Comments (7)
@JialianW For learning rate adjustment, please follow the
Linear Scaling Rule
: smaller batch size with smaller learning rate, vice versa.
Hi @JialianW.
To be precise, if you use 0.5x
batchsize, then the linear scaling rule
(https://arxiv.org/abs/1706.02677) recommends using 0.5x
lr optimized via SGD
. But QueryInst
& Sparse R-CNN
as well as DETR
families use Adam
families to optimize, therefore the linear scaling rule
might be too harsh. E.g., DETR does not scale their lr even with batchsize = 64
. You can refer to some issues in the DETR repo (facebookresearch/detr#48 (comment)) for details.
For QueryInst
, we do use the linear scaling rule
when scaling up the batchsize. But I am not sure if there exists a better principle for QueryInst
& Adam
families.
from queryinst.
Hi @JialianW, thanks for your interest in our work!
As for the logs, we will release them in the near future and we will let you know in the first place, please stay tuned :)
As for the warnings, it is fine and just let the bullets fly.
from queryinst.
Thanks. For the learning rate, do we need to change two times smaller when using 4 GPUs? The default learning rate is for 8 GPUs?
from queryinst.
@JialianW For learning rate adjustment, please follow the Linear Scaling Rule
: smaller batch size with smaller learning rate, vice versa.
from queryinst.
Thank you! It helps a lot!
from queryinst.
This issue won't be closed until the training logs are released.
from queryinst.
QueryInst is now officially included by mmdetection library, with new checkpoints, corresponding logs, and augmented training settings.
https://github.com/open-mmlab/mmdetection/blob/master/configs/queryinst/README.md
from queryinst.
Related Issues (20)
- pytorch2onnx failed HOT 1
- AttributeError: 'EmbeddingRPNHead' object has no attribute 'async_simple_test_rpn' HOT 2
- mAP = 0 all the time HOT 7
- Code navigation: queries HOT 5
- Details about QueryTrack HOT 5
- which learning rate is true? HOT 2
- The parameter of the tracking loss HOT 2
- gpu HOT 2
- how to inference the pretrained model on my test data without GT HOT 1
- KeyError: "QueryInst: 'QueryRoIHead is not in the models registry'" HOT 1
- Base config file does not exist
- Instance Segmentation using CPU fails on certain images when Swin Transformer backbone was used
- cityscapes config HOT 10
- Why use 'batch-nms' in an end2end model?
- 您好,请问代码里是不是没使用预训练模型? HOT 1
- MMCV version
- Loss value when training QueryInst
- test stage mAP(box)=0, mAP(seg)=0.71 HOT 1
- Welcome update to OpenMMLab 2.0
- How to get QueryInst to train on an external dataset
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 queryinst.