- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I hope to see support for Mask R-CNN very soon.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@GoldenWings Thanks for the input. Any other suggestions or features you guys would want to see?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Api corresponding to distributed processing to multiple sticks is necessary, not cyclic processing.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Would like to see support for squeezenet and Tensorflow mobilenet SSD object detection.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I would in general like to see more support for different tensorflow ops. This would enable greater freedom in design of networks which would be really cool. :) Also more tutorials for maybe custom Networks. :)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Support for Tensorflow mobilenet SSD. The blog posts at movidius.github.io are quite good - additional topics by the same authors would be helpful.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Tutorials on getting new networks not already in the ncappzoo working on the sticks. Like DSOD - Densely Supervised Object Detectors. MobileNets-SSD is slow to train on Caffe. (and will remain until they start supporting an efficient Depthwise Separable Layer, in Caffe-SSD)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@trevor you should be able to use this link for training SSD with efficient DWS convolution with CUDNN9: https://github.com/listenlink/caffe/tree/ssd
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Please support Keras. I have everything setup with Keras in Ubuntu. I do not see particular reason to add Caffe in my system other than Movidius stick. Untill then example graph files that can be deployed in RPi would be appreciated.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Yolo support in all flavors ( not just tiny .. I prefer correct classification above fast&wrong )
- tested and forgiving installation script ( It's not fun to install NCSDK2 under Ubuntu studio/Mate 16.04/18.04 )
- Update all samples from appzoo to run under version 2
- Movidius "under the hood", low level api ?
Release date for Movidius X ??? ( this year !? )
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
It would be great if the stick will support Pytorch in the future
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
1) NCS kit in general is messy and loaded with Python dependencies. Straight C/C++ solutions would be best and a little python maybe for conversion / support.
2) install.sh just fails in so many ways on a vanilla clean install Ubuntu 16.04 - like it was never really tested.
3) find a way to enable a broader support community by open sourcing more tools (e.g. myriad compilers) and selecting a few outside partners to support smaller hobbyist / maker types.
4) get a partner program going - important to all of the above items
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
It would also be nice for better Raspberry Pi / TinkerBoard support during installation and compilation.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Internal processing FP32 compatible
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Correspondence to FusedBatchNormV2
- Correspondence to Caffe-Segnet
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
- Correspondence to caffe-jacinto
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
@Tome_at_Intel please merge outstanding pull requests and support the Github code! I just made a PR to fix a simple syntax bug, and I now see someone made the exact same pull request on the 27th Feb, 8 MONTHS ago, and it hasn't been merged!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I'm working on face recognition using MTCNN and Sphereface, and found that
- both v1 and v2 cannot change the input shape/ cannot get multi-output *(and when I try to concatenate the outputs.. bugs come, even worse is that the outputs can't be concatenate..)
- v2 doesn't support MTCNN, there's always info saying that no weights provided, list index out of range when I try to compile the graph. (btw, somehow many warning messages aren't that specific, they are even misleading)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Multioutput Support many awesome tensorflow models has many outputs, and the only model that the documentation teach you to compile to graph is incepction v3
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page