dohe0342
Computer Vision, Face Recognition, Person Re-ID, Object Detection, DeepLearning acceleration, Cat 🐱
ECE @ University of SeoulSeoul, South Korea
Pinned Repositories
conf_wordcloud
darknet
Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)
example
fairseq
fairseq personally usage
insightface
Face Analysis Project on MXNet
pipelining_fd
c++ pipelining implementation. pre,post + infer 2 stage
PyTorch_study_21.02
PyTorch autograd, nn, optim study.(2021.02.15)
Seq2Seq_mnist
Seq2Seq model which can infer MNIST sequence data
VideoFaceRecognition
official implementation of videoFR via face object
VideoFaceRecognition_old
dohe0342's Repositories
dohe0342/VideoFaceRecognition_old
dohe0342/fairseq
fairseq personally usage
dohe0342/pipelining_fd
c++ pipelining implementation. pre,post + infer 2 stage
dohe0342/Seq2Seq_mnist
Seq2Seq model which can infer MNIST sequence data
dohe0342/VideoFaceRecognition
official implementation of videoFR via face object
dohe0342/conf_wordcloud
dohe0342/darknet
Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)
dohe0342/example
dohe0342/insightface
Face Analysis Project on MXNet
dohe0342/PyTorch_study_21.02
PyTorch autograd, nn, optim study.(2021.02.15)
dohe0342/rabbitexample
dohe0342/unittest_study_21.02
python unittest study(21.02.28)
dohe0342/2022-korean-ai-contest-weight-check
dohe0342/4-gram
dohe0342/CPC_asr
Automatic Speech Recognition using CPC algorithm
dohe0342/espnet
espent for personal usage
dohe0342/espnet2
for PAC
dohe0342/espnet_jieun
End-to-End Speech Processing Toolkit
dohe0342/fairseq_new
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
dohe0342/ICASSP2024
dohe0342/icefall
dohe0342/KegNet
Knowledge Extraction with No Observable Data (NeurIPS 2019)
dohe0342/models
Models and examples built with TensorFlow
dohe0342/task_disentanglement
gradient based task disentanglement
dohe0342/vall-e
An unofficial PyTorch implementation of the audio LM VALL-E
dohe0342/valle
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Can be trained on a single GPU!