image-classification

Enhancement

A discussion in #614 revealed a good place for improvement - we should ensure that input image is continuous upon start of the augmentation pipeline. This could be implemented by adding image = np.ascontiguousarray(image) to image and mask targets.

A proposed place to add this call - somewhere at the beginning of A.Compose.__call__.

At the moment, from API there are two useful columns about tasks:

However, in tabs (views) there are possible columns tasks:created_at a

My actions before raising this issue

• Read/searched the docs
• Searched past issues

Option to select chunk sizes does not exist in the CLI

Expected Beh

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

When running TabularPredictor.fit(), I encounter a BrokenPipeError for some reason.
What is causing this?
Could it be due to OOM error?

Fitting model: XGBoost ...
-34.1179 = Validation root_mean_squared_error score
10.58s = Training runtime
0.03s = Validation runtime
Fitting model: NeuralNetMXNet ...
-34.2849 = Validation root_mean_squared_error score
43.63s =

🚀 Feature Request

ENUMs for the catalyst-based conventions.
As an example, I will use scope.

Motivation

We have a lot of callbacks that used scope and maybe some other parameter that has only in catalyst-based meaning.
And every time we need to do something like that:

if isinstance(scope, str) and scope in [
            "on_batch_end",
            "on_batch_start",
  

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