Comments (4)
I think that running in batch mode will require nontrivial changes.
The current design is that the network accepts a single image of shape (1, C, H, W); the Localization Layer produces N regions of interest for the single image, and these region proposals end up in the minibatch dimension. If you wanted to run in batch mode, each image could potentially give rise to multiple regions of interest; you would need to keep track of the mapping between input image indexes and region proposal indexes, which would require modifying a number of files.
from densecap.
@jcjohnson thanks
from densecap.
@truskovskiyk Was your attempt successful in running batch mode ?
I also have a large data, which would take a lot of time if the batch size is 1. I was also trying to modify the code, but got stuck at Localization Layer. Particularly at expandAs since it only supports singleton expansion.
A trivial work around would be to just loop through all CNN features, but that's a bad idea. Any other thoughts ?
from densecap.
@abhinavagarwalla Unfortunately, I don't create batch mode. For my project now I use https://github.com/tensorflow/models/tree/master/im2txt which show greater improvements, wich shows greater result when train model with CNN
from densecap.
Related Issues (20)
- evaluate_model error of 'bad argument' HOT 3
- libjpeg and libpng version problem HOT 3
- Why gradients can not be propagated backward to the input proposal coordinates in the RoI pooling layer?
- users/my-name/torch/install/bin/luajit: cannot open run_model.lua: No such file or directory HOT 1
- Warning: cudnn.convert does not work with nngraph yet. Ignoring nn.gModule1/1 processing image imgs/elephant.jp
- run_model.lua unknown error
- Can't evaluate pretrained model HOT 2
- wrong jpeg library version 62: caller expects 90 iOS HOT 1
- Invalid URL at http request in server-client webcam demo
- No LuaRocks module found for densecap-master/densecap/DenseCapModel HOT 8
- cjson.so: undefined symbol: lua_objlen stack traceback: train.lua HOT 3
- In search of a Tf / Py-Torch Implementation. HOT 5
- training on new datasets of 100 random images.
- invalid pretrained model HOT 1
- Chinese image caption, In the result, multiple words of the same type appear
- th run_model.lua HOT 2
- When I install luarocks in Ubuntu, I came across a problem HOT 6
- VGG dataset issue HOT 1
- Segmentation fault (core dumped) HOT 1
- How do I determine the value of max_iters?
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 densecap.