Yanbo Fan
PhD Candidate
Summary
🤩
RockstarYanbo Fan is a PhD candidate and experienced machine learning engineer with nine years in research and applied computer vision, affiliated with NLPR, CASIA. He has contributed to high-impact open-source projects such as Tencent's tencent-ml-images, refining ResNet implementations and training pipelines for large-scale multi-label image datasets. Yanbo combines deep academic training with hands-on engineering—optimizing data parsing, model definition, and loss computation to improve ImageNet-class performance. Based in China, he bridges research rigor and production readiness, focusing on scalable CNN architectures and dataset engineering. Colleagues describe him as a pragmatic researcher who translates complex models into reliable, reproducible code for real-world benchmarks.
8 years of coding experience
Github Skills (8)
computer-vision10
deep-learning10
tensorflow10
resnet10
python10
imagenet10
data-processing9
machine-learning9
Programming languages (1)
Github contributions (3)
Tencent/tencent-ml-images
Oct 2018 - Oct 2019
Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet
Role in this project:
ML Engineer
ML EngineerContributions:15 commits, 8 pushes in 1 year
Contributions summary:Yanbo primarily contributes to the ResNet model implementation, likely for the ImageNet dataset, as evidenced by the code changes focusing on data parsing, model definition, and loss calculation. The commits include modifications to the training pipeline, data processing functions, and the inclusion of license information. The user also updates the resnet.py file indicating refinement of the core model.
pytorchimagenetdeep-learningimage-labelcomputer-vision
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.