Comments (6)
Hi @LMdeLiangMi, I used 2 Tesla K40 GPUs, for a total of 48Gb of VRAM. It took about 30-40 minutes per epoch. I trained for about 350 epochs before reaching a good convergence for the from-pixels version so in the end my training took about 10 days.
from relationnetworks-clevr.
@LMdeLiangMi Never heard about Dali, it seems interesting! However, check your CPU utilization. If it is low, I can tell you that, during my experiments, I observed that the disk was very often the bottleneck. Consider moving the CLEVR dataset onto a solid-state drive, if you haven't yet. You should observe a higher utilization of both CPUs and GPUs, together with an overall training speedup.
from relationnetworks-clevr.
I see. Thanks.
from relationnetworks-clevr.
I found that the data loader seems so slow because it does the image processing on CPU. I am trying to write a new loader based on Nvidia Dali.
from relationnetworks-clevr.
@mesnico I put the dataset on memory and use Dali, so now it is okay. By the way, could you tell me why label subs 1 in utils.py?
label = (label - 1).squeeze(1)
from relationnetworks-clevr.
@LMdeLiangMi I'm glad you solved the problem.
By the way, could you tell me why label subs 1 in utils.py?
You can see that in the function build_dictionaries()
I employed the one-based indexing while constructing the dictionaries, both for the questions and the answers. This is basically because the index 0 is usually reserved for padding (the padding is not necessary for the answers, I did so for consistency with the questions dictionary).
However, while preparing the data for the network, I need to shift back all the answer indexes, otherwise I would have a useless output neuron corresponding to the dummy index 0.
from relationnetworks-clevr.
Related Issues (9)
- Terminating at Epoch 9 HOT 3
- Does not converge HOT 1
- Train/Val Accuracy HOT 17
- logfile is not showing any runs for the test set. The plots also don't show anything for test set and accuracy. HOT 2
- stack() fails HOT 2
- Do you know how to calculate the accuracy of the Count, Exists, Compare Numbers, etc HOT 2
- Training time? HOT 1
- AttributeError: Can't get attribute '_rebuild_tensor_v2' on <module 'torch._utils' from '/home/GoodPaperCode/RelationNetworks-CLEVR-master/env/lib/python3.6/site-packages/torch/_utils.py'> HOT 2
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 relationnetworks-clevr.