Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Object Detection via Faster R-CNN #43

Closed
pribadihcr opened this issue Jan 4, 2016 · 8 comments
Closed

Object Detection via Faster R-CNN #43

pribadihcr opened this issue Jan 4, 2016 · 8 comments

Comments

@pribadihcr
Copy link

Hi @beniz ,

faster RCNN like https://github.com/rbgirshick/py-faster-rcnn is a very useful application. It's implemented and trained in Caffe framework.
Do you have a plan to implement it in deepdeteect?

Thanks,

@beniz beniz self-assigned this Jan 4, 2016
@beniz beniz changed the title Object Detection Object Detection via Faster R-CNN Jan 4, 2016
@beniz
Copy link
Collaborator

beniz commented Jan 4, 2016

@pribadihcr yes it is indeed on the roadmap, though not fast-tracked yet. It would be useful if you could share what the most important features are for you regarding faster R-CNN wrt DD's API and server side. Typically, are you mostly interested in the training phase or an in-production prediction phase (while training with py-faster-rcnn) ? Regarding the models, are you looking forward using the existing set of pre-trained ones, or building your own ?

@pribadihcr
Copy link
Author

I think an in-production prediction phase is the first. We can train the
model using existing faster RCNN framework (e.g. py-faster-rcnn).
Regarding the models, well, I want to localize and detect spesific objects. So, I think I
need custom model.

On Mon, Jan 4, 2016 at 12:22 PM, Emmanuel Benazera <notifications@github.com

wrote:

@pribadihcr https://github.com/pribadihcr yes it is indeed on the
roadmap, though not fast-tracked yet. It would be useful if you could share
what the most important features are for you regarding faster R-CNN wrt
DD's API and server side. Typically, are you mostly interested in the
training phase or an in-production prediction phase (while training with
py-faster-rcnn) ? Regarding the models, are you looking forward using the
existing set of pre-trained ones, or building your own ?


Reply to this email directly or view it on GitHub
https://github.com/beniz/deepdetect/issues/43#issuecomment-168585714.

@beniz
Copy link
Collaborator

beniz commented Jan 4, 2016

OK, thanks, that was my guess. There are two possible ways of doing this. First is fast-tracking of features, and we do this through sponsorship. Current running sponsorships are not about images (as can be seen from last PR) and this is typically why faster-RCNN is not in yet. Second is slower track where the prediction pipeline can be brought in but with no deadline attached. Timeline for this one track also depends on whether you plan on participating in the development.
Regarding custom modeling, you can use some of the models we keep releasing (e.g. http://www.deepdetect.com/applications/model/) from the datasets we collect and process, or use private datasets of labeled data and build your own. Of course the currently relased image models are for classification, not detection, but we would certainly release some new ones once the faster-RCNN code is in, as needed. Let me know your thoughts and whether this can fit your needs.

@beniz
Copy link
Collaborator

beniz commented Jan 23, 2016

After review, py-faster-cnn is lacking some features for integration into production / commodity deep learning tools such as dd, more precisely:

These are just a few of the many details to consider in order to turn this into a commodity.

@zyyang
Copy link

zyyang commented Feb 24, 2016

FYI: caffe with py-faster-rcnn has been updated from original git.

@vuvko
Copy link

vuvko commented Apr 14, 2016

Hi, I'm helping with seminars on deep learning and one of them is about RCNN.
Thought it can be usefull, here's theano's implementation of RoIPooling (only gpu though): https://github.com/ddtm/theano-roi-pooling

@beniz
Copy link
Collaborator

beniz commented May 26, 2016

FTR, BVLC/caffe#4163 seems to be coming to Caffe. Once it is stabilized, we may merge it to our own modified version of Caffe, independently of whether it makes it to official Caffe. From there, there'll be a path for service integration into DD.

@beniz
Copy link
Collaborator

beniz commented Nov 21, 2016

Object detection now implemented via SSD, see PR #213. Closing.

@beniz beniz closed this as completed Nov 21, 2016
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

4 participants