- Notifications
You must be signed in to change notification settings - Fork63
Docker for Your ML/DL Models Based on OCI Artifacts
License
kleveross/ormb
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
English |中文
ORMB is an open-source model registry to manage machine learning model.
ORMB helps you manage your Machine Learning/Deep Learning models with image registry. It makes your models easy to create, version, share and publish.
You can watch our sample usage video or read the text version below.
First, open a model folder that meets the specification ofORMB. (See our documentation for more information aboutormbfile.yaml)
# View the local file directory$ tree examples/SavedModel-fashionexamples/SavedModel-fashion├── model│ ├── saved_model.pb│ └── variables│ ├── variables.data-00000-of-00001│ └── variables.index├── ormbfile.yaml└── training-serving.ipynb2 directories, 5 filesNext, we can push the trained model from local to remote image registry.
# Save the model from model directory in local cache first$ ormb save<model directory> gaocegege/fashion_model:v1ref: gaocegege/fashion_model:v1digest: 6b08cd25d01f71a09c1eb852b3a696ee2806abc749628de28a71b507f9eab996size: 162.1 KiBformat: SavedModelv1: saved# Push the model from local cache to remote registry$ ormb push gaocegege/fashion_model:v1The push refers to repository [gaocegege/fashion_model]ref: gaocegege/fashion_model:v1digest: 6b08cd25d01f71a09c1eb852b3a696ee2806abc749628de28a71b507f9eab996size: 162.1 KiBformat: SavedModelv1: pushed to remote (1 layer, 162.1 KiB total)
TakingHarbor as an example, we can see the model's metadata in Harbor registry.
Then, we can download the model from the registry. The download process is similar to the push.
# Pull the model from remote registry to local cache$ ormb pull gaocegege/fashion_model:v1v1: Pulling from gaocegege/fashion_modelref: gaocegege/fashion_model:v1digest: 6b08cd25d01f71a09c1eb852b3a696ee2806abc749628de28a71b507f9eab996size: 162.1 KiBStatus: Downloaded newer modelfor gaocegege/fashion_model:v1# Export the model from local cache to current directory$ ormbexport gaocegege/fashion_model:v1ref: localhost/gaocegege/fashion_model:v1digest: 6b08cd25d01f71a09c1eb852b3a696ee2806abc749628de28a71b507f9eab996size: 162.1 KiB# View the local file directory$ tree examples/SavedModel-fashionexamples/SavedModel-fashion├── model│ ├── saved_model.pb│ └── variables│ ├── variables.data-00000-of-00001│ └── variables.index├── ormbfile.yaml└── training-serving.ipynb2 directories, 5 files
ORMB uses the image registry to store model, you can choose toinstall Harbor oruse Docker Registry. We recommended Harbor here.
You can install the pre-compiled binary, or compile from source.
Download the pre-compiled binaries fromthe releases page and copy to the desired location.
Clone:
$ git clone https://github.com/kleveross/ormb$ cd ormbGet the dependencies:
$ go mod tidyBuild:
$ make build-localVerify it works:
$ ./bin/ormb --helpSeeORMB introduction for more information.
SeeORMB docs for more information.
- Distribute models with
ORMBand Docker Registry:tutorial.md - Serving model with Seldon Core:tutorial-serving-seldon.md
Please have a look atdocs/spec_v1alpha1.md
ORMB project is part of Klever, a Cloud Native Machine Learning platform.
The Klever slack workspace is klever.slack.com. To join, click thisinvitation to our Slack workspace.
About
Docker for Your ML/DL Models Based on OCI Artifacts
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Packages0
Uh oh!
There was an error while loading.Please reload this page.