黄(Huáng)瓒(Zàn)'s Projects
Roaring bitmaps in C (and C++), with SIMD (AVX2, AVX-512 and NEON) optimizations
For Prof. Deng's Data Structure and Algorithms course(MOOC version)
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
Pieces of code extracted from homeworks and mini-projects:tiger:
About Udacity's Machine Learning Nanodegree program in Chinese:smiley::rocket:
For submitting project assignments
ONNX-TensorRT: TensorRT backend for ONNX
Bridging python and matlab version OTB
Gatech CSE6242 Spring2020 Project:rocket:
Assembler for NVIDIA Volta and Turing GPUs
Add README to my profile page by creating the user_id named repo
Mind Log
RAFT contains fundamental widely-used algorithms and primitives for data science, graph and machine learning.
CSE6240 project: RNN->Network Embedding->MOOC Dropout Prediction->:rocket:
pytorch rpc seems easier to use for distributed training, sample scripts :)
PyTorch(1.6+) implementation of https://github.com/kang205/SASRec
From simple artificial neural network for MNIST exercise to Network Analysis :cyclone:
Based on https://github.com/JiachengLi1995/TiSASRec, replace negative sampling based evaluation with all-item based evaluation and try to make it better for ranking all items.
https://github.com/JiachengLi1995/TiSASRec in PyTorch
"REVISITING THE DETAILS WHEN EVALUATING A VISUAL TRACKER":notebook:
Google Colab Notebooks for Udacity CS344 - Intro to Parallel Programming
Show how WaveNet works and how to accelerate model inference in reference to https://github.com/tomlepaine/fast-wavenet
Sample to show how input dim(input_dim for FC layer, for CNN, it's prod(tensor.shape[1:])) reciprocal could be used for initialize NN weights rather than sqrt(input_dim_reciprocal) hinted by Xavier:dragon: