From 13c60a8d48681f420b8f30eb650428bb896db008 Mon Sep 17 00:00:00 2001 From: Honney OC Date: Sun, 13 Sep 2026 19:36:45 +0000 Subject: [PATCH] feat: use lossless FFV1 and PCM for analysis clips --- .gitignore | 224 ++++++++++++++++++++++++++++++++++++++++++++++++++++- extract.py | 29 +++++-- 2 files changed, 245 insertions(+), 8 deletions(-) diff --git a/.gitignore b/.gitignore index 7c9dff2..16ccb8e 100644 --- a/.gitignore +++ b/.gitignore @@ -1,2 +1,224 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[codz] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py.cover +*.lcov +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +# Pipfile.lock + +# UV +# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# uv.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +# poetry.lock +# poetry.toml + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python. +# https://pdm-project.org/en/latest/usage/project/#working-with-version-control +# pdm.lock +# pdm.toml +.pdm-python +.pdm-build/ + +# pixi +# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control. +# pixi.lock +# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one +# in the .venv directory. It is recommended not to include this directory in version control. +.pixi/* +!.pixi/config.toml + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule* +celerybeat.pid + +# Redis +*.rdb +*.aof +*.pid + +# RabbitMQ +mnesia/ +rabbitmq/ +rabbitmq-data/ + +# ActiveMQ +activemq-data/ + +# SageMath parsed files +*.sage.py + +# Environments +.env +.envrc +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +# .idea/ + +# Abstra +# Abstra is an AI-powered process automation framework. +# Ignore directories containing user credentials, local state, and settings. +# Learn more at https://abstra.io/docs +.abstra/ + +# Visual Studio Code +# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore that +# can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore +# and can be added to the global gitignore or merged into this file. However, if you prefer, you +# could uncomment the following to ignore the entire vscode folder +# .vscode/ +# Temporary file for partial code execution +tempCodeRunnerFile.py + +# Ruff stuff: +.ruff_cache/ + +# PyPI configuration file +.pypirc + +# Marimo +marimo/_static/ +marimo/_lsp/ +__marimo__/ + +# Streamlit +.streamlit/secrets.toml + +# Custom extracted/*.mp3 -extracted/*.mkv \ No newline at end of file +extracted/*.mkv diff --git a/extract.py b/extract.py index 2d2183d..5d6c7bd 100644 --- a/extract.py +++ b/extract.py @@ -23,6 +23,22 @@ for input_file in inputs: DURATION = 90 # 1.5 minutes in seconds OUT_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "extracted") +# ─── Analysis-friendly codecs (NOT GPU) ─── +# Video: FFV1 (lossless, intra-only) in MKV. Every frame stands alone, no +# P/B-frame prediction, no blocking artifacts -> exact frames for similarity +# (SSIM/pHash/features) + fast random access. Decoded with -pix_fmt yuv444p +# to avoid 4:2:0 chroma-subsampling noise. +# Audio: PCM float32 WAV, 48 kHz mono. Bit-exact waveform preserves phase for +# cross-correlation / GCC-PHAT. Never MP3/AAC/Opus here (MDCT + padding +# smears transients and shifts correlation peaks). FLAC is the only +# acceptable compressed alternative (lossless). +# GPU (RX 7900 XTX via VAAPI/AMF: h264_vaapi/hevc_vaapi/h264_amf): deliberately +# NOT used. Those encoders are lossy delivery codecs, lower quality per bit, +# inter-frame only, and FFV1/PCM/ProRes/DNxHR have no GPU implementation. +# GPU only makes sense for preview proxies, not for measurement. CPU encode +# of 90 s clips is fast enough and bit-exact. +VIDEO_CODEC = ["-c:v", "ffv1", "-level", "3", "-pix_fmt", "yuv444p"] +AUDIO_CODEC = ["-c:a", "pcm_f32le", "-ar", "48000", "-ac", "1"] # ─── Check ffmpeg ─── if shutil.which(f"ffmpeg") is None: sys.exit(f"ERROR: 'ffmpeg' not found on PATH. Install it and try again.") @@ -34,22 +50,22 @@ for INPUT_FILE in INPUT_FILES: # ─── Derive output filenames ─── stem = os.path.splitext(os.path.basename(INPUT_FILE))[0] - video_out = os.path.join(OUT_DIR, f"{stem}_video.mkv") - audio_out = os.path.join(OUT_DIR, f"{stem}_audio.mp3") + video_out = os.path.join(OUT_DIR, f"{stem}_video.mkv") # FFV1 + audio_out = os.path.join(OUT_DIR, f"{stem}_audio.wav") # PCM f32 print(f"Input : {INPUT_FILE}") print(f"Video → {video_out}") print(f"Audio → {audio_out}") print(f"-" * 50) - # ─── Extract video-only (first 90s, no audio) ─── + # ─── Extract video-only (first 90s, no audio, CPU FFV1 re-encode) ─── cmd_video = [ "ffmpeg", "-y", # overwrite output "-i", INPUT_FILE, "-t", str(DURATION), "-an", # no audio - "-c:v", "copy", # copy video stream (no re-encode = fast + lossless) + *VIDEO_CODEC, # ffv1 lossless intra-only, CPU (no GPU equiv.) video_out ] print(f"[video: {stem}] running ffmpeg…") @@ -58,15 +74,14 @@ for INPUT_FILE in INPUT_FILES: sys.exit(f"ffmpeg (video) failed:\n{r.stderr}") print(f"[video: {stem}] done ✔") - # ─── Extract audio-only (first 90s, no video) ─── + # ─── Extract audio-only (first 90s, no video, CPU PCM re-encode) ─── cmd_audio = [ "ffmpeg", "-y", "-i", INPUT_FILE, "-t", str(DURATION), "-vn", # no video - "-c:a", "libmp3lame", - "-b:a", "192k", # 192 kbps + *AUDIO_CODEC, # pcm_f32le 48kHz mono, CPU (no GPU equiv.) audio_out ] print(f"[audio: {stem}] running ffmpeg…")