Comments (10)
@TinnyFlames @TinnyFlames Not straightforward, we have tried to pre-train the vit-base 100 epochs with hog prediction in ImageNet-1k under the MAE architecture. The hog targets is slightly higher than the pixel norm (82.7% vs 82.4%).
from videotransformer-pytorch.
Hi @mx-mark! Thanks for your reply. Is it possible to share suggestions on implementing the mask code? I tried to implement maskfeat for Imagenet but was confused about the mask part. The image size is (224,224,3) but the hog feature size is (14,14,108). If we randomly mask image patches, how to mask the hog features correctly since the dimension is not matched?
CubeMaskGenerator
is a little bit obscure to rewrite for me.
from videotransformer-pytorch.
@mx-mark May I ask you how you calculate your loss function in the imagenet? just as the same as this?
https://github.com/mx-mark/VideoTransformer-pytorch/blob/main/video_transformer.py#L899
from videotransformer-pytorch.
@RechelTeamo right, the loss minimizes the L2 distance between the predicted and original HOG feature.
from videotransformer-pytorch.
Thanks for your answer.
I try this loss function. But I meet the problem that my loss becomes NaN. I find this problem in the blocks(x). I think the problem is lr. May I ask about your lr setting? I use blr=1e-4 and batch size 1024 in 8 V100 GPU.
from videotransformer-pytorch.
@RechelTeamo the setting for what, pre-training or fine-tuning?
from videotransformer-pytorch.
for pre-training
from videotransformer-pytorch.
@RechelTeamo There are some related problems reported in the original MAE repos. You can check if it works facebookresearch/mae#65, facebookresearch/mae#42
from videotransformer-pytorch.
@RechelTeamo For my pretraining settings, the blr is 1.5e-4 and the effective batch size is 4096.
from videotransformer-pytorch.
@mx-mark Oh thanks a lot. I set blr: 5.00e-05 and batch 1024 (actual lr=2e-4)now it's epoch 16. I will report my result when it is finished.
My blr=1e-4 batch=1024 (actual lr=4e-4) will loss NaN.
from videotransformer-pytorch.
Related Issues (20)
- How do we load ImageNet-21k ViT weights? HOT 3
- Vivit Training Problem HOT 1
- What is the final score of maskfeat? HOT 6
- torch version HOT 1
- How to load Tensorflow checkpoints? HOT 3
- Missing keys in demo notebook HOT 4
- How to dataloader? HOT 2
- structure of ViViT-b HOT 1
- Errors when loading pretrained weights -pretrain_pth 'vivit_model.pth' -weights_from 'kinetics' HOT 1
- Question about Loading a pretrained model(ViT)
- Log-File for ViViT finetuning with Imagenet pre-train Weights
- How to convert TimeSformer Implementation For Regression Tasks
- While training viti I am getting thsi error
- 代码写的真好
- regarding fine-tuning ViViT model on my dataset.
- How can ViViT be used to extract video features?
- How Can I Create a Video_Loader Function That Lets Me Use My Own Videos With ViViT?
- where is vit-b pretrained model on imagenet-21k?
- How to test my trained model?
- how to make datasets use my own videos
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 videotransformer-pytorch.