Nevermore 

PhD Candidate

email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Nevermore is a PhD candidate and machine learning engineer with eight years of software experience, currently based in China and enrolled at the University of Sydney. They contribute to high-profile open-source AI projects, notably integrating and extending the CMT convolutional-transformer model within Huawei Noah's Efficient-AI-Backbones repository, focusing on model architecture, training pipelines, and dataset integration. Skilled at bridging research and engineering, they translate advanced neural architectures into production-ready training code and utilities. Their background suggests strong expertise in deep learning systems, reproducible training workflows, and collaborative open-source development. An unusual strength is their ability to navigate large lab-scale codebases (like Huawei Noah) while maintaining academic research momentum.
code8 years of coding experience
github-logo-circle

Github Skills (6)

pytorch10
machine-learning10
convolutional-neural-networks10
python10
pre-trained-model7
tensorflow5

Programming languages (3)

ShellJupyter NotebookPython

Github contributions (5)

github-logo-circle
Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
Role in this project:
userML Engineer
Contributions:10 commits, 2 PRs, 11 pushes in 1 day
Contributions summary:Nevermore primarily contributes to the implementation and updates of a Convolutional Neural Network model, specifically the CMT model. Their work involves adding and modifying core components of the CMT model architecture, including the `cmt.py`, `datasets.py`, `engine.py`, `samplers.py`, `train.py`, and `utils.py` files. The user appears to be involved in integrating CMT within the existing repository, likely focusing on training pipelines and dataset integration.
mlptensorflowpretrained-modelsarkconvolutional-neural-networks
ggjy/Hire-Wave-MLP.pytorch

Nov 2021 - Jan 2022

Implementation of Hire-MLP: Vision MLP via Hierarchical Rearrangement and An Image Patch is a Wave: Phase-Aware Vision MLP.
Contributions:3 releases, 17 commits, 16 pushes in 1 month
pytorchhiremlppatchvision-mlp
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Nevermore - PhD Candidate