Comments (5)
10分钟一个epoch是不正常的速度,我放出来的nextvit-small在imagenet上的log也是在8A100上训练的,你那边如果也是8A100,训练速度应该和log中的速度对齐才是正常的,代码有更改吗?跑的是否是fp16?
from next-vit.
感谢您的回答!
应该是因为我跑的不是fp16。
from next-vit.
您好,
请问fp16是否是在from timm.utils import NativeScaler
中自动实现了?
我直接clone你们的代码运行,反复多次仍是10min/epoch,请问可能是哪里出了问题?
实现fp16是否仍需要其他的代码?
谢谢!
from next-vit.
from next-vit.
好的,感谢!
from next-vit.
Related Issues (20)
- 博主,fig5的问题
- Weights for the ablation studies HOT 1
- Patch embedding in each NCB and NTB?
- no relu before the global pool?
- Welcome update to OpenMMLab 2.0
- Some problems about Code
- 进行throughout时存在bug
- Dockerfile request
- Please provide CoreML Segmentation pretrained models
- 论文引用
- out_channels error
- outputs of the NextViT class
- Hosting model ckpts on Hugging Face
- 分类训练的路径问题 HOT 1
- 单GPU训练
- would you like to give us pretrained models in BaiduWangpan? thanks.
- how to deploy the Next_ViT detection? HOT 1
- Error in conversion to ONNX HOT 2
- 关于论文对E-MHSA的空间缩减率的描述疑问 HOT 2
- 论文fig5的问题 HOT 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 next-vit.