vqa-mfb's Issues
Cannot re-implement result of MFH (FRCN img features) on COCO-VQA v2.0
The result reported is 68.76%. I use the features from Bottom-Up Attentionhttps://github.com/peteanderson80/bottom-up-attention, and use the same architecture as yours MFH, but only get 68.58% in the test-dev set. Is there anything different from the original MFH+CoAtt+GloVe? What should I pay attention to when re-implement? Thank you very much! Your code is very helpful!
pretrained model of MFH+RCN?
Thank you for your work !
Can you release the pretrained model of MFH+RCN as well?
Get feature through Trained with resnet 152 as backbone?
Hi,
Thanks for the excellent code base.
can i get the feature trained with faster rcnn and backbone resnet152?
I'm waiting for your reply.
Question about dataset
Hi Yu, when I am trying to run the code, I noticed that the config.py in mfh_coatt_glove contains some data files such as 'OpenEnded_mscoco_train2014_questions.json', but I have not found these files in the link you provided (http://visualqa.org/download.html). Could you please tell me where can I find those files? Thanks a lot.
Resuming training from last iteration
The original vqa-mcb didn't have build in support for restarting training which was due to the compact bilinear layer. Can this caffe implementation resume training from the last iteration?
The training process is much more time-consuming than other VQA systems.
In others paper, such as Bottom-Up Attention,training one network usually converges in 12-18 epochs, which takes in the order of 12-18 hours on a single Nvidia K40 GPU. However, this model takes me at least 9 hours to train an epoch, how many hours do you take in your side? Thanks!
A issue about dataset of VQA2 on preprocessing.
@yuzcccc Hi, Yu. When I do the preprocess for extracting features, I use the workstation with 2 TITAN. But the code use the GPU memory only 4G, the remaining 20G is not used, the code running speed is very slow. Could you tell me how to make full use of the 2 TITAN, and improve the code running speed?
FRCN Image features generation
Hi!
How did you generate the FRCN image features? Would you be willing to share that code?
Get the feature trained with faster rcnn and backbone resnet152?
Hi,
Thanks for the excellent code base.
can i get the feature trained with faster rcnn and backbone resnet152?
I'm waiting for your reply.
error on building caffe
[ RUN ] LayerFactoryTest/1.TestCreateLayer
src/caffe/test/test_layer_factory.cpp:47: Failure
Value of: layer->type()
Actual: "MatMul2"
Expected: iter->first
Which is: "MatMul"
[ FAILED ] LayerFactoryTest/1.TestCreateLayer, where TypeParam = caffe::CPUDevice (195 ms)
Any advice? I guess the error is due to the custom layer.
OpenEnded_mscoco_train2014_questions.json的预处理该如何处理呢
从OpenEnded questions中的annotations中怎么选取3000类答案
Question about MFB Baseline
This is a confirmation question about MFB Baseline. According to paper there should be two layers of LSTM with 1024-D hidden units each, but in the implementation only one LSTM layer with 1024-D is used. Kindly confirm.
Thanks
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.