Comments (5)
Hi @ryanccarelli,
Thanks for your interest in Scenic and this is exciting that you are considering Scenic for your self-supervised learning project.
We have a much more flexible and complete input-pipeline internally (that is somehow inline with proposal (a) from you) and we are in the are in the process of open-sourcing it. So hopefully soon, we will have that in Scenic. I can keep this issue open and comment on it as soon as the complete input pipeline is open-sourced.
CCing @andsteing.
from scenic.
Thank you again, this project has been very useful for us
from scenic.
An input pipeline that is much more flexible is now open-sourced. I also released some config files in #148 To show how to use this pipeline. Please let us know if you had any question or any issue.
from scenic.
Thank you for your fast response! It would be great if you could share an approximate timeline (weeks? months?) so we can plan around this
from scenic.
Sorry for a bit of delay! I was checking with people about the timeline and I think the part that is related to your need can be open-sourced sooner than the rest and I can spend some time to hopefully get it out in a few days.
from scenic.
Related Issues (20)
- UniVRD model release? HOT 2
- scenic/scenic/projects /mbt bottleneck shape shape?
- CUDA12.3 install
- Dockerfile for running SCENIC+CUDA
- What is the file format of the checkpoint files? HOT 1
- Focal loss in OWL-ViT HOT 6
- playground.ipynb of OWL-ViT starts having dependency and import error on Google Colab since Nov. 15 HOT 4
- AttributeError: module 'numpy.linalg._umath_linalg' has no attribute '_ilp64' HOT 3
- Clip implementation with Hugging Face Datasets
- Inconsistent Object Detection Results on Constant Video Stream and Text Query
- Knowledge Distillation - OwlViT Model
- OWL-ViT inference playround: ModuleNotFoundError: No module named 'jax.experimental.gda_serialization' HOT 1
- Full training example with custom dataset HOT 1
- I would like to ask for the code release of UniVRD (ICCV 2023). HOT 1
- Port Vid2Seq to use new train_lib
- not module named ’grain.python‘
- local checkpoint error
- Requirements for Vid2Seq
- finetune owl on image dataset with no caption
- CLIP feature compression package for the ActivityNet Captions dataset
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 scenic.