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.