There is a set of Pixel Level transforms that is used in the work Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

The authors also share the code => we can absorb some transforms that they have into the library.

https://github.com/hendrycks/robustness/blob/master/ImageNet-C/create_c/make_imagenet_c.py

• ShotNoise
• Defocus
• GlassBlur

My actions before raising this issue

• [ X ] Read/searched the docs
• [ X ] Searched past issues

Expected Behaviour

I want to use the same Labels in the same or

There are many links in Kinetics that have expired. As as result, everyone might not be using the same Kinetics dataset. As a reference, the statistics of the Kinetics dataset used in PySlowFast can be found here, https://github.com/facebookresearch/video-nonlocal-net/blob/master/DATASET.md. However, I cannot seem to find similar information for gluoncv. Will you guys be sharing the statistics and

Issue

I am getting a segmentation fault when running the following import statement

from autogluon.tabular import TabularPrediction

and segmentation fault: 11 when running

from autogluon.text import TextPrediction

I am using a recent branch of autogluon, installed in a clean virtual environment: autogluon version 0.0.16b20210120

Environment

with video_demo.py about 20% speed compared to your 1.0 repo. but thanks much for sharing!