Comments (2)
This code uses per-example unrolling, which is indeed different from what the paper does. If you want to change it to cap at 15 words, you can modify _encode_question() to only use the first 15 tokens and always return a length of 15.
from pytorch-vqa.
Just wanted to confirm. Thanks!
from pytorch-vqa.
Related Issues (20)
- when running preprocess_images.py, "size mismatch" occured HOT 1
- Large memory consume HOT 1
- Preprocessed path and vocabulary path issue HOT 3
- Issue with train_loader and val_loader in train.py HOT 2
- ssd create issue HOT 1
- why attention use '+' instead of '*' HOT 1
- Metric computation in training phase HOT 2
- EOFError: Ran out of input when training HOT 5
- concat or sum? HOT 4
- Runtime error with preprocess-images
- About attention showing in the pic
- Mismatch in Computing Accuracy HOT 1
- AttributeError: module ‘torchvision.transforms’ has no attribute ‘Scale’ HOT 3
- Training time HOT 4
- answer normalization HOT 3
- Information regarding training time HOT 1
- run without CUDA HOT 7
- Test the model HOT 5
- Working with abstract scenes VQA v1 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 pytorch-vqa.