Comments (2)
Exactly, since the modules aren't the same for each question (and even the length of each question varies) we have to construct a question-specific network and forward input one by one. Ultimately, this doesn't become too much of a problem.
I don't recall exactly how long things took, but it was in the neighbourhood of 45 minutes per epoch on CLEVR's 700,000 questions. A safe bet is somewhere between 30 minutes to an hour. The bulk of the work was on two different machines: a server with K80 GPUs and Xeon E5-2698 CPUs and a desktop with 1080TIs and i7-7700K CPU.
You can see the full training setup in our notebook. To summarize: batch size is 128 and we use 2 workers in the PyTorch DataLoader. All of our work was on a single GPU. If training time is a very big concern (you need it to take less than the roughly one day training took us) there are some inefficiencies that I'm sure could be improved upon.
Side note: I went ahead and edited your comment to fix the link.
from tbd-nets.
Great, thank you for the answer!
from tbd-nets.
Related Issues (14)
- Training the model Step 2
- Properties not specified in modules? HOT 1
- About converting HDF5 to npy HOT 1
- Version bumps HOT 2
- `imresize` was removed in scipy 1.3 HOT 2
- can not find file scripts/extract_features.py HOT 2
- The environment setting HOT 6
- How to evaluate test results? HOT 4
- evaluate error on val HOT 8
- tensor matches error HOT 10
- No longer runs on mybinder.org HOT 4
- RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn HOT 3
- What's the use of cat operation in SameModule 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 tbd-nets.