Coder Social home page Coder Social logo

Hello There 👋 A-suozhang Here

I am Tianchen Zhao, currently a Phd. student at NICS-EFC, EE Dept., Tsinghua University. My main research focus is Efficient Deep Learning algorithms, and software-hardware co-design. My recent research interest is Effiicent AIGC (diffusion-based generation methods).

📤 Feel free to contact me through [email protected] for discussion and cooperaion, and our lab is open for visting student, please ref here

I've done research about these compression techniques:

  • Network Pruning: (structural pruning for CNN)
  • Quantization: (binary network, low-bit training)
  • Neural Architecture Search: (participate in developing aw_nas a modularized NAS framework)
  • Adaptive Inference: (adaptive inference for 3D voxel-based CNN)

and these applications:

  • Autonomous Driving (3D Transformer & efficient lidar-based perception, intern at Novauto Inc.)
  • AIGC (efficient Diffusion methods)

tianchen's GitHub Stats, Rank: B+ (github-readme-stats.vercel.app)

github-readme-stats.vercel.app/api/top-langs/?username=A-suozhang&layout=compact&theme=vue

tianchen's Projects

aconvnet-pytorch icon aconvnet-pytorch

PyTorch implementation of Target Classification Using the Deep Convolutional Networks for SAR Images

ada3d icon ada3d

Code of ICCV23 paper: Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

ada3d.github.io icon ada3d.github.io

Project page for Ada3D: Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection

aw_nas icon aw_nas

aw_nas: A Modularized and Extensible NAS Framework

codedvtr icon codedvtr

code of [CVPR22] CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance

dpu_on_zcu102 icon dpu_on_zcu102

The Guidance For Installing dpu and some other stuff On Xilinx ZCU102

fb.resnet.torch icon fb.resnet.torch

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

fft-xilinx-ipcore icon fft-xilinx-ipcore

The implemention & test code for xilinx fft ip core(v 9.0), standard AIX4, for future reference

fifo2axi4 icon fifo2axi4

A Module To Read From Simple FIFO(with wr_en,rd_en), Give AXI4 Streaming Signal. Used For cases that DONOT Use AXI4Ffifo

find_max icon find_max

The Verilog find_max Code,reading Data From Streaming Data

gitignore icon gitignore

A collection of useful .gitignore templates

musclecontroller icon musclecontroller

This is the implementation code for MuscleController. a user-friendly controller based on EMG with Deep Learning Methods

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.