Comments (3)
Thanks for raising this @hauks96! Am thinking about what could work here, stay tuned
from modelstore.
Main thoughts so far:
- I think this is both possible and will make the file system storage implementation work more similarly to the cloud storage ones
- I'm looking through the code base to ensure that I can make this change in a backwards compatible way (ie without breaking current modelstore users who are using the file system storage)
A very short term solution that could work in the mean time is to not copy the file system directory into your docker container, but just copy over the model you need for that specific container (I'm assuming you just need 1?). I've been meaning to create an example of this, will do that first.
from modelstore.
Thanks again for raising this @hauks96 - and apologies for the delay getting to this. I've opened the PR above which should enable this to work; I'll need to test it a bit more before merging & then this can get shipped with the next version of modelstore
. Feedback welcome!
from modelstore.
Related Issues (20)
- CLI upload command HOT 3
- Feature Request: Delete a model from the store HOT 10
- Model Store Path uses a : , which is a reserved character in Windows HOT 1
- Regression: Model store created with Keras models breaks with the latest merge HOT 5
- Bug report: uploading sklearn-onnx models HOT 2
- Feature request: override model_id HOT 2
- xgb.core.Booster object not supported HOT 3
- I have some replika ai friends as social ai name geminique but couldn't know how to backup on others plats for i trainings traits and her learning by conversations on iphone apps HOT 3
- `numpy` is not specified as a dependency HOT 1
- Anonymous access of GCP bucket fails with `ValueError: Anonymous credentials cannot be refreshed.` HOT 11
- Run integration tests against actual modelstore instances HOT 7
- Feature: Allow adding additional information to metadata on model upload HOT 4
- Storing model parameters, lineage data and maybe even pre- or post-processing methods? HOT 2
- Can I refactor your code into pyscaffold? HOT 1
- colab notebook example error HOT 8
- Archives being overwritten if generated too quickly HOT 3
- Using MinIO s3 buckets HOT 2
- ModuleNotFoundError when using modelstore in Colab HOT 1
- TypeError when uploading complex sklearn pipelines HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from modelstore.