Comments (4)
Hi,
Thank you for your interest.
I suppose that your are training models with attention. Those models need to load features of size 14x14x2048xbatch_size which can be challenging.
That is why we trained our models with multiple SSD raid0 or SSD Pcie.
You can try to locate your bottleneck using htop and atop. It could come from your threads or the i/o times.
Please, let me know.
from vqa.pytorch.
Great, thanks for your feedback!
from vqa.pytorch.
Also another question--I noticed that when training the model for VQA 2.0 (and if I remember correctly, VQA 1.0 as well) with the default parameters on trainval, the accuracy peaks at around 60%. I assume you have a lot of experience tweaking the hyperparameters in the repo--do you have any intuition why this may be happening? I.e., I increased nans from 2k to 3k, but is it that? Or too much dropout? Any thoughts? The main issue seems to be with questions in the "other" category.
from vqa.pytorch.
Sorry for the late answer. Are you talking about the training accuracy ?
Did you already solved your problem ?
from vqa.pytorch.
Related Issues (20)
- Reproduce the problem using fusion scheme of concatenation HOT 2
- Hi cadene,why i get this error when i use demo? HOT 1
- iteration over a 0-d tensor when trying to run the demo HOT 7
- Hi, Cadene, why don't you update the feature extractor when training? HOT 1
- No learning rate decay? HOT 1
- 'OpenEnded_mscoco_val2014_model_accuracy.json' is not created HOT 2
- Left padding when encoding questions
- Batch first in LSTM
- Why don't you apply a softmax function before the final prediction? HOT 2
- The Link doesn't work: MutanNoAtt trained on the VQA 1.0 trainset HOT 1
- Results on test split
- LSTM avaliable?
- How to process the multiple choice answer HOT 1
- Feature extraction: CUDA out of memory HOT 1
- THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/THC/generic/THCStorage.c line=82 error=2 : out of memory
- FileNotFoundError: [Errno 2] No such file or directory: 'data/vqa2/raw/annotations/mscoco_train2014_annotations.json' HOT 1
- How did you create the attention maps in your readme? HOT 7
- sysntax error in line 80 HOT 1
- What should be the size of the input_question in engine.py ? HOT 2
- default vqa2/mutan_att_train example (also for demo) is messed
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 vqa.pytorch.