Skip to content

Video class refactor #1947

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 14 commits into
base: develop
Choose a base branch
from
Open

Video class refactor #1947

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
af406c7
starting structure for new video class
timmermansjoy Aug 9, 2025
5beb137
Merge remote-tracking branch 'myfork/video-refactor' into video-refactor
timmermansjoy Aug 9, 2025
b8f820d
fix(pre_commit): 🎨 auto format pre-commit hooks
pre-commit-ci[bot] Aug 9, 2025
505689b
add better deprication warnings
timmermansjoy Aug 13, 2025
15286b1
add ffmpeg (pyav) backend as support
timmermansjoy Aug 13, 2025
bb67f6f
add better depracated warnings
timmermansjoy Aug 13, 2025
fab59ea
format docstrings correctly
timmermansjoy Aug 13, 2025
9561e3d
keep keep naming consistent with pyav
timmermansjoy Aug 14, 2025
a9bf329
add test notebook (will removed later)
timmermansjoy Aug 14, 2025
9bd156d
Merge branch 'video-refactor' of https://github.com/timmermansjoy/sup…
timmermansjoy Aug 14, 2025
83d3b65
fix(pre_commit): 🎨 auto format pre-commit hooks
pre-commit-ci[bot] Aug 14, 2025
375883c
remove answered question
timmermansjoy Aug 14, 2025
f25e3b1
Merge branch 'video-refactor' of https://github.com/timmermansjoy/sup…
timmermansjoy Aug 14, 2025
cb2f265
fix(pre_commit): 🎨 auto format pre-commit hooks
pre-commit-ci[bot] Aug 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
297 changes: 297 additions & 0 deletions Video_Demo_notebook.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,297 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "fb864ed3",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n"
]
}
],
"source": [
"from tqdm import tqdm\n",
"\n",
"import supervision as sv"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "94cbdffa",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Video gemist.mp4 : VideoInfo(width=848, height=480, fps=15, precise_fps=14.955430835259161, total_frames=151) : Backend: opencv>"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"video = sv.Video(\"gemist.mp4\")\n",
"video"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3cd5bbd6",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 151/151 [00:00<00:00, 1929.48it/s]\n"
]
}
],
"source": [
"video = sv.Video(\"gemist.mp4\")\n",
"for frame in tqdm(video):\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "5ca4d68c",
"metadata": {},
"outputs": [],
"source": [
"for frame in sv.Video(\"gemist.mp4\").frames(\n",
" stride=5, start=100, end=500, resolution_wh=(1280, 720)\n",
"):\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "90463868",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Saving video: 151it [00:00, 540.72it/s]\n"
]
}
],
"source": [
"import cv2\n",
"\n",
"\n",
"def blur(frame, i):\n",
" return cv2.GaussianBlur(frame, (11, 11), 0)\n",
"\n",
"\n",
"sv.Video(\"gemist.mp4\").save(\"blurred.mp4\", callback=blur, show_progress=True)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "47382afa",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Saving video: 151it [00:00, 539.70it/s]\n"
]
}
],
"source": [
"sv.Video(\"gemist.mp4\").save(\n",
" \"timelapse.mp4\", fps=60, callback=lambda f, i: f, show_progress=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "11bbe111",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Saving video: 151it [00:00, 625.05it/s]\n"
]
}
],
"source": [
"from supervision import Video, VideoInfo\n",
"\n",
"# Need more elaboration on this\n",
"\n",
"source = Video(\"gemist.mp4\")\n",
"target_info = VideoInfo(width=200, height=600, fps=200)\n",
"\n",
"source.save(\"resized.mp4\", info=target_info, show_progress=True)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "f60323ab",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Video gemist.mp4 : VideoInfo(width=848, height=480, fps=15, precise_fps=14.955430835259161, total_frames=151) : Backend: pyav>"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import supervision as sv\n",
"\n",
"video = sv.Video(\"gemist.mp4\", backend=\"pyav\")\n",
"video"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "de97b6c3",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 151/151 [00:00<00:00, 1969.45it/s]\n"
]
}
],
"source": [
"from tqdm import tqdm\n",
"\n",
"import supervision as sv\n",
"\n",
"video = sv.Video(\"gemist.mp4\", backend=\"pyav\")\n",
"for frame in tqdm(video):\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "726ffd1a",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"13it [00:00, 318.78it/s]\n"
]
}
],
"source": [
"from tqdm import tqdm\n",
"\n",
"import supervision as sv\n",
"\n",
"for frame in tqdm(\n",
" sv.Video(\"gemist.mp4\", backend=\"pyav\").frames(\n",
" stride=5, start=100, end=500, resolution_wh=(1280, 720)\n",
" )\n",
"):\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "0da30fa8",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Saving video: 151it [00:00, 413.05it/s]\n"
]
}
],
"source": [
"def blur(frame, i):\n",
" return cv2.GaussianBlur(frame, (11, 11), 0)\n",
"\n",
"\n",
"sv.Video(\"gemist.mp4\", backend=\"pyav\").save(\n",
" \"blurred_av.mp4\", callback=blur, show_progress=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "ef5fb50e",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Saving video: 151it [00:00, 413.50it/s]\n"
]
}
],
"source": [
"sv.Video(\"gemist.mp4\", backend=\"pyav\").save(\n",
" \"timelapse.mp4\", fps=60, callback=lambda f, i: f, show_progress=True\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a8db8606",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
3 changes: 3 additions & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,9 @@ build = [
"wheel>=0.40,<0.46",
"build>=0.10,<1.3"
]
video = [
"av>=15.0.0"
]

[tool.bandit]
target = ["test", "supervision"]
Expand Down
3 changes: 2 additions & 1 deletion supervision/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,11 +131,11 @@
from supervision.utils.notebook import plot_image, plot_images_grid
from supervision.utils.video import (
FPSMonitor,
VideoInfo,
VideoSink,
get_video_frames_generator,
process_video,
)
from supervision.video.core import Video, VideoInfo

__all__ = [
"LMM",
Expand Down Expand Up @@ -193,6 +193,7 @@
"TriangleAnnotator",
"VertexAnnotator",
"VertexLabelAnnotator",
"Video",
"VideoInfo",
"VideoSink",
"approximate_polygon",
Expand Down
14 changes: 14 additions & 0 deletions supervision/utils/video.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@
import numpy as np
from tqdm.auto import tqdm

from supervision.utils.internal import deprecated


@dataclass
class VideoInfo:
Expand Down Expand Up @@ -60,6 +62,10 @@ def resolution_wh(self) -> tuple[int, int]:
return self.width, self.height


@deprecated(
"VideoSink is deprated and will be removed in a future version. "
"Use `sv.Video(path).save(...)` instead."
)
class VideoSink:
"""
Context manager that saves video frames to a file using OpenCV.
Expand Down Expand Up @@ -141,6 +147,10 @@ def _validate_and_setup_video(
return video, start, end


@deprecated(
"get_video_frames_generator is deprated and will be removed in a future version. "
"Use `sv.Video(source).frames(...)` instead."
)
def get_video_frames_generator(
source_path: str,
stride: int = 1,
Expand Down Expand Up @@ -192,6 +202,10 @@ def get_video_frames_generator(
video.release()


@deprecated(
"get_video_frames_generator is deprated and will be removed in a future version."
"Use `sv.Video(source).save(target, callback=...)` instead."
)
def process_video(
source_path: str,
target_path: str,
Expand Down
4 changes: 4 additions & 0 deletions supervision/video/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
from .core import Video
from .utils import VideoInfo

__all__ = ["Video", "VideoInfo"]
7 changes: 7 additions & 0 deletions supervision/video/backends/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
BACKENDS = {
"opencv": "supervision.video.backends.opencv",
"pyav": "supervision.video.backends.pyav",
}


__all__ = ["BACKENDS"]
Loading