Pietro Antonio Cicalese

Making YOLACT compatible with 16:9 aspect ratio without 1:1 reshaping

1

Hello @dbolya , thanks for the awesome implementation and the excellent paper. I am planning on modifying the YOLACT architecture to be compatible with aspect ratios other than squares, so...

Question regarding queries dimensionality in Perceiver IO

3

Hi @lucidrains, I think I may be missing something - why do we define the perceiver IO queries vector to have a batch dimension (i.e. `queries = torch.randn(1, 128, 32)`)?...

Not sure what the reason for this may be. I will keep trying to debug.

Upgrade file reader to tifffile

7

Hi there, Ive found openslide to be quite problematic when dealing with high mag WSIs. Your code can be upgraded to use tifffile, which would eliminate the image size limitations...

* inferno version: October 14 2020 (not installed) * Python version: 3.7.9 * Operating System: Ubuntu 16.04 ### Description I am working on adapting your cityscapes data loader. It appears...

Hello! First of all, this is truly wonderful work and I expect to be playing with this repo for some time to come. LDMs are a great idea and they...

Generating image label pairs with dataset containing more labeled than unlabeled images

1

Hello I am working with datasets that contain more labeled images than unlabeled. In my experiments with default settings, it seems that the generator struggles to learn the input, and...