Comments (6)
choys73
commented on June 28, 2024
1
I solved the problem by installing luajit!
And I install the hdf5 version 1.10.
from visdial.
abhshkdz
commented on June 28, 2024
Not completely certain of the fix, but might be worth trying google-deepmind/torch-hdf5#79 (comment)
from visdial.
yellowjs0304
commented on June 28, 2024
I appreciate your help, but I have not found the solution.
from visdial.
wanyao1992
commented on June 28, 2024
@yellowjs0304 have you solved the problem? I encounter the same problem.
from visdial.
abhshkdz
commented on June 28, 2024
@wanyao1992 @yellowjs0304 could you try this with luajit instead of lua 5.1 please. That seems to have fixed it for a bunch of people on the issue referenced above.
from visdial.
yellowjs0304
commented on June 28, 2024
@wanyao1992 @ChoYS96
No way, it is not a good solution.
I installed the LuaJit instead of lua5.1 and the issue about line 579 is gone.
But in extracting the image feature, It occurs out of memory error.
from visdial.
Related Issues (20)
- Generate the new data_img.h5 from prepro_img_pool5.lua HOT 10
- Inconsistent tensor size, training with mn-att-ques-im-hist HOT 1
- Error in forwardbackward() function while training the data HOT 1
- Evaluation of pretrained late fusion model fails HOT 1
- Update pretrained checkpoints HOT 1
- bad argument #2 to 'add' (sizes do not match at /torch-addons/cutorch/lib/THC/generated/../generic/THCTensorMathPointwise.cu:269) HOT 3
- Why is the dimension of input image features in attention case 14x14x4096? HOT 1
- Issue with prepro.py at line 150. HOT 3
- dimension doesn't match during evalution HOT 7
- Pytorch starter code HOT 2
- why 80,000 visual feature? not 82,783
- Error with command "python prepro.py -download 1 -image_root /path/to/coco/images HOT 1
- Is there any particular reason why you add +1 HOT 1
- Wrong filename for visdial_data_{}.h5 in VisDial v1.0 HOT 1
- Invalid permutation error reading image feature you gave HOT 2
- Support for extracting conv layer / spatial features for ResNets (for attention-based models) HOT 1
- The chat interface of visual dialog on this page: https://visualdialog.org/ is not working. HOT 1
- How did you generate Figure 5 in your paper? HOT 1
- THCudaCheck FAIL error=2 : out of memory... MultiGPU training
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 visdial.