Dl

vs. stable diffusion. EXPERIMENTS

We attempted this challenge as part of our Deep Learning and Neural Networks Major Project.

Notebook#

Implementation details of U-Net, SamNet, VGG-Net and nnU-Net: {{< embed-notebook “/code/10khrs-ai-ml-dl/projects/kits19/report.html” >}}

Report#

The corresponding report contains a literature review along with other scientific details. We were restricted in length here, but not in the notebook above.

Non-descriptive frisbee stats#

A computer vision model that takes in streamed games and outputs a player statistic that factors in non-descriptive events — i.e. giving the correct call at the correct time, or poaching in the lane to force a bad throw.

I expect this to be trained using a transformer and written in Python. It is inspired by Andrew Wood’s analytical Ultimate dream.

OCR#

This was one of the first times I fell in love with Machine Learning, without knowing that the magic came from Machine Learning methods.

I simply had a `pdf` file with handwritten or scanned text, and desperately wanted to find something within the document without having to do it manually.

I google online for an OCR; upload my file; download it back again, and hey presto — such magical, accurate results!