beenull/immich
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

chore(ml): memory optimisations (#3934)

Browse source
This commit is contained in:
Mert 2023-08-31 19:30:53 -04:00 committed by GitHub
parent c0a48d7357
commit 41461e0d5d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 122 additions and 107 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
machine-learning/Dockerfile
View file

@ -1,4 +1,4 @@
FROM python:3.11.4-bullseye@sha256:5b401676aff858495a5c9c726c60b8b73fe52833e9e16eccdb59e93d52741727 as builder FROM python:3.11-bookworm as builder
ENV PYTHONDONTWRITEBYTECODE=1 \ ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \ PYTHONUNBUFFERED=1 \
@ -14,9 +14,9 @@ COPY poetry.lock pyproject.toml requirements.txt ./
RUN poetry install --sync --no-interaction --no-ansi --no-root --only main RUN poetry install --sync --no-interaction --no-ansi --no-root --only main
RUN pip install --no-deps -r requirements.txt RUN pip install --no-deps -r requirements.txt
FROM python:3.11.4-slim-bullseye@sha256:91d194f58f50594cda71dcd2e8fdefd90e7ecc57d07823813b67c8521e565dcd FROM python:3.11-slim-bookworm
RUN apt-get update && apt-get install -y --no-install-recommends tini && rm -rf /var/lib/apt/lists/* RUN apt-get update && apt-get install -y --no-install-recommends tini libmimalloc2.0 && rm -rf /var/lib/apt/lists/*
WORKDIR /usr/src/app WORKDIR /usr/src/app
ENV NODE_ENV=production \ ENV NODE_ENV=production \
@ -27,6 +27,7 @@ ENV NODE_ENV=production \
PYTHONPATH=/usr/src PYTHONPATH=/usr/src
COPY --from=builder /opt/venv /opt/venv COPY --from=builder /opt/venv /opt/venv
COPY start.sh log_conf.json ./
COPY app . COPY app .
ENTRYPOINT ["tini", "--"] ENTRYPOINT ["tini", "--"]
CMD ["python", "-m", "app.main"] CMD ["./start.sh"]

19
machine-learning/app/config.py
View file

@ -2,6 +2,7 @@ import logging
import os import os
from pathlib import Path from pathlib import Path
import gunicorn
import starlette import starlette
from pydantic import BaseSettings from pydantic import BaseSettings
from rich.console import Console from rich.console import Console
@ -56,12 +57,14 @@ LOG_LEVELS: dict[str, int] = {
settings = Settings() settings = Settings()
log_settings = LogSettings() log_settings = LogSettings()
console = Console(color_system="standard", no_color=log_settings.no_color)
logging.basicConfig( class CustomRichHandler(RichHandler):
format="%(message)s", def __init__(self) -> None:
handlers=[ console = Console(color_system="standard", no_color=log_settings.no_color)
RichHandler(show_path=False, omit_repeated_times=False, console=console, tracebacks_suppress=[starlette]) super().__init__(
], show_path=False, omit_repeated_times=False, console=console, tracebacks_suppress=[gunicorn, starlette]
) )
log = logging.getLogger("uvicorn")
log = logging.getLogger("gunicorn.access")
log.setLevel(LOG_LEVELS.get(log_settings.log_level.lower(), logging.INFO)) log.setLevel(LOG_LEVELS.get(log_settings.log_level.lower(), logging.INFO))

23
machine-learning/app/main.py
View file

@ -1,11 +1,8 @@
import asyncio import asyncio
import logging
import os
from concurrent.futures import ThreadPoolExecutor from concurrent.futures import ThreadPoolExecutor
from typing import Any from typing import Any
import orjson import orjson
import uvicorn
from fastapi import FastAPI, Form, HTTPException, UploadFile from fastapi import FastAPI, Form, HTTPException, UploadFile
from fastapi.responses import ORJSONResponse from fastapi.responses import ORJSONResponse
from starlette.formparsers import MultiPartParser from starlette.formparsers import MultiPartParser
@ -33,7 +30,7 @@ def init_state() -> None:
) )
) )
# asyncio is a huge bottleneck for performance, so we use a thread pool to run blocking code # asyncio is a huge bottleneck for performance, so we use a thread pool to run blocking code
app.state.thread_pool = ThreadPoolExecutor(settings.request_threads) app.state.thread_pool = ThreadPoolExecutor(settings.request_threads) if settings.request_threads > 0 else None
log.info(f"Initialized request thread pool with {settings.request_threads} threads.") log.info(f"Initialized request thread pool with {settings.request_threads} threads.")
@ -73,17 +70,7 @@ async def predict(
async def run(model: InferenceModel, inputs: Any) -> Any: async def run(model: InferenceModel, inputs: Any) -> Any:
return await asyncio.get_running_loop().run_in_executor(app.state.thread_pool, model.predict, inputs) if app.state.thread_pool is not None:
return await asyncio.get_running_loop().run_in_executor(app.state.thread_pool, model.predict, inputs)
else:
if __name__ == "__main__": return model.predict(inputs)
is_dev = os.getenv("NODE_ENV") == "development"
uvicorn.run(
"app.main:app",
host=settings.host,
port=settings.port,
reload=is_dev,
workers=settings.workers,
log_config=None,
access_log=log.isEnabledFor(logging.INFO),
)

1
machine-learning/app/models/base.py
View file

@ -53,6 +53,7 @@ class InferenceModel(ABC):
log.debug(f"Setting intra_op_num_threads to {intra_op_num_threads}") log.debug(f"Setting intra_op_num_threads to {intra_op_num_threads}")
self.sess_options.inter_op_num_threads = inter_op_num_threads self.sess_options.inter_op_num_threads = inter_op_num_threads
self.sess_options.intra_op_num_threads = intra_op_num_threads self.sess_options.intra_op_num_threads = intra_op_num_threads
self.sess_options.enable_cpu_mem_arena = False
try: try:
loader(**model_kwargs) loader(**model_kwargs)

17
machine-learning/log_conf.json Normal file
View file

@ -0,0 +1,17 @@
{
"version": 1,
"disable_existing_loggers": true,
"formatters": { "rich": { "show_path": false, "omit_repeated_times": false } },
"handlers": {
"console": {
"class": "app.config.CustomRichHandler",
"formatter": "rich",
"level": "INFO"
}
},
"loggers": {
"gunicorn.access": { "propagate": true },
"gunicorn.error": { "propagate": true }
},
"root": { "handlers": ["console"] }
}

144
machine-learning/poetry.lock generated
View file

@ -164,13 +164,13 @@ tests = ["pytest"]
[[package]] [[package]]
name = "anyio" name = "anyio"
version = "3.7.1" version = "4.0.0"
description = "High level compatibility layer for multiple asynchronous event loop implementations" description = "High level compatibility layer for multiple asynchronous event loop implementations"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "anyio-3.7.1-py3-none-any.whl", hash = "sha256:91dee416e570e92c64041bd18b900d1d6fa78dff7048769ce5ac5ddad004fbb5"}, {file = "anyio-4.0.0-py3-none-any.whl", hash = "sha256:cfdb2b588b9fc25ede96d8db56ed50848b0b649dca3dd1df0b11f683bb9e0b5f"},
{file = "anyio-3.7.1.tar.gz", hash = "sha256:44a3c9aba0f5defa43261a8b3efb97891f2bd7d804e0e1f56419befa1adfc780"}, {file = "anyio-4.0.0.tar.gz", hash = "sha256:f7ed51751b2c2add651e5747c891b47e26d2a21be5d32d9311dfe9692f3e5d7a"},
] ]
[package.dependencies] [package.dependencies]
@ -178,9 +178,9 @@ idna = ">=2.8"
sniffio = ">=1.1" sniffio = ">=1.1"
[package.extras] [package.extras]
doc = ["Sphinx", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme (>=1.2.2)", "sphinxcontrib-jquery"] doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)"]
test = ["anyio[trio]", "coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "mock (>=4)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"] test = ["anyio[trio]", "coverage[toml] (>=7)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
trio = ["trio (<0.22)"] trio = ["trio (>=0.22)"]
[[package]] [[package]]
name = "async-timeout" name = "async-timeout"
@ -874,18 +874,18 @@ test = ["anyio[trio] (>=3.2.1,<4.0.0)", "black (==23.1.0)", "coverage[toml] (>=6
[[package]] [[package]]
name = "filelock" name = "filelock"
version = "3.12.2" version = "3.12.3"
description = "A platform independent file lock." description = "A platform independent file lock."
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "filelock-3.12.2-py3-none-any.whl", hash = "sha256:cbb791cdea2a72f23da6ac5b5269ab0a0d161e9ef0100e653b69049a7706d1ec"}, {file = "filelock-3.12.3-py3-none-any.whl", hash = "sha256:f067e40ccc40f2b48395a80fcbd4728262fab54e232e090a4063ab804179efeb"},
{file = "filelock-3.12.2.tar.gz", hash = "sha256:002740518d8aa59a26b0c76e10fb8c6e15eae825d34b6fdf670333fd7b938d81"}, {file = "filelock-3.12.3.tar.gz", hash = "sha256:0ecc1dd2ec4672a10c8550a8182f1bd0c0a5088470ecd5a125e45f49472fac3d"},
] ]
[package.extras] [package.extras]
docs = ["furo (>=2023.5.20)", "sphinx (>=7.0.1)", "sphinx-autodoc-typehints (>=1.23,!=1.23.4)"] docs = ["furo (>=2023.7.26)", "sphinx (>=7.1.2)", "sphinx-autodoc-typehints (>=1.24)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "diff-cover (>=7.5)", "pytest (>=7.3.1)", "pytest-cov (>=4.1)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"] testing = ["covdefaults (>=2.3)", "coverage (>=7.3)", "diff-cover (>=7.7)", "pytest (>=7.4)", "pytest-cov (>=4.1)", "pytest-mock (>=3.11.1)", "pytest-timeout (>=2.1)"]
[[package]] [[package]]
name = "flask" name = "flask"
@ -1453,17 +1453,17 @@ test = ["objgraph", "psutil"]
[[package]] [[package]]
name = "gunicorn" name = "gunicorn"
version = "20.1.0" version = "21.2.0"
description = "WSGI HTTP Server for UNIX" description = "WSGI HTTP Server for UNIX"
optional = false optional = false
python-versions = ">=3.5" python-versions = ">=3.5"
files = [ files = [
{file = "gunicorn-20.1.0-py3-none-any.whl", hash = "sha256:9dcc4547dbb1cb284accfb15ab5667a0e5d1881cc443e0677b4882a4067a807e"}, {file = "gunicorn-21.2.0-py3-none-any.whl", hash = "sha256:3213aa5e8c24949e792bcacfc176fef362e7aac80b76c56f6b5122bf350722f0"},
{file = "gunicorn-20.1.0.tar.gz", hash = "sha256:e0a968b5ba15f8a328fdfd7ab1fcb5af4470c28aaf7e55df02a99bc13138e6e8"}, {file = "gunicorn-21.2.0.tar.gz", hash = "sha256:88ec8bff1d634f98e61b9f65bc4bf3cd918a90806c6f5c48bc5603849ec81033"},
] ]
[package.dependencies] [package.dependencies]
setuptools = ">=3.0" packaging = "*"
[package.extras] [package.extras]
eventlet = ["eventlet (>=0.24.1)"] eventlet = ["eventlet (>=0.24.1)"]
@ -2619,69 +2619,61 @@ files = [
[[package]] [[package]]
name = "pandas" name = "pandas"
version = "2.0.3" version = "2.1.0"
description = "Powerful data structures for data analysis, time series, and statistics" description = "Powerful data structures for data analysis, time series, and statistics"
optional = false optional = false
python-versions = ">=3.8" python-versions = ">=3.9"
files = [ files = [
{file = "pandas-2.0.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e4c7c9f27a4185304c7caf96dc7d91bc60bc162221152de697c98eb0b2648dd8"}, {file = "pandas-2.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:40dd20439ff94f1b2ed55b393ecee9cb6f3b08104c2c40b0cb7186a2f0046242"},
{file = "pandas-2.0.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f167beed68918d62bffb6ec64f2e1d8a7d297a038f86d4aed056b9493fca407f"}, {file = "pandas-2.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d4f38e4fedeba580285eaac7ede4f686c6701a9e618d8a857b138a126d067f2f"},
{file = "pandas-2.0.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ce0c6f76a0f1ba361551f3e6dceaff06bde7514a374aa43e33b588ec10420183"}, {file = "pandas-2.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e6a0fe052cf27ceb29be9429428b4918f3740e37ff185658f40d8702f0b3e09"},
{file = "pandas-2.0.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba619e410a21d8c387a1ea6e8a0e49bb42216474436245718d7f2e88a2f8d7c0"}, {file = "pandas-2.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d81e1813191070440d4c7a413cb673052b3b4a984ffd86b8dd468c45742d3cc"},
{file = "pandas-2.0.3-cp310-cp310-win32.whl", hash = "sha256:3ef285093b4fe5058eefd756100a367f27029913760773c8bf1d2d8bebe5d210"}, {file = "pandas-2.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:eb20252720b1cc1b7d0b2879ffc7e0542dd568f24d7c4b2347cb035206936421"},
{file = "pandas-2.0.3-cp310-cp310-win_amd64.whl", hash = "sha256:9ee1a69328d5c36c98d8e74db06f4ad518a1840e8ccb94a4ba86920986bb617e"}, {file = "pandas-2.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:38f74ef7ebc0ffb43b3d633e23d74882bce7e27bfa09607f3c5d3e03ffd9a4a5"},
{file = "pandas-2.0.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b084b91d8d66ab19f5bb3256cbd5ea661848338301940e17f4492b2ce0801fe8"}, {file = "pandas-2.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cda72cc8c4761c8f1d97b169661f23a86b16fdb240bdc341173aee17e4d6cedd"},
{file = "pandas-2.0.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:37673e3bdf1551b95bf5d4ce372b37770f9529743d2498032439371fc7b7eb26"}, {file = "pandas-2.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d97daeac0db8c993420b10da4f5f5b39b01fc9ca689a17844e07c0a35ac96b4b"},
{file = "pandas-2.0.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9cb1e14fdb546396b7e1b923ffaeeac24e4cedd14266c3497216dd4448e4f2d"}, {file = "pandas-2.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8c58b1113892e0c8078f006a167cc210a92bdae23322bb4614f2f0b7a4b510f"},
{file = "pandas-2.0.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9cd88488cceb7635aebb84809d087468eb33551097d600c6dad13602029c2df"}, {file = "pandas-2.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:629124923bcf798965b054a540f9ccdfd60f71361255c81fa1ecd94a904b9dd3"},
{file = "pandas-2.0.3-cp311-cp311-win32.whl", hash = "sha256:694888a81198786f0e164ee3a581df7d505024fbb1f15202fc7db88a71d84ebd"}, {file = "pandas-2.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:70cf866af3ab346a10debba8ea78077cf3a8cd14bd5e4bed3d41555a3280041c"},
{file = "pandas-2.0.3-cp311-cp311-win_amd64.whl", hash = "sha256:6a21ab5c89dcbd57f78d0ae16630b090eec626360085a4148693def5452d8a6b"}, {file = "pandas-2.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:d53c8c1001f6a192ff1de1efe03b31a423d0eee2e9e855e69d004308e046e694"},
{file = "pandas-2.0.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:9e4da0d45e7f34c069fe4d522359df7d23badf83abc1d1cef398895822d11061"}, {file = "pandas-2.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:86f100b3876b8c6d1a2c66207288ead435dc71041ee4aea789e55ef0e06408cb"},
{file = "pandas-2.0.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:32fca2ee1b0d93dd71d979726b12b61faa06aeb93cf77468776287f41ff8fdc5"}, {file = "pandas-2.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:28f330845ad21c11db51e02d8d69acc9035edfd1116926ff7245c7215db57957"},
{file = "pandas-2.0.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:258d3624b3ae734490e4d63c430256e716f488c4fcb7c8e9bde2d3aa46c29089"}, {file = "pandas-2.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9a6ccf0963db88f9b12df6720e55f337447aea217f426a22d71f4213a3099a6"},
{file = "pandas-2.0.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9eae3dc34fa1aa7772dd3fc60270d13ced7346fcbcfee017d3132ec625e23bb0"}, {file = "pandas-2.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d99e678180bc59b0c9443314297bddce4ad35727a1a2656dbe585fd78710b3b9"},
{file = "pandas-2.0.3-cp38-cp38-win32.whl", hash = "sha256:f3421a7afb1a43f7e38e82e844e2bca9a6d793d66c1a7f9f0ff39a795bbc5e02"}, {file = "pandas-2.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b31da36d376d50a1a492efb18097b9101bdbd8b3fbb3f49006e02d4495d4c644"},
{file = "pandas-2.0.3-cp38-cp38-win_amd64.whl", hash = "sha256:69d7f3884c95da3a31ef82b7618af5710dba95bb885ffab339aad925c3e8ce78"}, {file = "pandas-2.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:0164b85937707ec7f70b34a6c3a578dbf0f50787f910f21ca3b26a7fd3363437"},
{file = "pandas-2.0.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5247fb1ba347c1261cbbf0fcfba4a3121fbb4029d95d9ef4dc45406620b25c8b"}, {file = "pandas-2.1.0.tar.gz", hash = "sha256:62c24c7fc59e42b775ce0679cfa7b14a5f9bfb7643cfbe708c960699e05fb918"},
{file = "pandas-2.0.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:81af086f4543c9d8bb128328b5d32e9986e0c84d3ee673a2ac6fb57fd14f755e"},
{file = "pandas-2.0.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1994c789bf12a7c5098277fb43836ce090f1073858c10f9220998ac74f37c69b"},
{file = "pandas-2.0.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ec591c48e29226bcbb316e0c1e9423622bc7a4eaf1ef7c3c9fa1a3981f89641"},
{file = "pandas-2.0.3-cp39-cp39-win32.whl", hash = "sha256:04dbdbaf2e4d46ca8da896e1805bc04eb85caa9a82e259e8eed00254d5e0c682"},
{file = "pandas-2.0.3-cp39-cp39-win_amd64.whl", hash = "sha256:1168574b036cd8b93abc746171c9b4f1b83467438a5e45909fed645cf8692dbc"},
{file = "pandas-2.0.3.tar.gz", hash = "sha256:c02f372a88e0d17f36d3093a644c73cfc1788e876a7c4bcb4020a77512e2043c"},
] ]
[package.dependencies] [package.dependencies]
numpy = [ numpy = {version = ">=1.23.2", markers = "python_version >= \"3.11\""}
{version = ">=1.21.0", markers = "python_version >= \"3.10\""},
{version = ">=1.23.2", markers = "python_version >= \"3.11\""},
]
python-dateutil = ">=2.8.2" python-dateutil = ">=2.8.2"
pytz = ">=2020.1" pytz = ">=2020.1"
tzdata = ">=2022.1" tzdata = ">=2022.1"
[package.extras] [package.extras]
all = ["PyQt5 (>=5.15.1)", "SQLAlchemy (>=1.4.16)", "beautifulsoup4 (>=4.9.3)", "bottleneck (>=1.3.2)", "brotlipy (>=0.7.0)", "fastparquet (>=0.6.3)", "fsspec (>=2021.07.0)", "gcsfs (>=2021.07.0)", "html5lib (>=1.1)", "hypothesis (>=6.34.2)", "jinja2 (>=3.0.0)", "lxml (>=4.6.3)", "matplotlib (>=3.6.1)", "numba (>=0.53.1)", "numexpr (>=2.7.3)", "odfpy (>=1.4.1)", "openpyxl (>=3.0.7)", "pandas-gbq (>=0.15.0)", "psycopg2 (>=2.8.6)", "pyarrow (>=7.0.0)", "pymysql (>=1.0.2)", "pyreadstat (>=1.1.2)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)", "python-snappy (>=0.6.0)", "pyxlsb (>=1.0.8)", "qtpy (>=2.2.0)", "s3fs (>=2021.08.0)", "scipy (>=1.7.1)", "tables (>=3.6.1)", "tabulate (>=0.8.9)", "xarray (>=0.21.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=1.4.3)", "zstandard (>=0.15.2)"] all = ["PyQt5 (>=5.15.6)", "SQLAlchemy (>=1.4.36)", "beautifulsoup4 (>=4.11.1)", "bottleneck (>=1.3.4)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=0.8.1)", "fsspec (>=2022.05.0)", "gcsfs (>=2022.05.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.8.0)", "matplotlib (>=3.6.1)", "numba (>=0.55.2)", "numexpr (>=2.8.0)", "odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pandas-gbq (>=0.17.5)", "psycopg2 (>=2.9.3)", "pyarrow (>=7.0.0)", "pymysql (>=1.0.2)", "pyreadstat (>=1.1.5)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)", "pyxlsb (>=1.0.9)", "qtpy (>=2.2.0)", "s3fs (>=2022.05.0)", "scipy (>=1.8.1)", "tables (>=3.7.0)", "tabulate (>=0.8.10)", "xarray (>=2022.03.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)", "zstandard (>=0.17.0)"]
aws = ["s3fs (>=2021.08.0)"] aws = ["s3fs (>=2022.05.0)"]
clipboard = ["PyQt5 (>=5.15.1)", "qtpy (>=2.2.0)"] clipboard = ["PyQt5 (>=5.15.6)", "qtpy (>=2.2.0)"]
compression = ["brotlipy (>=0.7.0)", "python-snappy (>=0.6.0)", "zstandard (>=0.15.2)"] compression = ["zstandard (>=0.17.0)"]
computation = ["scipy (>=1.7.1)", "xarray (>=0.21.0)"] computation = ["scipy (>=1.8.1)", "xarray (>=2022.03.0)"]
excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.0.7)", "pyxlsb (>=1.0.8)", "xlrd (>=2.0.1)", "xlsxwriter (>=1.4.3)"] consortium-standard = ["dataframe-api-compat (>=0.1.7)"]
excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pyxlsb (>=1.0.9)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)"]
feather = ["pyarrow (>=7.0.0)"] feather = ["pyarrow (>=7.0.0)"]
fss = ["fsspec (>=2021.07.0)"] fss = ["fsspec (>=2022.05.0)"]
gcp = ["gcsfs (>=2021.07.0)", "pandas-gbq (>=0.15.0)"] gcp = ["gcsfs (>=2022.05.0)", "pandas-gbq (>=0.17.5)"]
hdf5 = ["tables (>=3.6.1)"] hdf5 = ["tables (>=3.7.0)"]
html = ["beautifulsoup4 (>=4.9.3)", "html5lib (>=1.1)", "lxml (>=4.6.3)"] html = ["beautifulsoup4 (>=4.11.1)", "html5lib (>=1.1)", "lxml (>=4.8.0)"]
mysql = ["SQLAlchemy (>=1.4.16)", "pymysql (>=1.0.2)"] mysql = ["SQLAlchemy (>=1.4.36)", "pymysql (>=1.0.2)"]
output-formatting = ["jinja2 (>=3.0.0)", "tabulate (>=0.8.9)"] output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.8.10)"]
parquet = ["pyarrow (>=7.0.0)"] parquet = ["pyarrow (>=7.0.0)"]
performance = ["bottleneck (>=1.3.2)", "numba (>=0.53.1)", "numexpr (>=2.7.1)"] performance = ["bottleneck (>=1.3.4)", "numba (>=0.55.2)", "numexpr (>=2.8.0)"]
plot = ["matplotlib (>=3.6.1)"] plot = ["matplotlib (>=3.6.1)"]
postgresql = ["SQLAlchemy (>=1.4.16)", "psycopg2 (>=2.8.6)"] postgresql = ["SQLAlchemy (>=1.4.36)", "psycopg2 (>=2.9.3)"]
spss = ["pyreadstat (>=1.1.2)"] spss = ["pyreadstat (>=1.1.5)"]
sql-other = ["SQLAlchemy (>=1.4.16)"] sql-other = ["SQLAlchemy (>=1.4.36)"]
test = ["hypothesis (>=6.34.2)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"] test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"]
xml = ["lxml (>=4.6.3)"] xml = ["lxml (>=4.8.0)"]
[[package]] [[package]]
name = "pathspec" name = "pathspec"
@ -3877,13 +3869,13 @@ files = [
[[package]] [[package]]
name = "tifffile" name = "tifffile"
version = "2023.8.25" version = "2023.8.30"
description = "Read and write TIFF files" description = "Read and write TIFF files"
optional = false optional = false
python-versions = ">=3.9" python-versions = ">=3.9"
files = [ files = [
{file = "tifffile-2023.8.25-py3-none-any.whl", hash = "sha256:40318485b59e9acb62e7139f22bd46e6760f92daea562b79900bfce3ee2613b7"}, {file = "tifffile-2023.8.30-py3-none-any.whl", hash = "sha256:62364eef35a6fdcc7bc2ad6f97dd270f577efb01b31260ff800af76a66c1e145"},
{file = "tifffile-2023.8.25.tar.gz", hash = "sha256:0a3ebcdfe71eb61a487dd22eaf21ed8962c511e6eb692153c7ac15f81798dfa4"}, {file = "tifffile-2023.8.30.tar.gz", hash = "sha256:6a8c53b012a286b75d09a1498ab32f202f24cc6270a105b5d5911dc4426f162a"},
] ]
[package.dependencies] [package.dependencies]
@ -3894,13 +3886,13 @@ all = ["defusedxml", "fsspec", "imagecodecs (>=2023.8.12)", "lxml", "matplotlib"
[[package]] [[package]]
name = "timm" name = "timm"
version = "0.9.5" version = "0.9.6"
description = "PyTorch Image Models" description = "PyTorch Image Models"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "timm-0.9.5-py3-none-any.whl", hash = "sha256:6e70af3a347bddb4167db46c3252a83c59165332ecf6b3df480d49c22866fa46"}, {file = "timm-0.9.6-py3-none-any.whl", hash = "sha256:7549a924b86a6151d4083a880c27ae86ce729e1b5c8c6099657217d0a0526a4e"},
{file = "timm-0.9.5.tar.gz", hash = "sha256:669835f0030cfb2412c464b7b563bb240d4d41a141226afbbf1b457e4f18cff1"}, {file = "timm-0.9.6.tar.gz", hash = "sha256:6c3c0451b69431de0290eed5662e66b134caf916f1cb9b4aa3b9a13c3d61fd03"},
] ]
[package.dependencies] [package.dependencies]
@ -4126,13 +4118,13 @@ telegram = ["requests"]
[[package]] [[package]]
name = "transformers" name = "transformers"
version = "4.32.0" version = "4.32.1"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
optional = false optional = false
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = [
{file = "transformers-4.32.0-py3-none-any.whl", hash = "sha256:32d8adf0ed76285508e7fd66657b4448ec1f882599ae6bf6f9c36bd7bf798402"}, {file = "transformers-4.32.1-py3-none-any.whl", hash = "sha256:b930d3dbd907a3f300cf49e54d63a56f8a0ab16b01a2c2a61ecff37c6de1da08"},
{file = "transformers-4.32.0.tar.gz", hash = "sha256:ca510f9688d2fe7347abbbfbd13f2f6dcd3c8349870c8d0ed98beed5f579b354"}, {file = "transformers-4.32.1.tar.gz", hash = "sha256:1edc8ae1de357d97c3d36b04412aa63d55e6fc0c4b39b419a7d380ed947d2252"},
] ]
[package.dependencies] [package.dependencies]
@ -4693,4 +4685,4 @@ testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = "^3.11" python-versions = "^3.11"
content-hash = "6d200d3ea1ccf9fb89f44043e3e0845e70f19aac374b96227559375f44508dc5" content-hash = "4e97a32e7525cfedbf23892b8c1191b3fe7b4d09b9f043cdb285ed9772862d67"

3
machine-learning/pyproject.toml
View file

@ -33,13 +33,13 @@ open-clip-torch = "^2.20.0"
python-multipart = "^0.0.6" python-multipart = "^0.0.6"
orjson = "^3.9.5" orjson = "^3.9.5"
safetensors = "0.3.2" safetensors = "0.3.2"
gunicorn = "^21.1.0"
[tool.poetry.group.dev.dependencies] [tool.poetry.group.dev.dependencies]
mypy = "^1.3.0" mypy = "^1.3.0"
black = "^23.3.0" black = "^23.3.0"
pytest = "^7.3.1" pytest = "^7.3.1"
locust = "^2.15.1" locust = "^2.15.1"
gunicorn = "^20.1.0"
httpx = "^0.24.1" httpx = "^0.24.1"
pytest-asyncio = "^0.21.0" pytest-asyncio = "^0.21.0"
pytest-cov = "^4.1.0" pytest-cov = "^4.1.0"
@ -74,6 +74,7 @@ warn_untyped_fields = true
module = [ module = [
"huggingface_hub", "huggingface_hub",
"transformers", "transformers",
"gunicorn",
"cv2", "cv2",
"insightface.model_zoo", "insightface.model_zoo",
"insightface.utils.face_align", "insightface.utils.face_align",

13
machine-learning/start.sh Executable file
View file

@ -0,0 +1,13 @@
#!/usr/bin/env sh
export LD_PRELOAD="/usr/lib/$(arch)-linux-gnu/libmimalloc.so.2"
: "${MACHINE_LEARNING_HOST:=0.0.0.0}"
: "${MACHINE_LEARNING_PORT:=3003}"
: "${MACHINE_LEARNING_WORKERS:=1}"
gunicorn app.main:app \
-k uvicorn.workers.UvicornWorker \
-w $MACHINE_LEARNING_WORKERS \
-b $MACHINE_LEARNING_HOST:$MACHINE_LEARNING_PORT \
--log-config-json log_conf.json