Comments (4)
Thanks for your interests!
- This option should be enabled all the time :)
- To make the transformer aware of the mask positions, we use special tokens to denote the missing elements of input sequence following original BERT model in NLP. You could also try to add such constraints while performing attention to see what will happen.
- Great question! I think it relys on how you sample the exact token from current distribution. Selecting the token with top probability will lead to good pixel quality but low diversities, and vice versa. In the paper we just adopt the most naive way for sampling. Considering the property of bi-directional transformer, I believe there exists more robust and efficient sampling strategy could be explored :)
from ict.
Thanks for your reply. I completely understood 1 and 2.
About question 3, I want to confirm the question with you. I want to know about why we can select the pixel in first masked position each sampling like code in sample_mask function
Line98, uitl.py , since the model generate all masked pixels a time which have no difference in mask region in training. Is it more reasonable to select the position who have the highest/Top-K probability in the rest of mask region each sampling.
from ict.
Thanks for your reply. I completely understood 1 and 2.
About question 3, I want to confirm the question with you. I want to know about why we can select the pixel in first masked position each sampling like code insample_mask function
Line98, uitl.py , since the model generate all masked pixels a time which have no difference in mask region in training. Is it more reasonable to select the position who have the highest/Top-K probability in the rest of mask region each sampling.
Absolutely. You could try the mentioned sampling strategy to see if the performance will become better. Currently I just sample the token in the sequential order.
from ict.
I see, thanks!
from ict.
Related Issues (20)
- Will your kmeans data work well on other domains? HOT 5
- About the validation_path of Transformer training. HOT 2
- About the test effect is not good HOT 3
- About the missing parameter 'loader' in Guided Upsampling when inference is done HOT 2
- Enable --random_stroke option but the mask path is still the default
- ### Something Wrong ### HOT 1
- What's wrong with the results?
- Pretrained weight of upsampler of Places does not work well. HOT 1
- About mask ratio of the pretrained models
- ProcessExitedException: process 0 terminated with signal SIGKILL HOT 3
- New easy to use inpanting method with transformers
- Downloading pretrained models from a non-Baidu source
- ProcessExitedException: process 0 terminated with signal SIGKILL #38
- where is the mask path
- TypeError: 'NoneType' object does not support item assignment
- 您好,我想知道使用自己的数据集训练模型的话,需要改哪些地方呢
- Transformer训练过程中的问题
- 训练问题
- RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:75] data. DefaultCPUAllocator: not enough memory: you tried to allocate 17179869184 bytes. Buy new RAM!
- Regarding the bi-directional attention you mentioned in the article
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 ict.