Comments (4)
通过与DPMv3的代码对照,LDM是不使用thresholding的,predict_x0=True效果会好一些。
from diff-sampler.
我未能复现LSUNbedroom LDM的结果。您能提供一下DPM++求解器的sample参数吗
from diff-sampler.
设置predict_x0=False反而work了,这很奇怪。看起来实现有一些问题
from diff-sampler.
1.我们最多使用了四张A100
2.Batch size: 主要依照显存来设置。四卡下,SD/ImageNet256/Bedroom取batch_size=32,Bedroom_LDM/ImageNet64/FFHQ64取batch_size=64,CIFAR10取128。
3.Leaning rate: 统一取5e-3
4.�kimg: 出于时长考虑,SD取5;其他统一取10。
5.对于SD/LDM/ImageNet256,我们默认取predict_x0=False,lower_order_final=True。对NFE=4下的Bedroom_LDM,lower_order_final=False效果更好
6.等目前的项目处理完后,我会在文档中更新主要实验设置
1.We use up to 4 A100 GPUs.
2.We set batch_size arroding to the graphics memory. Using 4 GPUs, we set 32 for SD/ImageNet256/Bedroom, 64 for Bedroom_LDM/ImageNet64/FFHQ64 and 128 for CIFAR10.
3.The learning rate is 5e-3 across all experiments.
4.kimg: mostly 10. Only for SD we use 5 considering the training time.
5.For SD/LDM/ImageNet256, we use predict_x0=False and lower_order_final=True by default. We find lower_order_final=False better for 4-NFE Bedroom_LDM.
6.Currenly working on other projects. Afterwards, I will update the main experimental settings in the document.
from diff-sampler.
Related Issues (14)
- 开源代码计划 HOT 1
- EDM 源码Heun的最后一步是Euler,没用AFS步数就是奇数,是怎么变成偶数的? HOT 1
- 为什么没有DEIS的结果的 HOT 5
- AFS实现有误 HOT 1
- scale_time 和 scale_dir 对结果有多大影响? HOT 1
- 为什么UniPC看起来比其baseline dpm++还差 HOT 1
- latent-space LSUN Bedroom 为什么是偶数NFE
- 请问最新的GITS sampler (On the Trajectory Regularity of ODE-based Diffusion Sampling) 的相关代码何时会开源呢? HOT 1
- 请问uniform和discrete schedule的区别是什么? HOT 1
- 关于GITS做DP过程的cost_mat计算的一点疑问 HOT 1
- ValueError: You should supply an encoding or a list of encodings to this method that includes input_ids, but you provided []
- integrate to svd HOT 1
- Reproduction code for Figure 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from diff-sampler.