Pulkit Mishra

Better support for self supervised learning

6

## 🚀 Feature Add support for self supervised learning, especially for multimodal input and improve the current vissl backed features. ### Motivation I have been working on multimodal self supervised...

Calculation of viideo score is too slow

2

Is there a way to speed up this?

pyre analyse --no-verify crashes with "Worker interrupted with signal: sigpipe"

1

# Pysa Bug **Bug description** I've been trying to get pysa to run on the [example flask app in the repo](https://github.com/facebook/pyre-check/blob/master/documentation/deliberately_vulnerable_flask_app/rce.py) but the process gets killed everytime (sometimes with sigpipe,...

WIP - creates a model validation testing system for the Opensource models

Rekognition UI

3

While a lot of work has gone into training deep learning models and creating easy to consume REST APIs, work on the frontend hasn't progresses since 2019 which you can...

What is the best way to save and access bounding box of previous frame inside a gvapython module. Indeed it is possible to pickle them on ith frame and load...

[Bug] ntu_pose_extraction in tools/data/skeleton gives keypoints in COCO format instead of NTU RGBD

1

### Branch main branch (1.x version, such as `v1.0.0`, or `dev-1.x` branch) ### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmaction2/issues) and [Discussions](https://github.com/open-mmlab/mmaction2/discussions) but cannot get the expected help. - [X]...

@ivona-tooploox @IvonaTau after the features have been extracted and saved to vse. How do I save it and use it later ? I want to avoid feature extraction everytime.