Comments (3)
According to the paper (Section 4.1), you mentioned the best result (80.2%) was achieved by training ResNet-50 with an SGD optimizer. However, from the config files provided in this repo, AdamP is used for ResNet-50+ReLabel+CutMix. I am wondering that which optimizer did you use for training with CutMix? Looking forward to your reply. Thanks!
from relabel_imagenet.
Thank you for the inspiring work! I have read the paper and the code, and would like to raise a question about the selection of the training hyper-parameters. Specifically, I found that you use custom setups for optimizers (e.g., SGD v.s. AdamP, learning rate, weight decay, etc.) in three configs (baseline, relabel, relabel+cutmix). I am wondering that how did you tune it? Are there any policies? Thanks!
According to the paper (Section 4.1), you mentioned the best result (80.2%) was achieved by training ResNet-50 with an SGD optimizer. However, from the config files provided in this repo, AdamP is used for ResNet-50+ReLabel+CutMix. I am wondering that which optimizer did you use for training with CutMix? Looking forward to your reply. Thanks!
Yes, we used AdamP
optimizer when applying CutMix
regularization for further improvement.
Otherwise, we used SGD
optimizer.
For your information,
ResNet-50+ReLabel+CutMix
withSGD
: 79.8%ResNet-50+ReLabel+CutMix
withAdamP
: 80.2%
The hyperparameter for AdamP
is described in our config file (relabel_train_resnet50_cutmix.yaml). We tuned the lr
and wd
for AdamP
by grid search.
We will add these details in Section 4.1.
Thank you for pointing it out!
from relabel_imagenet.
Thanks a lot for your reply!
from relabel_imagenet.
Related Issues (13)
- Relabel data HOT 6
- Relabel maps generating code HOT 1
- Dataset Downloading HOT 4
- ImageNet of Validation HOT 3
- Crop Coordinate Calculation. HOT 1
- LabelPooling in 4.3 Multi-Label Classification HOT 1
- infer HOT 1
- Relabling on cutmix ? HOT 5
- Reproduce resnet 18 + relabel HOT 5
- about dataset download HOT 2
- about relabel dataset HOT 3
- How to relabel imagenet? HOT 2
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 relabel_imagenet.