Comments (3)
When samples_per_bn
is smaller than samples_per_gpu
, sync bn won't work so it is disabled. And note that the actual samples_per_bn
should be at least the same as samples_per_gpu
(samples_per_bn
=N x samples_per_gpu
, N>=1), so the actual samples_per_bn
will be the same as samples_per_gpu
by default if samples_per_bn
<samples_per_gpu
.
In source-domain pre-training, the best setup is to train with a batch size of 64 and global sync bn (samples_per_bn
=64). And in target-domain fine-tuning on 4 GPUs, the best setup is to train with a batch size of 64 and no sync bn (samples_per_bn
=16, 16x4=64). However, when conducting experiments on 8 GPUs (8 batch_size on each GPU), sync bn will be activated since two GPUs need to sync their BNs to perform samples_per_bn
=16.
from openunreid.
hi,@yxgeee, thanks for your detailed explanation, but why in target-domain fine-tuning, the best setup is to train with no sync bn. i am not familiar with domain adaptation, but this is against common practice in general training CNN.
from openunreid.
Such an optimal setup (16 samples for each BN and 64 samples in a mini-batch) was found empirically, as the re-ID dataset is sensitive to the number of batch size.
from openunreid.
Related Issues (20)
- AttributeError: module 'faiss._swigfaiss' has no attribute 'delete_SwigPyIterator' HOT 1
- Difference between OpenUnReID and the original MMT's implementation HOT 2
- Something about the Sampler HOT 1
- Implement of SpCL HOT 1
- spcl+在UDA上不能复现结果
- About Leaderboard. HOT 1
- strong_basline训练到后期acc突然降到0 loss变为nan HOT 3
- Faiss assertion 'err__ == cudaSuccess' failed in void faiss::gpu::runL2Norm(faiss::gpu::Tensor<T, 2, HOT 1
- 关于num_parts的问题 HOT 3
- Validation freq HOT 3
- Question about train loader
- Question about 'jaccard distance'
- 计算三元组损失时,特征需要归一化吗,代码里没有做归一化
- 这是什么问题?
- K-means for SpCL
- Loss becomes nan when I try to train MMT for 100 epochs
- severe overfitting with a single GPU HOT 2
- Ask for help for solving faiss assertion error HOT 1
- batchsize
- super strong baseline
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 openunreid.