,10), (10,11), (11,12),
+    (0,13), (13,14), (14,15), (15,16),
+    (0,17), (17,18), (18,19), (19,20)
+]
+
+FINGER_COLORS = {
+    'thumb': (245, 245, 245),
+    'index': (128, 0, 128),
+    'middle': (0, 255, 0),
+    'ring': (0, 165, 255),
+    'pinky': (255, 0, 0),
+    'palm': (100, 100, 100)
+}
+
+def get_finger_color(start_idx):
+    if start_idx in range(0, 5):
+        return FINGER_COLORS['thumb']
+    elif start_idx in range(5, 9):
+        return FINGER_COLORS['index']
+    elif start_idx in range(9, 13):
+        return FINGER_COLORS['middle']
+    elif start_idx in range(13, 17):
+        return FINGER_COLORS['ring']
+    elif start_idx in range(17, 21):
+        return FINGER_COLORS['pinky']
+    else:
+        return FINGER_COLORS['palm']
+
+def process_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
+    out_path = tmp_out.name
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    out = cv2.VideoWriter(out_path, fourcc, fps, (w, h))
+
+    options = HandLandmarkerOptions(
+        base_options=BaseOptions(model_asset_path=MODEL_PATH),
+        running_mode=VisionRunningMode.IMAGE,
+        num_hands=2,
+        min_hand_detection_confidence=0.5,
+        min_hand_presence_confidence=0.5,
+        min_tracking_confidence=0.5
+    )
+
+    with HandLandmarker.create_from_options(options) as landmarker:
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
+            results = landmarker.detect(mp_img)
+
+            if results.hand_landmarks:
+                for hand_landmarks in results.hand_landmarks:
+                    points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
+
+                    for start, end in HAND_CONNECTIONS:
+                        color = get_finger_color(start)
+                        cv2.line(frame, points[start], points[end], color, 2)
+
+                    for i, (x, y) in enumerate(points):
+                        cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
+
+            out.write(frame)
+
+    cap.release()
+    out.release()
+    return out_path
+
+# Gradio interface
+demo = gr.Interface(
+    fn=process_video,
+    inputs=gr.Video(label="Upload Video or Use Webcam"),
+    outputs=gr.Video(label="Hand Landmark Annotated Video"),
+    title="Hand Detection ",
+    description="Upload a video or use webcam to detect hands."
+)
+
+demo.launch()

requirement.text → requirements.txt

@@ -1,216 +1,216 @@
-absl-py==2.2.2
-aiofiles==24.1.0
-aiohappyeyeballs==2.4.6
-annotated-types==0.7.0
-antlr4-python3-runtime==4.9.3
-anyio==4.9.0
-appdirs==1.4.4
-asgiref==3.8.1
-asttokens==3.0.0
-astunparse==1.6.3
-attrs==25.1.0
-backcall==0.2.0
-backoff==2.2.1
-bcrypt==4.2.1
-blinker==1.9.0
-cachetools==5.5.2
-certifi==2025.1.31
-cffi==1.17.1
-charset-normalizer==3.4.1
-click==8.1.8
-colorama==0.4.6
-comtypes==1.4.10
-contourpy==1.3.1
-cycler==0.12.1
-decorator==5.2.1
-distro==1.9.0
-Django==5.1.7
-docopt==0.6.2
-docstring_parser==0.16
-durationpy==0.9
-et_xmlfile==2.0.0
-executing==2.2.0
-fastapi==0.115.12
-fastjsonschema==2.21.1
-ffmpy==0.5.0
-filelock==3.17.0
-filetype==1.2.0
-flatbuffers==25.2.10
-fonttools==4.57.0
-frozenlist==1.5.0
-fsspec==2025.2.0
-gast==0.6.0
-google-api-core==2.24.2
-google-auth==2.38.0
-google-auth-oauthlib==1.2.1
-google-cloud-aiplatform==1.85.0
-google-cloud-bigquery==3.30.0
-google-cloud-core==2.4.3
-google-cloud-resource-manager==1.14.2
-google-cloud-storage==2.19.0
-google-crc32c==1.7.0
-google-pasta==0.2.0
-google-resumable-media==2.7.2
-googleapis-common-protos==1.69.2
-gradio==5.24.0
-gradio_client==1.8.0
-groovy==0.1.2
-grpc-google-iam-v1==0.14.2
-grpcio==1.71.0
-grpcio-status==1.71.0
-h11==0.14.0
-h5py==3.13.0
-httpcore==1.0.7
-httptools==0.6.4
-httpx==0.28.1
-huggingface-hub==0.30.2
-idna==3.10
-importlib_resources==6.5.2
-jax==0.5.3
-jaxlib==0.5.3
-Jinja2==3.1.5
-jiter==0.8.2
-jmespath==1.0.1
-joblib==1.4.2
-json5==0.10.0
-json_repair==0.39.1
-jsonpath-python==1.0.6
-jsonpickle==4.0.2
-jsonref==1.1.0
-junitparser==3.2.0
-jupyterlab_pygments==0.3.0
-keras==2.15.0
-kiwisolver==1.4.8
-langdetect==1.0.9
-libclang==18.1.1
-lxml==5.3.1
-Markdown==3.7
-markdown-it-py==3.0.0
-MarkupSafe==3.0.2
-marshmallow==3.26.1
-matplotlib==3.10.1
-matplotlib-inline==0.1.7
-mdurl==0.1.2
-mediapipe==0.10.21
-mistune==3.1.3
-ml_dtypes==0.5.1
-mmh3==5.1.0
-monotonic==1.6
-mpmath==1.3.0
-multidict==6.1.0
-mypy-extensions==1.0.0
-namex==0.0.8
-nest-asyncio==1.6.0
-networkx==3.4.2
-numpy==1.26.4
-oauthlib==3.2.2
-olefile==0.47
-omegaconf==2.3.0
-opencv-contrib-python==4.11.0.86
-opencv-python==4.11.0.86
-openpyxl==3.1.5
-opentelemetry-proto==1.31.0
-opentelemetry-util-http==0.52b0
-opt_einsum==3.4.0
-optree==0.15.0
-orjson==3.10.15
-overrides==7.7.0
-packaging==24.2
-pandas==2.2.3
-pandocfilters==1.5.1
-parso==0.8.4
-pickleshare==0.7.5
-pillow==10.4.0
-platformdirs==4.3.7
-prompt_toolkit==3.0.50
-propcache==0.3.0
-proto-plus==1.26.1
-protobuf==4.25.6
-psutil==7.0.0
-pure_eval==0.2.3
-pyasn1==0.6.1
-pyasn1_modules==0.4.1
-pycparser==2.22
-pydantic==2.10.6
-pydantic_core==2.27.2
-pydub==0.25.1
-pyee==12.0.0
-Pygments==2.19.1
-PyJWT==2.10.1
-pypandoc==1.15
-pyparsing==3.2.1
-pypdf==5.4.0
-pypdfium2==4.30.1
-PyPika==0.48.9
-pypiwin32==223
-pyproject_hooks==1.2.0
-pyreadline3==3.5.4
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-python-iso639==2025.2.18
-python-json-logger==2.0.7
-python-magic==0.4.27
-python-multipart==0.0.20
-pyttsx3==2.98
-pytz==2025.1
-pywin32==310
-PyYAML==6.0.2
-pyzmq==26.4.0
-RapidFuzz==3.12.2
-referencing==0.36.2
-regex==2024.11.6
-requests==2.32.3
-requests-oauthlib==2.0.0
-rich==14.0.0
-rpds-py==0.23.1
-rsa==4.9
-ruff==0.11.4
-safehttpx==0.1.6
-safetensors==0.5.3
-scipy==1.15.2
-semantic-version==2.10.0
-sentencepiece==0.2.0
-sentry-sdk==2.23.1
-shapely==2.0.7
-shellingham==1.5.4
-six==1.17.0
-sniffio==1.3.1
-sounddevice==0.5.1
-soupsieve==2.6
-sqlparse==0.5.3
-stack-data==0.6.3
-starlette==0.46.1
-sympy==1.13.1
-tenacity==8.3.0
-tensorboard==2.15.2
-tensorboard-data-server==0.7.2
-tensorboardX==1.5
-tensorflow-estimator==2.15.0
-tensorflow-io-gcs-filesystem==0.31.0
-termcolor==2.5.0
-threadpoolctl==3.6.0
-tinycss2==1.4.0
-tomli==2.2.1
-tomli_w==1.2.0
-tomlkit==0.13.2
-torch==2.6.0
-tornado==6.4.2
-tqdm==4.67.1
-traitlets==5.14.3
-typer==0.15.2
-typing-inspection==0.4.0
-typing_extensions==4.12.2
-tzdata==2025.1
-urllib3==2.3.0
-uv==0.6.3
-uvicorn==0.34.0
-wcwidth==0.2.13
-webencodings==0.5.1
-websocket-client==1.8.0
-websockets==15.0
-Werkzeug==3.1.3
-wrapt==1.14.1
-xlrd==2.0.1
-XlsxWriter==3.2.2
-yarl==1.18.3
+absl-py==2.2.2
+aiofiles==24.1.0
+aiohappyeyeballs==2.4.6
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.9.0
+appdirs==1.4.4
+asgiref==3.8.1
+asttokens==3.0.0
+astunparse==1.6.3
+attrs==25.1.0
+backcall==0.2.0
+backoff==2.2.1
+bcrypt==4.2.1
+blinker==1.9.0
+cachetools==5.5.2
+certifi==2025.1.31
+cffi==1.17.1
+charset-normalizer==3.4.1
+click==8.1.8
+colorama==0.4.6
+comtypes==1.4.10
+contourpy==1.3.1
+cycler==0.12.1
+decorator==5.2.1
+distro==1.9.0
+Django==5.1.7
+docopt==0.6.2
+docstring_parser==0.16
+durationpy==0.9
+et_xmlfile==2.0.0
+executing==2.2.0
+fastapi==0.115.12
+fastjsonschema==2.21.1
+ffmpy==0.5.0
+filelock==3.17.0
+filetype==1.2.0
+flatbuffers==25.2.10
+fonttools==4.57.0
+frozenlist==1.5.0
+fsspec==2025.2.0
+gast==0.6.0
+google-api-core==2.24.2
+google-auth==2.38.0
+google-auth-oauthlib==1.2.1
+google-cloud-aiplatform==1.85.0
+google-cloud-bigquery==3.30.0
+google-cloud-core==2.4.3
+google-cloud-resource-manager==1.14.2
+google-cloud-storage==2.19.0
+google-crc32c==1.7.0
+google-pasta==0.2.0
+google-resumable-media==2.7.2
+googleapis-common-protos==1.69.2
+gradio==5.24.0
+gradio_client==1.8.0
+groovy==0.1.2
+grpc-google-iam-v1==0.14.2
+grpcio==1.71.0
+grpcio-status==1.71.0
+h11==0.14.0
+h5py==3.13.0
+httpcore==1.0.7
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.30.2
+idna==3.10
+importlib_resources==6.5.2
+jax==0.5.3
+jaxlib==0.5.3
+Jinja2==3.1.5
+jiter==0.8.2
+jmespath==1.0.1
+joblib==1.4.2
+json5==0.10.0
+json_repair==0.39.1
+jsonpath-python==1.0.6
+jsonpickle==4.0.2
+jsonref==1.1.0
+junitparser==3.2.0
+jupyterlab_pygments==0.3.0
+keras==2.15.0
+kiwisolver==1.4.8
+langdetect==1.0.9
+libclang==18.1.1
+lxml==5.3.1
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+matplotlib==3.10.1
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mediapipe==0.10.21
+mistune==3.1.3
+ml_dtypes==0.5.1
+mmh3==5.1.0
+monotonic==1.6
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+namex==0.0.8
+nest-asyncio==1.6.0
+networkx==3.4.2
+numpy==1.26.4
+oauthlib==3.2.2
+olefile==0.47
+omegaconf==2.3.0
+opencv-contrib-python==4.11.0.86
+opencv-python==4.11.0.86
+openpyxl==3.1.5
+opentelemetry-proto==1.31.0
+opentelemetry-util-http==0.52b0
+opt_einsum==3.4.0
+optree==0.15.0
+orjson==3.10.15
+overrides==7.7.0
+packaging==24.2
+pandas==2.2.3
+pandocfilters==1.5.1
+parso==0.8.4
+pickleshare==0.7.5
+pillow==10.4.0
+platformdirs==4.3.7
+prompt_toolkit==3.0.50
+propcache==0.3.0
+proto-plus==1.26.1
+protobuf==4.25.6
+psutil==7.0.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.10.6
+pydantic_core==2.27.2
+pydub==0.25.1
+pyee==12.0.0
+Pygments==2.19.1
+PyJWT==2.10.1
+pypandoc==1.15
+pyparsing==3.2.1
+pypdf==5.4.0
+pypdfium2==4.30.1
+PyPika==0.48.9
+pypiwin32==223
+pyproject_hooks==1.2.0
+pyreadline3==3.5.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-iso639==2025.2.18
+python-json-logger==2.0.7
+python-magic==0.4.27
+python-multipart==0.0.20
+pyttsx3==2.98
+pytz==2025.1
+pywin32==310
+PyYAML==6.0.2
+pyzmq==26.4.0
+RapidFuzz==3.12.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==14.0.0
+rpds-py==0.23.1
+rsa==4.9
+ruff==0.11.4
+safehttpx==0.1.6
+safetensors==0.5.3
+scipy==1.15.2
+semantic-version==2.10.0
+sentencepiece==0.2.0
+sentry-sdk==2.23.1
+shapely==2.0.7
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+sounddevice==0.5.1
+soupsieve==2.6
+sqlparse==0.5.3
+stack-data==0.6.3
+starlette==0.46.1
+sympy==1.13.1
+tenacity==8.3.0
+tensorboard==2.15.2
+tensorboard-data-server==0.7.2
+tensorboardX==1.5
+tensorflow-estimator==2.15.0
+tensorflow-io-gcs-filesystem==0.31.0
+termcolor==2.5.0
+threadpoolctl==3.6.0
+tinycss2==1.4.0
+tomli==2.2.1
+tomli_w==1.2.0
+tomlkit==0.13.2
+torch==2.6.0
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+typer==0.15.2
+typing-inspection==0.4.0
+typing_extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+uv==0.6.3
+uvicorn==0.34.0
+wcwidth==0.2.13
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==15.0
+Werkzeug==3.1.3
+wrapt==1.14.1
+xlrd==2.0.1
+XlsxWriter==3.2.2
+yarl==1.18.3
 zipp==3.21.0