Comments (16)
It is not open for contributions as of now. I believe Sayak will be contributing these to Keras core. Is that correct @sayakpaul? As of now KerasCV won't be accepting models until some details are ironed out on our end.
from keras-cv.
I have implemented it: https://github.com/sayakpaul/ConvNeXt-TF/. Should be available here soon: https://tfhub.dev/sayakpaul/collections/convnext/1.
from keras-cv.
I suppose that one had an inital approach of converting the Pytorch reference impl weights.
It would be nice to see how we will handle this with the points we have at #71
from keras-cv.
Yeah, absolutely. If you serialize the weights of the converted models you will have something similar to what's expected here.
from keras-cv.
More ore less. I think that some of difference in this repo could be:
-
As a library we could care to have a reusable components API of the network components. Probably more generic that just to build the original Networks and its variants that we could find in the same paper.
-
The training scirpts, dataset interfaces API and Markdowns to reproduce the weights from scratch
-
Extra (IMHO) finte tuning
-
Extra++ Having a community CI infra/github self-hosted actions on GKE to launch user contributed training/fine-tuning jobs approved by maintainers revieiws.
from keras-cv.
I am not absolutely sure about any of these points. I am also not sure how individual contributors could run the models from scratch without any involved support from the maintainers.
For implementing architectures, there could be specific bits while generic bits could still benefit from what the library already offers. If you see what I have implemented, you'd probably notice there's not too many specific bits there.
Also, it's helpful to have examples aiding your points. For example, if you could provide an example on what you meant in your first point in the context of this issue thread, that would be super helpful.
from keras-cv.
I am not absolutely sure about any of these points. I am also not sure how individual contributors could run the models from scratch without any involved support from the maintainers.
We don't have this infra right now inpalce. So we cannot contribute a Github action orchestrating the training job for reproducibility.
It was just my perspective feature request (this why was tagget as extra++).
For implementing architectures, there could be specific bits while generic bits could still benefit from what the library already offers. If you see what I have implemented, you'd probably notice there's not too many specific bits there. Also, it's helpful to have examples aiding your points. For example, if you could provide an example on what you meant in your first point in the context of this issue thread, that would be super helpful.
Yes other then thinking about obivious reusable components related to a specific network like new layers, optimizers, losses and metrics that It could introduce and exposed here as API. There was also:
#59
So mainly It is just thinking as a library with the network as an e2e integration example of the new (if needed) introduced components API
from keras-cv.
Hey @sayakpaul just a heads up, we are planning to hold off on incorporating models for a little bit longer.
@qlzh727 has some great ideas on changing the structure for Keras applications a bit, and we'd like to iron those out before adding any models.
from keras-cv.
Thanks for letting me know. Does this also mean keras.applications
will be held off from accepting new models for now?
from keras-cv.
Thanks for letting me know. Does this also mean
keras.applications
will be held off from accepting new models for now?
I'd guess so, this should only last a month or so before we have the new sample model ready though.
from keras-cv.
Understood. Thank you.
from keras-cv.
@LukeWood Is this issue open for contributions as well?! Next to SWIN transformers, ConvNext boasts even higher performance and stats utilizing similar robustness of training datasets! I definitely want to learn more about ConvNext in kerasCV as one of my research projects would have direct benefits having ConvNext integrated into Keras!
from keras-cv.
I am working on it, yes.
from keras-cv.
@sayakpaul we can migrate this to KerasCV when you are ready.
from keras-cv.
Yes sure. I will start working on it very soon.
from keras-cv.
Sayak fixed this!
from keras-cv.
Related Issues (20)
- YOLOV8Detector Tflite conversion model size problem. HOT 1
- Flaky Test Case in RPN Label Encoder and ROI Sampler HOT 1
- Migrate vgg16 from legacy to backbone HOT 2
- Possible indentation error HOT 4
- Migrate `vit` model from legacy to backbone HOT 3
- Ragged Tensor in Inference issue HOT 6
- bugs in object detection kpl
- incompatibility issue between keras_cv and TensorFlow and keras in windows 10 HOT 3
- stable_diffusion vs diffusion_model HOT 2
- Is image warping already ported from tfa? HOT 2
- yolo_v8_detector not compatible with torch backend because no good option for ragged tensor HOT 3
- kerascv layers demonstration HOT 2
- Boxes from TensorFlow Serving HOT 5
- KerasCV on Google Colab HOT 7
- How does Keras-YOLOv7 deal with conv2d layer padding bug? HOT 6
- Getting 'Killed' while trying to run 'pytest keras_cv' HOT 4
- Support `CutMix` for video data HOT 8
- Issue with KerasCV list of models in the documlentation
- CLIP result seems wrong HOT 5
- Add test for `roi_align`
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 keras-cv.