Comments (6)
Thanks for your question. The validation error plot in (b) is without EMA while the validation accuracy in (c) is with EMA.
from ml-cvnets.
Thanks a lot for the reply. It is surprising that the EMA strategy can rise so much. My previous experimental conclusions are basically between 0-0.2%.
By the way, the top-1 accuracy of the standard training method is only 77% without using the EMA strategy?
from ml-cvnets.
Our experiments also suggests that EMA improves performance by 0.2-0.3%.
The top-1 accuracy without EMA is about 78%. The difference we observe in graph is because part (c) performance is measured after the training on a single GPU ensuring batches are neither truncated nor padded. While the data for plots in (b) are measured during training. For (b), depending on the batch size, there could be cases when dataset size is not multiple of batch size. For example, for ImageNet, we have 50k validation images. If we use a batch size of 1024 for computing validation statistics during training, then few batches will be either truncated or padded. So, training/validation curves could be bit noisy.
Hope this helps.
from ml-cvnets.
Ok! Thanks for your reply. However, I still have some questions. According to what you said, I reproduced the process. Although there will be some differences in accuracy, it will not be as big as 1%. I would like to take the liberty to ask, can you provide the training log here?
I look forward to your reply.
from ml-cvnets.
Hi @cuicheng01 ,
Extremely sorry for the late response. I did not realize that I did not respond to your comment.
Here are the training/validation/validation + EMA loss curves. Hope this helps.
from ml-cvnets.
Closing issue because of no activity.
from ml-cvnets.
Related Issues (20)
- Questions about the file bytes length of ByteFormer HOT 3
- How to solve this problem:ModuleNotFoundError: No module named 'cvnets.models.classification.' HOT 5
- Normalization Params
- 'nan' loss when training 'ByteFormer' using ImageNet
- Runtime error on single GPU Linux environment training HOT 1
- Not possible to test ByteFormer HOT 5
- Cross Attention Computation in LinearSelfAttention()
- [Feature Request] Docker container
- Segmentation model conversion size mismatch HOT 1
- Size mismatch error when loading a pretrained model HOT 1
- The license of pretrained weights
- Question: Do you have removed the support for video classification? HOT 2
- crash if different number of classess within `train/test` set HOT 6
- VIT-tiny weights and config dont match? HOT 1
- How to convert segmentation model results into VNInstanceMaskObservation? HOT 4
- ModuleNotFoundError: No module named 'main_train' HOT 2
- Using vision transformers for different image resolutions HOT 1
- ModuleNotFoundError: No module named 'main_train'
- ModuleNotFoundError: No module named 'main_train'
- AttributeError: 'NoneType' object has no attribute 'size' 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 ml-cvnets.