Ethan Harris

Awesome! Thanks for your help. > So, I guess after I push in the new update (which may take a while), we may want to re-look at the integration to...

Hello, The visualising code is in visualise.py. Specifically, the `red_sqare` method is used to make a red square of a certain side which must then be transformed with the same...

Hi, The way to do it in torchbearer would be to use a callback. There's a couple of options, either use the callback `StagesGrid` in visualise.py or use torchbearers MakeGrid...

+1 We are also seeing this issue. A lot of first-time contributor PRs come from master branches so coverage drops can be quite frequent for some projects.

Hey @Nexer8 thanks for the feature request! More heads / backbones (including transformers) is definitely something we'd like to have. We tried to source backbones from MMdetection once before but...

Hey @MGReyes thanks for reporting this! There are a few things to unpack here that we should work on: - documentation for using tasks with your own datamodules (expect this...

Hey @uakarsh instead of creating a script from scratch, could you just apply your changes to the script here: https://github.com/Lightning-AI/lightning-flash/blob/master/flash_examples/integrations/learn2learn/image_classification_imagenette_mini.py Happy for you to drop the `ddp_shared`, looks like a...

Closing this as addressed in #1410

Fixed by #1389

Hey @Moumeneb1 Thanks for reporting this! We'll look into it and get back to you 😃