Rhythmblue
My research revolves around multi-model understanding (image, video and text).
Shanghai, China
Pinned Repositories
ctcdecode
PyTorch CTC Decoder bindings
CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python and OpenCL.
CUHK03_reader
Just a small Script to change cuhk-03.mat to images
dense_flow
Tools to extract dense optical flow from videos, based on OpenCV
i3d_finetune
This is an i3d version which can be used to finetune on other video dataset.
imgaug
Image augmentation for machine learning experiments.
Sign-Language-Datasets
Intro of some sign language datasets suitable for research
statistical_learning_homework
This is the programming exercises for statistical learning in USTC. （统计学习）
PruneVid
The official repository for paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".
S3LG
Rhythmblue's Repositories
Rhythmblue/i3d_finetune
This is an i3d version which can be used to finetune on other video dataset.
Rhythmblue/Sign-Language-Datasets
Intro of some sign language datasets suitable for research
Rhythmblue/CUHK03_reader
Just a small Script to change cuhk-03.mat to images
Rhythmblue/statistical_learning_homework
This is the programming exercises for statistical learning in USTC. （统计学习）
Rhythmblue/ctcdecode
PyTorch CTC Decoder bindings
Rhythmblue/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python and OpenCL.
Rhythmblue/dense_flow
Tools to extract dense optical flow from videos, based on OpenCV
Rhythmblue/imgaug
Image augmentation for machine learning experiments.
Rhythmblue/kenlm
KenLM: Faster and Smaller Language Model Queries
Rhythmblue/kinetics-i3d
Convolutional neural network model for video classification trained on the Kinetics dataset.
Rhythmblue/LeinaoPAI
Rhythmblue/license-plate-generator
**车牌生成
Rhythmblue/warp-ctc
Pytorch Bindings for warp-ctc
Rhythmblue/PyKinect2
Wrapper to expose Kinect for Windows v2 API in Python
Rhythmblue/pyttsx3
pyttsx for python3 ( offline tts for python : works for both python2 and python3 )
Rhythmblue/Rhythmblue.github.io
Rhythmblue/SCTK