Comments (2)
The problem was normalization of bbox features (including adding two extra dimensions like in the provided model) I had added to the GQA_v2 dataloader class (akin to GQA_v1). Had added it inside the training loop, so it wasn't applied in testing. Now works fine.
from meta-module-network.
The problem was normalization of bbox features (including adding two extra dimensions like in the provided model) I had added to the GQA_v2 dataloader class (akin to GQA_v1). Had added it inside the training loop, so it wasn't applied in testing. Now works fine.
The memory is out of utilization when I used
from meta-module-network.
Related Issues (14)
- Complete code release HOT 2
- Question about coordinate projection in TreeTransformerSparsePostv2 HOT 1
- Code for teacher model
- How much memory is needed to train the NLP model? HOT 1
- Failing to download gqa_features.zip continually
- Coarse-to-fine Parser HOT 1
- where does gqa_visual_features.zip come from? HOT 6
- GQA_hypernym missing. HOT 1
- missing en_emb.npy HOT 1
- Pretrained models HOT 1
- Code for CLEVR experiments? HOT 2
- Code for extracting features from Bottom up attention HOT 4
- Implement details of MMN w/o BS 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 meta-module-network.