Grace Luo

tanh activation

1

Hi, I was curious why in the implementation of GFPGAN there is no final tanh activation to keep generator outputs constrained between [-1, 1]; is there a reason why /...

Attention is None

3

I'm getting an error in this line https://github.com/alasdairtran/transform-and-tell/blob/c8da745646fbc4a823079cbe7bc8b75659b770b6/tell/models/decoder_faces_objects.py#L289 where the attn seems to be `None` -- @alasdairtran do you have any insight as to why this error might be occurring?...

Hi @JiahuiYu / @jasonbaldridge, I was wondering what "oversampling" in this line from the paper meant: "The validation set of the Localized Narratives COCO split contains only 5,000 unique images,...

gdal-merge output dimensions

1

Hi, my output from gdal merge is a tiff file with dimension (735, 256), where I have collected a series of images at zoom 8. Individually, each image / tiff...

Grad CAM for Visual Transformers

2

Awesome repo; thank you for creating this! I was wondering if you looked into visualizing the Grad CAM saliency maps for the ViT based CLIP models (and if so, which...

Bug: a course with no grade data prevents subsequent course data from displaying

3

This course has no data, yet it shows up in grades

Inform students of courses which have been previously offered under a different name/department

1

- EL ENG 126: https://berkeleytime.com/grades/0-2418-all-all - EECS 126: https://berkeleytime.com/grades/0-14673-all-all