Tweet

Sayak Paul

1 Nov, 4 tweets, 3 min read

@soumikRakshit96

@soumikRakshit96 and I have been working on this project for a while now. Today, we are delighted to share our progress.

Point cloud segmentation in the wild with @TensorFlow:

github.com/soumik12345/po…

1/

@fchollet

Our repository comes with full TPU support. You can also use multiple GPUs with mixed-precision (when supported). Here's a blog post to get started:

keras.io/examples/visio…

Thanks to @fchollet for your reviews.

2/

We provide standalone scripts and also notebooks for training and testing our models. We open-source all the experimental results and pre-trained models:

github.com/soumik12345/po…

3/

@GoogleDevExpert

We have included a notebook to run hyperparameter-tuning using Keras Tuner as well.

We hope you'll find this repository useful if you're into modeling 3D geometric vision data.

Thanks to @GoogleDevExpert program for providing #GCP support.

4/

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @RisingSayak

Sayak Paul

@RisingSayak

1 Jun

Recipes that I find to be beneficial when working in low-data/imbalance regimes (vision):

* Use a weighted loss function &/or focal loss.
* Either use simpler/shallower models or use models that are known to work well in these cases. Ex: SimCLRV2, Big Transfer, DINO, etc.

1/n

@TensorFlow

* Use MixUp or CutMix in the augmentation pipeline to relax the space of marginals.
* Ensure a certain percent of minority class data is always present during each mini-batch. In @TensorFlow, this can be done using `rejection_resampling`.

tensorflow.org/guide/data#rej…

2/n

@facebookai

* Use semi-supervised learning recipes that combine the benefits of self-supervision and few-shot learning. Ex: PAWS by @facebookai.
* Use of SWA is generally advised for better generalization but its use in these regimes is particularly useful.

3/n

Read 4 tweets

Sayak Paul

@RisingSayak

26 Apr

https://twitter.com/fchollet/status/1386400929704906754

New #Keras example is up on *consistency regularization*or an important recipe for semi-supervised learning and tackling distribution shifts as shown in *Noisy Student Training*.

keras.io/examples/visio…

1/n

https://twitter.com/fchollet/status/1386400929704906754

This example provides a template for performing semi-supervised / weakly supervised learning. A few things one can plug right in:

* Incorporate more data while training the student.
* Filter the high-confidence predictions while training the student.

2/n

The example uses Stochastic Weight Averaging during training the teacher to induce geometric ensembling. With elements like Stochastic Dropout, the performance might even be better.

Here are the full experiments: git.io/JO55v.

Read 5 tweets

Sayak Paul

@RisingSayak

2 Dec 20

@TensorFlow

Got the @TensorFlow Developer Certification.

Thanks to the #ML @GoogleDevExpert program for sponsoring the exam.

In this thread, I will summarize my experience.

⬇️

@TensorFlow

If you use @TensorFlow in your work moderately, I think you already have the prerequisites. Definitely take the *TensorFlow in Practice* specialization by @lmoroney & @DeepLearningAI_. It will get you up to speed.

Study the contents rigorously.

@pycharm

Review the certificate handbook carefully. It really has all the information you need to know about the certification - tensorflow.org/extras/cert/TF….

* Install @pycharm & get sufficiently comfortable with it.
* Set up the exam environment properly.

Read 6 tweets

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!