jiashenggu's Projects
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Code for CodeT5: a new code-aware pre-trained encoder-decoder model.
C++ console application template using Bazel and googletest
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
👀
My personal homepage
KnowBert -- Knowledge Enhanced Contextual Word Representations
MetaFormer Baselines for Vision
Few-shot image classification based on CADA-VAE, using cosine similarity to align two modal features.
CVNets: A library for training computer vision networks
Code and models for mobile-former
[ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"
PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion
Prefix-Tuning: Optimizing Continuous Prompts for Generation
Progressive Prompts: Continual Learning for Language Models
A pre-trained GPT model for Python code completion and generation
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning