Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bytedance/diffusionengine

https://github.com/bytedance/diffusionengine

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.2%) to scientific vocabulary

Keywords

research
Last synced: 11 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: bytedance
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 12.8 MB
Statistics
  • Stars: 85
  • Watchers: 5
  • Forks: 5
  • Open Issues: 7
  • Releases: 0
Topics
research
Created over 3 years ago · Last pushed almost 3 years ago
Metadata Files
Readme License

README.md

DiffusionEngine

[Project Page]

Environment

```shell conda create -n DE python=3.10 conda activate DE

pip install torch torchvision python -m pip install -e detectron2 pip install -e . ```

Datasets

DE datasets are assumed to be placed in ./engine_output/ We provide COCO-DE, VOC-DE

Pretrained Models

Download the checkpoints and placed in ./pt_models/ - stable-diffusion-2-base - diffengmodelbest

Try DiffusionEngine with Gradio App

shell python diffusionEngine_gradio.py

Train your own DiffusionEngine

shell python projects/diffusionengine/train_net.py \ --config-file projects/diffusionengine/configs/dino-ldm/dino_sd2_512_5scale_90k.py \ --num-gpus ${GPUS_PER_NODE} --machine-rank ${RANK} --num-machines ${NNODES} \ --dist-url=tcp://${MASTER_ADDR}:${MASTER_PORT}

Dataset Scaling-up with DiffusionEngine

shell python projects/diffusionengine/train_net.py \ --config-file projects/diffusionengine/configs/dino-ldm/dino_sd2_512_5scale_90k.py \ --num-gpus ${GPUS_PER_NODE} --machine-rank ${RANK} --num-machines ${NNODES} \ --dist-url=tcp://${MASTER_ADDR}:${MASTER_PORT} \ -de \ train.init_checkpoint=pt_models/dino_sd2-0_5scale_bsz64_90k_model_best.pth \ train.engine_output_dir=${OUTPUT_DIR} \ train.seed=${SEED}

Dataset PostProcess & Regsiter

Add the engine output dataset dir in ./detectron2/detectron2/data/datasets/register_coco_de.py.

License

This project is released under the Apache 2.0 license.

Owner

  • Name: Bytedance Inc.
  • Login: bytedance
  • Kind: organization
  • Location: Singapore

GitHub Events

Total
  • Watch event: 12
  • Fork event: 1
Last Year
  • Watch event: 12
  • Fork event: 1

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 4
  • Total Committers: 1
  • Avg Commits per committer: 4.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
任玉羲 r****2@b****m 4
Committer Domains (Top 20 + Academic)
bytedance.com: 1

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 13
  • Total pull requests: 0
  • Average time to close issues: about 1 month
  • Average time to close pull requests: N/A
  • Total issue authors: 7
  • Total pull request authors: 0
  • Average comments per issue: 1.15
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Lucy-IM (4)
  • QJSQJS (1)
  • hhaAndroid (1)
  • AiXia520 (1)
  • rxmao (1)
  • GipsonLeo (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels