ccszhang

ccszhang's Stars

• facebookresearch/sapiens

  High-resolution models for human tasks.

  Language:Python4.5k249

• meta-llama/llama3

  The official Meta Llama 3 GitHub site

  Language:Python27.1k3.1k

• karpathy/nn-zero-to-hero

  Neural Networks: Zero to Hero

  Language:Jupyter Notebook11.9k1.5k

• lanl/vision_transformers_explained

  This folder of code contains code and notebooks to supplement the "Vision Transformers Explained" series published on Towards Data Science written by Skylar Callis.

  Language:Jupyter Notebook6216

• higher-hai/video_model_impl

  Deep learning for video object detection, video semantic segmentation, video object tracking and video pose estimation.

  Language:Jupyter Notebook1

• tsb0601/EMP-SSL

  This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."

  Language:Python22012

• geekan/MetaGPT

  🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

  Language:Python45.2k5.4k

• XiaokunSun/SemanticHuman

  [CVPR 2023] Official repo of "Learning Semantic-Aware Disentangled Representation for Flexible 3D Human Body Editing“

  Language:Python301

• vijishmadhavan/Crop-CLIP

  Crop using CLIP

  Language:Jupyter Notebook33634

• jmtomczak/intro_dgm

  "Deep Generative Modeling": Introductory Examples

  Language:Jupyter Notebook1.1k176

• open-mmlab/mmskeleton

  A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

  Language:Python2.9k1k

• Spico197/random-luck

  Automatically select the best random seed based on ancient Chinese I Ching. Good luck and best wishes !

  Language:Python446

• younesbelkada/interfacegan

  InterfaceGAN++: Exploring the limits of InterfaceGAN. In this repository, we propose an approach, termed as InterFaceGAN++, for semantic face editing based on the work from Shen et al. Specifically, we leverage the ideas from the previous work, by applying the method for new face attributes, and also for StyleGAN3. We qualitatively explain that moving the latent vector toward the trained boundaries leads in many cases to keeping the semantic information of the generated images (by preserving its local structure) and modify the desired attribute, thus helps to demonstrate the disentangled property of the StyleGANs.

  Language:Python6210

• microsoft/FaceSynthetics

  82260

• facebookresearch/luckmatters

  Understanding Training Dynamics of Deep ReLU Networks

  Language:Python27831

• google-research/vision_transformer

  Language:Jupyter Notebook10.4k1.3k

• openai/guided-diffusion

  Language:Python6.3k822

• openai/improved-diffusion

  Release for Improved Denoising Diffusion Probabilistic Models

  Language:Python3.3k487