Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
huolongshe bf1fd89051 | 2 months ago | |
---|---|---|
app | 2 months ago | |
docs | 2 months ago | |
.gitignore | 2 months ago | |
Dockerfile | 2 months ago | |
LICENSE | 2 months ago | |
README.md | 2 months ago | |
application.yml | 2 months ago | |
build-docker.sh | 2 months ago | |
pack_model.py | 2 months ago | |
pip-install-reqs.sh | 2 months ago | |
requirements.txt | 2 months ago | |
run_model_server.py | 2 months ago |
Score-Based Generative Modeling through Stochastic Differential Equations (SDE)
Paper: Score-Based Generative Modeling through Stochastic Differential Equations
Authors: Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
Abstract:
Creating noise from data is easy; creating data from noise is generative modeling. We present a stochastic differential equation (SDE) that smoothly transforms a complex data distribution to a known prior distribution by slowly injecting noise, and a corresponding reverse-time SDE that transforms the prior distribution back into the data distribution by slowly removing the noise. Crucially, the reverse-time SDE depends only on the time-dependent gradient field (\aka, score) of the perturbed data distribution. By leveraging advances in score-based generative modeling, we can accurately estimate these scores with neural networks, and use numerical SDE solvers to generate samples. We show that this framework encapsulates previous approaches in score-based generative modeling and diffusion probabilistic modeling, allowing for new sampling procedures and new modeling capabilities. In particular, we introduce a predictor-corrector framework to correct errors in the evolution of the discretized reverse-time SDE. We also derive an equivalent neural ODE that samples from the same distribution as the SDE, but additionally enables exact likelihood computation, and improved sampling efficiency. In addition, we provide a new way to solve inverse problems with score-based models, as demonstrated with experiments on class-conditional generation, image inpainting, and colorization. Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9.89 and FID of 2.20, a competitive likelihood of 2.99 bits/dim, and demonstrate high fidelity generation of 256 x 256 images for the first time from a score-based generative model.
模型来源: https://hf-mirror.com/google/ncsnpp-celebahq-256
本模型基于 ServiceBoot微服务引擎 进行服务化封装,参见: 《CubeAI模型开发指南》
$ sh pip-install-reqs.sh
$ serviceboot start
或
$ python3 run_model_server.py
一键式本地容器化部署和运行,参见: 《CubeAI模型独立部署指南》 或 CubeAI Docker Builder
本模型服务可一键发布至 CubeAI智立方平台 进行共享和部署,参见: 《CubeAI模型发布指南》
No Description
Python Shell Dockerfile Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》