Micah Bowles's Projects
Fast image augmentation library and an easy-to-use wrapper around other libraries. Documentation: https://albumentations.ai/docs/ Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Learned attention mechanism for radio astronomy.
A package with various custom augmentations implemented which are specifically designed around astronomical data.
Project to collect ALL the data!
Astronomy and astrophysics core library
:page_facing_up: Awesome CV is LaTeX template for your outstanding job application
Computationally minimal gravitational simulation of galaxy collisions.
Produce a loadable data set from a catalogue.
My attempt for climatehack
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Code repository for the paper: Fanaroff-Riley classification of radio galaxies using group-equivariant convolutional neural networks, 2021, Scaife & Porter
An implementation of Equivariant e2 convolutional kernals into a convolutional self attention network, applied to radio astronomy data.
Recovering image posterior out of interferometer visibility data.
Adapted pipeline for MeerKAT polarisation imaging on the IRIS cluster.
Multimodal Masked Autoencoders (M3AE): A JAX/Flax Implementation
Config files for my GitHub profile.
Portfolio / personal website.
Science imaging on Manchester's Galahad HPC for MIGHTEE-POL.
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Digital asset initially produced during QML research placement with DiRAC and Google.
Schrödinger and Schrödinger-Feynman simulators for quantum circuits.
Machine learning to excise RFI from a response to a field of view of the EVLA in D-Configuration
Python 3.6+ toolbox for submitting jobs to Slurm