fujenchu
Research Scientist at Facebook AI Research, PhD from Georgia Tech
Facebook AI ResearchMenlo Park
Pinned Repositories
20bn-something-something-label-hierarchies
Metadata for the Something-Something dataset
AdaptSegNet
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
affordance-net
AffordanceNet - Multiclass Instance Segmentation Framework - ICRA 2018
deep-learning-drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
matchingNet
implementation of Matching Net in Pytorch
relationNet
implementation of relationNet naive version
grasp_multiObject
Robotic grasp dataset for multi-object multi-grasp evaluation with RGB-D data. This dataset is annotated using the same protocal as Cornell Dataset, and can be used as multi-object extension of Cornell Dataset.
grasp_multiObject_multiGrasp
An implementation of our RA-L work 'Real-world Multi-object, Multi-grasp Detection'
simData
The dataset of our RA-L work 'Learning Affordance Segmentation for Real-world Robotic Manipulation via Synthetic Images'
simData_imgSaver
This repo contains tools to save images of simulated objects in Gazebo for affordance segmentation
fujenchu's Repositories
fujenchu/relationNet
implementation of relationNet naive version
fujenchu/matchingNet
implementation of Matching Net in Pytorch
fujenchu/deep-learning-drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
fujenchu/20bn-something-something-label-hierarchies
Metadata for the Something-Something dataset
fujenchu/AdaptSegNet
Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)
fujenchu/affordance-net
AffordanceNet - Multiclass Instance Segmentation Framework - ICRA 2018
fujenchu/Algorithm_Interview_Notes-Chinese
2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记
fujenchu/android-demo-app
PyTorch android examples of usage in applications
fujenchu/Augmentor
Image augmentation library in Python for machine learning.
fujenchu/da-faster-rcnn
An implementation of our CVPR 2018 work 'Domain Adaptive Faster R-CNN for Object Detection in the Wild'
fujenchu/DeepLearning-500-questions
深度学习500问,以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述,以帮助自己及有需要的读者。 全书分为18个章节,50余万字。由于水平有限,书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作,联系scutjy2015@163.com 版权所有,违权必究 Tan 2018.06
fujenchu/examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
fujenchu/faster-rcnn.pytorch
A faster pytorch implementation of faster r-cnn
fujenchu/fujenchu.github.io
fujenchu/fujenchu1.github.io
for hexo deploy
fujenchu/Matrix-Capsules-EM-Tensorflow
A Tensorflow implementation of CapsNet based on paper Matrix Capsules with EM Routing
fujenchu/ML-NLP
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现,也是作为一个算法工程师必会的理论基础知识。
fujenchu/paper-tips-and-tricks
Best practice and tips & tricks to write scientific papers in LaTeX, with figures generated in Python or Matlab.
fujenchu/papers
:paperclip: Summaries of papers on deep learning
fujenchu/PRML
PRML algorithms implemented in Python
fujenchu/prototypical-networks
Code for the NIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
fujenchu/pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
fujenchu/pytorch_geometric
Geometric Deep Learning Extension Library for PyTorch
fujenchu/realai.org
fujenchu/reinforcement-learning-an-introduction
Python implementation of Reinforcement Learning: An Introduction
fujenchu/science_rcn
Reference implementation of a two-level RCN model
fujenchu/SpeechToText
Speech To Text in Android
fujenchu/supervised-reptile
Reptile on supervised meta-learning datasets
fujenchu/system-design-primer
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
fujenchu/visual-pushing-grasping
Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.