Comments (5)
Thanks for the feedback. Could you specify which model/config are you referring to?
from tadaconv.
Please refer to the following link. (
TAdaConv/configs/pool/base.yaml
Line 65 in 75b7839
from tadaconv.
Yes, if you wish to turn on EMA, you will have to manually enable ema and set the ema decay factor in your config file to run. We indeed used EMA during training TAdaFormer, but we actually observe negligible performance differences for the ema models and the original model. Therefore, turning on ema is not a must for training TAdaFormers.
from tadaconv.
As mentioned in your paper, turning on the ema mode may prevent the model from over-fitting problems. I am curious how important it is for training.
from tadaconv.
It affects the top-1 accuracy by 0.2~0.4 for large models.
from tadaconv.
Related Issues (20)
- Issue on running on sthv2 HOT 2
- Problems on loading imagenet weight HOT 1
- features HOT 2
- Use TAdaConv in Video Object Detection? HOT 1
- How to use R(2+1)D with TAda? HOT 1
- some questions about flops and inference time HOT 1
- TAdaConvNeXt-T HOT 3
- Frame description and temporal modeling HOT 1
- Applying TadaConv HOT 1
- Batch-wise and Temporal-wise modeling HOT 1
- I am curious about why the flops and parms of TAdaConvNeXt-T is one half of the ResNet50's, to my knowledge they should be similar. HOT 2
- apply AdaConv to P3D or SlowFast HOT 1
- Applying TAdaConv3d to Timesformer HOT 2
- top1-5 accuracy did not achieve the expected effect(Mosi/Finetuned on UCF101/HMDB51 dataset) HOT 12
- TAdaConv2d needs in_channels to equal out_channels HOT 1
- Enquiry on the batch size when using 32-frames HOT 2
- In Mosi, training on hmdb51 based on the pre trained checkpoint you provided cannot reproduce the results HOT 1
- Question on reproducing the results on sthv2
- RuntimeError: Error(s) in loading state_dict for BaseVideoModel: size mismatch for head.out.weight: copying a param with shape torch.Size([400, 768]) from checkpoint, the shape in current model is torch.Size([5, 768]). size mismatch for head.out.bias: copying a param with shape torch.Size([400]) from checkpoint, the shape in current model is torch.Size([5]). HOT 1
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 tadaconv.