Comments (2)
Hi, a padding token is generally masked such that unmasked tokens are not influenced by it. However, since these are tokens we do not need and do not influence the content tokens, we usually don't care about their values.
In your first example, you restrict all tokens in the first batch sequence to only look at the first two values. This includes the padding tokens, meaning that their new value depends on the first two tokens and thus are not zero. In the second case, you mask out everything for the padding tokens, which results in the division by zero.
Generally, which of the two options you choose is up to you, since they don't make a difference in the content tokens. If you prefer a clearer indication of where the padding tokens are throughout the network, you can go with option 2 and prevent NaNs. Otherwise, option 1 is the simpler version to implement.
from uvadlc_notebooks.
Thank you! And Thank you for maintaining these tutorials! They very detailed and really useful.
from uvadlc_notebooks.
Related Issues (20)
- Not really a bug: images don't show well with dark background HOT 2
- Prototypical Network Clarification from Tutorial 16 HOT 2
- Example job script in Guide 1 is depricated on Snellius HOT 1
- [Question] Computing normalization stats for RGB image datasets (CIFAR10, etc.) HOT 2
- [Question] ResNet pre actiovation blocks HOT 2
- [Question] Evaluating the loss for Autoencoders HOT 3
- About the same amount of images in every class HOT 1
- [Question] Use of MLP in Transformer Encoder/Decoder HOT 2
- test_anom_dataset raised RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly' HOT 1
- Can PositionalEncoding used with position information? HOT 1
- [Question] Tutorial 11, Variational dequantization HOT 3
- Introduction_to_PyTorch.ipynb: Mean Sigma Formula HOT 1
- Introduction_to_PyTorch.ipynb: Typo HOT 1
- [Question]Tutorial 3(Pytorch, JAX) Test accuracy for the model with sigmoid activation function HOT 2
- Activation_Functions.ipynb : Learning rate Notation
- "Getting runtime error" HOT 2
- New tutorial request to extend Normalizing Flow HOT 1
- unable to use tensorboard in "Tutorial 16: Meta-Learning - Learning to Learn"
- [JAX] Meta Learning Tutorial? 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 uvadlc_notebooks.