Comments (4)
Yes, these images are just the first 16 images on the cifar10 validation dataset. I didn't shuffle the dataset since I want to see how reconstruction gets better as we trained longer.
from mae.
Yes, these images are just the first 16 images on the cifar10 validation dataset. I didn't shuffle the dataset since I want to see how reconstruction gets better as we trained longer.
Sorry, maybe I didn't express the question clearly. My question is not about the selected 16 images from the dataset, but the reason why are those masks positions same? Theoretically, these masked patches should be shuffled randomly.
from mae.
Oh, I see.
Yes, the patches are shuffled randomly, and you can verify that by checking the visualization for different epochs (just scroll the tensorboard).
However, you get the same result as mine is because we fix the random seed at the beginning, which controls all the randomness. That is, if you run the code without changing the default random seed, you get exactly the same result I got, even for the positions that were masked in the last visualization.
from mae.
Oh, I see.
Yes, the patches are shuffled randomly, and you can verify that by checking the visualization for different epochs (just scroll the tensorboard).
However, you get the same result as mine is because we fix the random seed at the beginning, which controls all the randomness. That is, if you run the code without changing the default random seed, you get exactly the same result I got, even for the positions that were masked in the last visualization.
I see. Thank you very much!
from mae.
Related Issues (20)
- What are the rules for setting the parameters of vit-tiny's decoder? HOT 1
- Fine-tuning and linear evaluation HOT 4
- What are the versions you worked with, keep getting errors HOT 2
- Need help for reconstracting your experiments HOT 2
- how to make the masked patches not random HOT 2
- 最后你得重建图像是怎么来的? HOT 2
- Suspected minor bug HOT 1
- resource requirement HOT 2
- Ask some questions HOT 8
- tqdm is required package HOT 1
- Custom masking HOT 11
- train_classifier HOT 1
- 权重读取后重建图像不理想
- Expected dtype int64 for index HOT 3
- Could you provide a one-dimensional MAE implementation in pytorch? HOT 1
- The training loss is decreasing while the validation loss is increasing HOT 4
- Unable to reconstruct a distinguishable image HOT 5
- extracting embeddings HOT 1
- Turn off masking HOT 3
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 mae.