profile
viewpoint
If you are wondering where the data of this site comes from, please visit https://api.github.com/users/ak9250/events. GitMemory does not store any data, but only uses NGINX to cache data for a period of time. The idea behind GitMemory is simply to give users a better reading experience.

ak9250/3DDFA 3

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

ak9250/Bringing-Old-Photos-Back-to-Life 3

Bringing Old Photo Back to Life (CVPR 2020 oral)

ak9250/AudioDVP 1

AudioDVP:Photorealistic Audio-driven Video Portraits

ak9250/coconet-colab 1

train coconet in colab

ak9250/3d-photo-inpainting 0

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting

ak9250/3Dpose_ssl 0

3D Human Pose Machines with Self-supervised Learning

ak9250/AI4Animation 0

Character Animation in Unity3D using Deep Learning and Artificial Intelligence

ak9250/angry-birds-python 0

Angry Birds game written in python using pygame and pymunk

ak9250/anycost-gan 0

[CVPR 2021] Anycost GANs for Interactive Image Synthesis and Editing

issue closedopenai/jukebox

multilingual jukebox

anyone interested in collected a multilingual dataset to train jukebox, possible close to 2M songs of raw audio?

closed time in 2 months

ak9250

issue closedopenai/jukebox

clip guided jukebox

has anyone applied clip to jukebox, see https://github.com/AndreyGuzhov/AudioCLIP

closed time in 2 months

ak9250

issue closedEleutherAI/project-menu

Multilingual Jukebox

  • Project: What is your project name?
  • Multilingual Jukebox
  • Elevator Pitch: A short (max 1 paragraph) explanation of what your project is and why it is awesome.
  • train a scaled up jukebox on a multilingual dataset
  • Goal Outputs: When this project is over, what things do you intend to have produced? An open source codebase? An academic paper? A new dataset?
  • codebase, pretrained models, possible paper
  • Milestones: At a high level, what are the major milestones of this project (including completed ones)? Which ones are completed and which ones are in progress?
  • dataset collection (~2M songs)
  • How to Help: If someone wanted to join the project, what would you like them to do?
  • dataset collection (~2M songs)
  • Desired Support: What sort of funding, compute, data, or other materials do you need help obtaining to carry out your project? Will EAI be providing them? Do you have alternate sources of support? Feel free to add any additional relevant information.
  • dataset collection
  • compute for training

closed time in 3 months

ak9250

issue openedEleutherAI/project-menu

Multilingual Jukebox

  • Project: What is your project name?
  • Multilingual Jukebox
  • Elevator Pitch: A short (max 1 paragraph) explanation of what your project is and why it is awesome.
  • train a scaled up jukebox on a multilingual dataset
  • Goal Outputs: When this project is over, what things do you intend to have produced? An open source codebase? An academic paper? A new dataset?
  • codebase, pretrained models, possible paper
  • Milestones: At a high level, what are the major milestones of this project (including completed ones)? Which ones are completed and which ones are in progress?
  • dataset collection (~2M songs)
  • How to Help: If someone wanted to join the project, what would you like them to do?
  • dataset collection (~2M songs)
  • Desired Support: What sort of funding, compute, data, or other materials do you need help obtaining to carry out your project? Will EAI be providing them? Do you have alternate sources of support? Feel free to add any additional relevant information.

created time in 3 months

issue openedopenai/jukebox

clip guided jukebox

has anyone applied clip to jukebox, see https://github.com/AndreyGuzhov/AudioCLIP

created time in 3 months

issue openedopenai/jukebox

multilingual jukebox

anyone interested in collected a multilingual dataset to train jukebox, possible close to 2M songs of raw audio?

created time in 3 months