devinzhang91/immch_rknn

By devinzhang91 · ↓ 0 · ♥ 0 · Updated 2025-02-08

What's in this repo

This page lists the files in devinzhang91/immch_rknn, including model.onnx and more.

12 ONNX models (.onnx files)
80 files, including 21 .armnn, 18 .json, 12 .onnx, 12 .rknn, 7 .md, 3 .txt
Last updated 2025-02-08

ONNX files

File	Size	Download
cache-rk3566/clip/ViT-B-32__openai/textual/model.onnx	—	Download
cache-rk3566/clip/ViT-B-32__openai/visual/model.onnx	—	Download
cache-rk3566/facial-recognition/buffalo_l/detection/model.onnx	—	Download
cache-rk3566/facial-recognition/buffalo_l/recognition/model.onnx	—	Download
cache-rk3568/clip/ViT-B-32__openai/textual/model.onnx	—	Download
cache-rk3568/clip/ViT-B-32__openai/visual/model.onnx	—	Download
cache-rk3568/facial-recognition/buffalo_l/detection/model.onnx	—	Download
cache-rk3568/facial-recognition/buffalo_l/recognition/model.onnx	—	Download
cache-rk3588/clip/ViT-B-32__openai/textual/model.onnx	—	Download
cache-rk3588/clip/ViT-B-32__openai/visual/model.onnx	—	Download

Showing 10 of 12 .onnx files — see the full file list on the right.

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

immch machine learning with rockchip NPU (rknpu) model, with rknn format.

modify your docker-compose file:

immich-machine-learning:
    container_name: immich_machine_learning
    # For hardware acceleration, add one of -[armnn, cuda, openvino, rknn] to the image tag.
    # Example tag: ${IMMICH_VERSION:-release}-cuda
    image: registry.cn-hangzhou.aliyuncs.com/devinzhang91/immich-machine-learning:rknn-toolkit-lite2-rknn
    extends: # uncomment this section for hardware acceleration - see https://immich.app/docs/features/ml-hardware-acceleration
      file: hwaccel.ml.yml
      service: rknn # set to one of [armnn, cuda, openvino, openvino-wsl, rknn] for accelerated inference - use the `-wsl` version for WSL2 where applicable
    volumes:
      - cache-{YOUR_PLATFORM}:/cache

docker run -v cache-{YOUR_PLATFORM}:/cache ...

github: here

immich-rknn docker images (ARC):

docker pull registry.cn-hangzhou.aliyuncs.com/devinzhang91/immich-machine-learning:rknn-toolkit-lite2-rknn

docker pull registry.cn-hangzhou.aliyuncs.com/devinzhang91/immich-server:rknn-toolkit-lite2-rknn

Model info

onnx license:apache-2.0 region:us

↓ 0 ♥ 0

Created: 2025-02-07

Updated: 2025-02-08

View on Hugging Face

Files (80)

.gitattributes

README.md

cache-rk3566/clip/ViT-B-32__openai/.gitattributes

cache-rk3566/clip/ViT-B-32__openai/README.md

cache-rk3566/clip/ViT-B-32__openai/config.json

cache-rk3566/clip/ViT-B-32__openai/textual/fp16/model.armnn

cache-rk3566/clip/ViT-B-32__openai/textual/merges.txt

cache-rk3566/clip/ViT-B-32__openai/textual/model.onnx ONNX

cache-rk3566/clip/ViT-B-32__openai/textual/model.rknn

cache-rk3566/clip/ViT-B-32__openai/textual/special_tokens_map.json

cache-rk3566/clip/ViT-B-32__openai/textual/tokenizer.json

cache-rk3566/clip/ViT-B-32__openai/textual/tokenizer_config.json

cache-rk3566/clip/ViT-B-32__openai/textual/vocab.json

cache-rk3566/clip/ViT-B-32__openai/visual/fp16/model.armnn

cache-rk3566/clip/ViT-B-32__openai/visual/model.armnn

cache-rk3566/clip/ViT-B-32__openai/visual/model.onnx ONNX

cache-rk3566/clip/ViT-B-32__openai/visual/model.rknn

cache-rk3566/clip/ViT-B-32__openai/visual/preprocess_cfg.json

cache-rk3566/facial-recognition/buffalo_l/.gitattributes

cache-rk3566/facial-recognition/buffalo_l/README.md

cache-rk3566/facial-recognition/buffalo_l/detection/fp16/model.armnn

cache-rk3566/facial-recognition/buffalo_l/detection/model.armnn

cache-rk3566/facial-recognition/buffalo_l/detection/model.onnx ONNX

cache-rk3566/facial-recognition/buffalo_l/detection/model.rknn

cache-rk3566/facial-recognition/buffalo_l/recognition/fp16/model.armnn

cache-rk3566/facial-recognition/buffalo_l/recognition/model.armnn

cache-rk3566/facial-recognition/buffalo_l/recognition/model.onnx ONNX

cache-rk3566/facial-recognition/buffalo_l/recognition/model.rknn

cache-rk3568/clip/ViT-B-32__openai/.gitattributes

cache-rk3568/clip/ViT-B-32__openai/README.md

cache-rk3568/clip/ViT-B-32__openai/config.json

cache-rk3568/clip/ViT-B-32__openai/textual/fp16/model.armnn

cache-rk3568/clip/ViT-B-32__openai/textual/merges.txt

cache-rk3568/clip/ViT-B-32__openai/textual/model.onnx ONNX

cache-rk3568/clip/ViT-B-32__openai/textual/model.rknn

cache-rk3568/clip/ViT-B-32__openai/textual/special_tokens_map.json

cache-rk3568/clip/ViT-B-32__openai/textual/tokenizer.json

cache-rk3568/clip/ViT-B-32__openai/textual/tokenizer_config.json

cache-rk3568/clip/ViT-B-32__openai/textual/vocab.json

cache-rk3568/clip/ViT-B-32__openai/visual/fp16/model.armnn

cache-rk3568/clip/ViT-B-32__openai/visual/model.armnn

cache-rk3568/clip/ViT-B-32__openai/visual/model.onnx ONNX

cache-rk3568/clip/ViT-B-32__openai/visual/model.rknn

cache-rk3568/clip/ViT-B-32__openai/visual/preprocess_cfg.json

cache-rk3568/facial-recognition/buffalo_l/.gitattributes

cache-rk3568/facial-recognition/buffalo_l/README.md

cache-rk3568/facial-recognition/buffalo_l/detection/fp16/model.armnn

cache-rk3568/facial-recognition/buffalo_l/detection/model.armnn

cache-rk3568/facial-recognition/buffalo_l/detection/model.onnx ONNX

cache-rk3568/facial-recognition/buffalo_l/detection/model.rknn

cache-rk3568/facial-recognition/buffalo_l/recognition/fp16/model.armnn

cache-rk3568/facial-recognition/buffalo_l/recognition/model.armnn

cache-rk3568/facial-recognition/buffalo_l/recognition/model.onnx ONNX

cache-rk3568/facial-recognition/buffalo_l/recognition/model.rknn

cache-rk3588/clip/ViT-B-32__openai/.gitattributes

cache-rk3588/clip/ViT-B-32__openai/README.md

cache-rk3588/clip/ViT-B-32__openai/config.json

cache-rk3588/clip/ViT-B-32__openai/textual/fp16/model.armnn

cache-rk3588/clip/ViT-B-32__openai/textual/merges.txt

cache-rk3588/clip/ViT-B-32__openai/textual/model.onnx ONNX

cache-rk3588/clip/ViT-B-32__openai/textual/model.rknn

cache-rk3588/clip/ViT-B-32__openai/textual/special_tokens_map.json

cache-rk3588/clip/ViT-B-32__openai/textual/tokenizer.json

cache-rk3588/clip/ViT-B-32__openai/textual/tokenizer_config.json

cache-rk3588/clip/ViT-B-32__openai/textual/vocab.json

cache-rk3588/clip/ViT-B-32__openai/visual/fp16/model.armnn

cache-rk3588/clip/ViT-B-32__openai/visual/model.armnn

cache-rk3588/clip/ViT-B-32__openai/visual/model.onnx ONNX

cache-rk3588/clip/ViT-B-32__openai/visual/model.rknn

cache-rk3588/clip/ViT-B-32__openai/visual/preprocess_cfg.json

cache-rk3588/facial-recognition/buffalo_l/.gitattributes

cache-rk3588/facial-recognition/buffalo_l/README.md

cache-rk3588/facial-recognition/buffalo_l/detection/fp16/model.armnn

cache-rk3588/facial-recognition/buffalo_l/detection/model.armnn

cache-rk3588/facial-recognition/buffalo_l/detection/model.onnx ONNX

cache-rk3588/facial-recognition/buffalo_l/detection/model.rknn

cache-rk3588/facial-recognition/buffalo_l/recognition/fp16/model.armnn

cache-rk3588/facial-recognition/buffalo_l/recognition/model.armnn

cache-rk3588/facial-recognition/buffalo_l/recognition/model.onnx ONNX

cache-rk3588/facial-recognition/buffalo_l/recognition/model.rknn

Related models

More from devinzhang91

No other models by this author.

More models

No task type declared.