2e62c7b417
refactor: node_env => immich_env ( #9561 )
2024-05-17 13:30:05 -04:00
5583635947
chore(deps): update python:3.11-bookworm docker digest to 96de1ea ( #9490 )
2024-05-14 19:13:56 +00:00
77b8c2f330
chore(deps): update machine-learning ( #9478 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-05-14 10:57:15 -04:00
c1636ef7ab
chore(deps): update machine-learning ( #9168 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-04-30 02:24:09 +00:00
1bca1b8bde
fix(deps): update machine-learning ( #8646 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-04-11 01:38:30 -04:00
e2d5a8c0bb
fix(deps): update machine-learning ( #8280 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-03-31 06:05:18 +00:00
3a045b33ca
chore(deps): update onnxruntime-openvino ( #7854 )
2024-03-16 00:04:45 -04:00
eea0a98090
chore(deps): update machine-learning ( #7890 )
2024-03-15 17:19:28 -04:00
4c0bb2308c
fix(deps): update machine-learning ( #7634 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-03-06 00:24:33 -05:00
8ce18b3403
feat(machine-learning): support cuda 12 ( #7569 )
...
* feat: support cuda12
* fix: group optional
* move to cuda 12
* pr feedback
2024-03-02 23:36:16 -05:00
3cfe2dd31f
chore(deps): update machine-learning ( #7084 )
2024-02-13 16:04:40 +00:00
a0159251d9
chore(deps): update machine-learning ( #7074 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-02-13 09:02:32 -05:00
bfba81de94
chore(deps): update machine-learning ( #6931 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-02-12 21:08:17 -05:00
49c378d706
fix(ml): re-enable ARMNN integration ( #7053 )
2024-02-12 13:29:55 -05:00
871d0c725f
chore(deps): pin dependencies ( #6436 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2024-01-22 11:08:00 -05:00
95cfe22866
feat(ml)!: cuda and openvino acceleration ( #5619 )
...
* cuda and openvino ep, refactor, update dockerfile
* updated workflow
* typing fixes
* added tests
* updated ml test gh action
* updated README
* updated docker-compose
* added compute to hwaccel.yml
* updated gh matrix
updated gh matrix
updated gh matrix
updated gh matrix
updated gh matrix
give up
* remove cuda/arm64 build
* add hwaccel image tags to docker-compose
* remove unnecessary quotes
* add suffix to git tag
* fixed kwargs in base model
* armnn ld_library_path
* update pyproject.toml
* add armnn workflow
* formatting
* consolidate hwaccel files, update docker compose
* update hw transcoding docs
* add ml hwaccel docs
* update dev and prod docker-compose
* added armnn prerequisite docs
* support 3.10
* updated docker-compose comments
* formatting
* test coverage
* don't set arena extend strategy for openvino
* working openvino
* formatting
* fix dockerfile
* added type annotation
* add wsl configuration for openvino
* updated lock file
* copy python3
* comment out extends section
* fix platforms
* simplify workflow suffix tagging
* simplify aio transcoding doc
* update docs and workflow for `hwaccel.yml` change
* revert docs
2024-01-21 18:22:39 -05:00
20be42cec0
chore(deps): update machine-learning ( #6302 )
...
* chore(deps): update machine-learning
* fix typing, use new lifespan syntax
* wrap in try / finally
* move log
---------
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com >
2024-01-13 05:00:09 +00:00
753292956e
feat(ml): ARMNN acceleration ( #5667 )
...
* feat(ml): ARMNN acceleration for CLIP
* wrap ANN as ONNX-Session
* strict typing
* normalize ARMNN CLIP embedding
* mutex to handle concurrent execution
* make inputs contiguous
* fine-grained locking; concurrent network execution
---------
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com >
2024-01-11 18:26:46 +01:00
3edc87f684
fix(deps): update machine-learning ( #5180 )
...
* fix(deps): update machine-learning
* updated ruff command
* use isinstance
---------
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com >
2023-12-25 22:37:48 -05:00
09402eb6d0
fix(ml): disable core dumps ( #5770 )
...
* update dockerfile
* remove sysctl line
2023-12-16 20:30:29 -06:00
d2ad01cd2f
chore(deps): update python:3.11-slim-bookworm docker digest to cfd7ed5 ( #5572 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-09 21:15:15 -06:00
56aed8246d
chore(deps): update python:3.11-slim-bookworm docker digest to cc75851 ( #5462 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-04 13:26:41 -06:00
6959cf689b
chore(deps): update python:3.11-bookworm docker digest to ba7a7ac ( #5438 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-02 18:35:23 +00:00
cbdcbd3ab4
chore(deps): update python:3.11-slim-bookworm docker digest to 8f82989 ( #5435 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 20:24:50 +00:00
cb00d45e3d
chore(deps): update python:3.11-bookworm docker digest to 47c1829 ( #5434 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 20:13:23 +00:00
40964187bb
chore(deps): update python:3.11-slim-bookworm docker digest to 23f5220 ( #5388 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 18:36:54 +00:00
fe3d951f26
chore(deps): update python:3.11-bookworm docker digest to c56b0c6 ( #5387 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-12-01 18:36:30 +00:00
1fa5e220a1
chore(deps): pin dependencies ( #5367 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-11-29 02:09:11 +00:00
87a0ba3db3
feat(ml): export clip models to ONNX and host models on Hugging Face ( #4700 )
...
* export clip models
* export to hf
refactored export code
* export mclip, general refactoring
cleanup
* updated conda deps
* do transforms with pillow and numpy, add tokenization config to export, general refactoring
* moved conda dockerfile, re-added poetry
* minor fixes
* updated link
* updated tests
* removed `requirements.txt` from workflow
* fixed mimalloc path
* removed torchvision
* cleaner np typing
* review suggestions
* update default model name
* update test
2023-10-31 05:02:04 -05:00
41461e0d5d
chore(ml): memory optimisations ( #3934 )
2023-08-31 18:30:53 -05:00
165b91b068
feat(ml)!: switch image classification and CLIP models to ONNX ( #3809 )
2023-08-25 06:28:51 +02:00
bc885f3644
fix(server): properly handle SIGTERM ( #3350 )
...
* use tini init
* Move python into CMD
* Use tini as entrypoint
* Toggle executable bit
* Avoid compose changes
* Adapt web entrypoint
2023-07-21 09:20:04 -05:00
a2f5674bbb
refactor(ml): modularization and styling ( #2835 )
...
* basic refactor and styling
* removed batching
* module entrypoint
* removed unused imports
* model superclass, model cache now in app state
* fixed cache dir and enforced abstract method
---------
Co-authored-by: Alex Tran <alex.tran1502@gmail.com >
2023-06-24 22:18:09 -05:00
0909335d02
chore(deps): update python:3.11.4-slim-bullseye docker digest to 91d194f ( #2797 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-06-16 11:38:59 -05:00
827e4b5f75
chore(deps): update python:3.11.4-bullseye docker digest to 5b40167 ( #2796 )
...
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2023-06-16 11:17:23 -05:00
16171eee8d
pin image digests ( #2754 )
...
Manifest list digests can be found with:
```sh
docker buildx imagetools inspect python:3.11.4-bullseye
docker buildx imagetools inspect python:3.11.4-slim-bullseye
docker buildx imagetools inspect ghcr.io/nginxinc/nginx-unprivileged:1.25.0-alpine3.17
```
The node images are pinned in #2736
Fixes #2751
Partially fixes #2752
2023-06-16 10:28:41 -05:00
1e748864c5
chore(ml): updated dockerfile, added typing, packaging ( #2642 )
...
* updated dockerfile, added typing, packaging
apply env change
* added arm64 support
* added ml version pump, second try for arm64
* added linting config to pyproject.toml
* renamed ml input field
* fixed linter config
* fixed dev docker compose
2023-06-05 09:40:48 -05:00
93863b0629
feat: facial recognition ( #2180 )
2023-05-17 12:07:17 -05:00
8cc9b08c06
chore(ml): use official pytorch channel ( #2416 )
2023-05-10 07:09:33 -05:00
b6b9f51bd7
chore(ml): Fix entrypoint path ( #2373 )
2023-05-03 14:27:35 -05:00
7e965cb6d4
chore(ml): move to fastAPI ( #2336 )
2023-04-26 05:39:24 -05:00
2dcccb37a0
chore(docker): Default NODE_ENV to production for server image and update alpine version ( #2157 )
...
* default NODE_ENV to production for server image
* update node image to use 3.17 alpine in server
* update web docker image to use alpine 3.17
* remove NODE_ENV from production docker-compose
* NODE_ENV is also needed default in machine-learning
2023-04-03 15:05:29 -05:00
d5d0624311
Feat/ml image optimisations ( #1916 )
...
* Use multi stage build to slim down ML image size
* Use gunicorn as WSGI server in ML image
* Configure gunicorn server for ML use case
* Use requirements.txt file to install python dependencies in ML image
* Make ML listen IP configurable
* Revert "Use requirements.txt file to install python dependencies in ML image"
This reverts commit 32e706c7f3db1d0aa1a66b3733ab9ec9dfb86534.
* Separate out pip installs in ML builder image
2023-03-03 16:45:20 -06:00
1cc184ed10
Revert "feat(server): Machine learning's image optimisations ( #1908 )" ( #1915 )
...
This reverts commit 977740045a
2023-03-01 11:48:35 -06:00
977740045a
feat(server): Machine learning's image optimisations ( #1908 )
...
* Use multi stage build to slim down ML image size
* Use gunicorn as WSGI server in ML image
* Configure gunicorn server for ML use case
* Use requirements.txt file to install python dependencies in ML image
* Make ML listen IP configurable
2023-03-01 09:37:12 -06:00
ab90b01122
feat(server) Enable ML support for ARM CPUs ( #1880 )
...
* Install nightly release of pytorch to enable ML support for arm CPUs
* Remove linux/arm/v7 from ML docker builds
* Add --no-cache-dir to torch installation command in ML image build
* Use PIP_NO_CACHE_DIR option in ML build to further decrease image size
2023-02-26 15:00:09 -06:00
b00631d186
fix(machine-learning): Add the command to execute at startup ( #1843 )
...
* fix(machine-learning): Add the command to execute at startup
Previously it wasn't set in the Docker container but it should be.
* fix(docker): remove machine-learning command arg
* fix(docker): machine-learning CMD argument
2023-02-23 09:54:04 -06:00
a3b9a0be3a
fix(server): Flask not found ( #1830 )
...
* fix(server): Flask not found
* trial 1
2023-02-22 10:53:59 -06:00
57136e48fb
feat(machine-learning)!: move machine learning to Python based image ( #1774 )
...
BREAKING CHANGES
* Users have to update the docker-compose file, machine-learning portion.
* Temporary dropping machine-learning support for Arm64 and Armv7
2023-02-18 09:13:37 -06:00
43da8c2a72
chore: reduce docker image size ( #1523 )
...
* chore: remove @tensorflow/tfjs-node-gpu as it is unused
* chore: remove ffmpeg from machine-learning docker image
* chore: remove unneeded dependencies + move dev dependencies in server
* chore: reduce server image size
* chore: machine-learning remove extraneous dependencies
* chore: web remove extraneous dependencies
* chore: web Dockerfile reduce production image size
* chore: add exiftool-vendored.pl as a dependency
2023-02-02 21:28:34 -06:00
