Giter Site home page Giter Site logo

dim's Introduction

DiT with MoE \ Mamba Block

This repository is a modification of fast DiT. It provides two different blocks.
The first block is based on the MoE (Mixture of Experts) module. The second block is a re-implementation of the bi-mamba block, inspired by DIFFUSSM and Vim

The version 2 and 3 of the bi-mamba block is as follows:

bi-mamba v2

see models.py for details.

There is no completed training version yet.

There are some experimental results:

DiT Model Train Steps FID-50K
(PyTorch Training)
PyTorch Global Training Seed
XL/2 400K 18.1 42
B/4 400K 68.9 42
B/4 400K 68.3 100
------------ ------------- -------------------------------- ------------------------------
DiM-B/4 400K 58.6 0
DiM-L/2 400K 19.8 0

Sampling of DiM-L/2(400K Step)

sample

Preparation Before Training

To extract ImageNet features with 1 GPUs on one node:

bash extract_feature.sh

Training

To launch DiT-XL/2 (256x256) training with N GPUs on one node:

bash train.sh

Evaluation (FID, Inception Score, etc.)

bash sample_ddp.sh

generates a folder of samples as well as a .npz file which can be directly used with ADM's TensorFlow evaluation suite to compute FID, Inception Score and other metrics.

dim's People

Contributors

zqgong avatar

Stargazers

 avatar yh avatar

Watchers

 avatar

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.