Comments (5)
Do you have plane to implement more CV algorithm or model? for example,DeepLab for image segmentation
from chainercv.
We are planning to work on image classification models and their train code.
DeepLab code is requested quite often, but we have no concrete plan to implement it yet.
from chainercv.
I just want to use chainer to implement a network, But last layer is modified from a already written C++ code. Do you have any suggestion?
How to plugin C++ code to chainer as a layer most convenient yet efficient.
from chainercv.
Are you talking about CRF layer?
You can call C++ functions from Cython code, but it may not be easy if you are not used to do this.
If you are interested in DeepLab network, I would suggest you to start from one without CRF.
The performance seems to be not bad without it.
See table 4 https://arxiv.org/pdf/1606.00915.pdf.
from chainercv.
Updated ChainerCV release plan
ChainerCV will continue to develop only on the master
branch.
Since there are users that use development version and stable version of Chainer, ChainerCV will try to support both versions of Chainer as much as possible.
The priority is on stable version of Chainer, and ChainerCV will be made sure to always work on the stable version.
The development version will be supported while it is possible to support the two versions simultaneously. This means that CI tests will run with the development version and the stable version.
In ChainerCV, new features added to Chainer will not be used. If a new feature is necessary, the relevant part can be copied to ChainerCV temporarily. In this case, the code will be deleted once the development version is released.
This will be deleted once this post is finalized.
- When new class/function is added to Chainer that ChainerCV's functionality needs to use. --> Copy the class until the development version becomes the stable version.
- When new feature is added to the existing class/function to Chainer --> Try to support it on both versions using if/else statements. If this is not feasible, only support this feature for the development version of ChainerCV.
- When recommended style of API usage changes (old style API is deprecated, e.g. deprecation of add_link in v2) --> Use the old style
- When destructive API change happens (old API is deleted, e.g. abolish of test kwarg in v2) --> We expect this kind of change extensively affecting ChainerCV will not happen in the near future.
from chainercv.
Related Issues (20)
- Faster RCNN training result problem HOT 2
- Add a img.resize function in utils HOT 2
- A function to return segmented image HOT 2
- no module named 'chainercv.datasets' HOT 6
- Problems of FCIS HOT 6
- Problem about eval_detection HOT 2
- Accuracy problems of FCIS example HOT 5
- loc_normalize_std in ProposalTargetCreator HOT 5
- yolo/train_v3.py does not work HOT 2
- DirectoryParsingLabelDataset fails to read images with an alpha channel
- Allow empty object bounding box for SSD training
- `neg_iou_thresh_lo` value in `ProposalTargetCreator`
- Is it fixed for loading the trained weights for FPN model? HOT 2
- Change Request in chainercv/examples/fpn/train_multi.py HOT 1
- build wheels for chainerCV failed HOT 1
- can't install environment, invalid channel HOT 3
- "Introduction to Chainer" doc link broken
- Request for train.py for YOLO
- eval_semantic_segmentation and calc_semantic_segmentation_confusion for when we have ignore label
- possible bug in the way that mIoU is computed
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 chainercv.