Greetings,
Noticed in PyBOMBS 2.1.0Fresh and stock Ubuntu 16.04 on intel 4 core.
https://github.com/apache/thrift.git.
PyBOMBS.Fetcher - ERROR - [Errno 2] No such file or directory:
'/home/gratcliff/gnuradio/.pybombs/inventory.yml'
PyBOMBS.Packager.source - ERROR - Problem occurred while buil
I have made a lot of progress but am now at a sticking point.
I am using the version of Qt that comes with RHEL6u6, which is version 4.6.2
Scanning dependencies of target gnuradio-qtgui
[ 77%] Building CXX object
gr-qtgui/lib/CMakeFiles/gnuradio-qtgui.dir/__/include/gnuradio/qtgui/moc_spectrumd
Hi Martin,
I'm just going to have a look through a number of their publications at
https://wireless.vt.edu/publications.html
I'm now looking at http://arxiv.org/abs/1602.04105# too which looks very
interesting!
If you have any other URLs regarding Virginia Tech & TensorFlow, I'd be
very interest
Christopher,
there's a bunch of researchers at Virginia Tech using Tensor Flow (and
other ML techniques) for signal classification, and other DSP related
tasks. Have you looked into their efforts? It would be a shame to see
time going into duplicate work.
Cheers,
Martin
On 06/29/2016 01:23 AM, C
Kevin:
Thank you for the quick and complete reply, I appreciate the help!
-Ed
On Wed, Jun 29, 2016 at 11:04 AM, Kevin Reid wrote:
> On Jun 29, 2016, at 07:50, Ed Coleman wrote:
> > if __name__ == '__main__':
> > simpleTone().run()
> >
> > The code above works fine, however if I make the f
Hi everyone,
we're very happy to announce that we will be doing another set of
tutorials at this year's GRCon. The tutorial is free, and will happen on
the new user's day at GRCon (Mon, September 12th), *but* it requires
that you purchase a ticket for the new user's day, should you have not
alread
This is not the first time this has come up, and yes, patches are
welcome. The simplest fix might be to add a factory-time argument that
disables the resampler entirely -- this will guarantee no sample
offsets, ever, but of course will not allow to change the timing offset
at runtime.
M
On 06/28/
On Jun 29, 2016, at 07:50, Ed Coleman wrote:
> if __name__ == '__main__':
> simpleTone().run()
>
> The code above works fine, however if I make the following substitution:
>
> if __name__ == '__main__':
> simpleTone().start()
> simpleTone().wait()
> #time.sleep(3)
> simpleTon
I'm experimenting with writing GNUradio scripts in python. My eventual goal
is to have a routine that periodically writes a floating point result from
within a GNUradio process to the serial port. As a first step I wanted to
try and interact with a simple routine by simply pausing after a short tim
Hi Stefan,
Thanks for your reply.
I'm currently working on a GNU Radio block which will be able to load any
TensorFlow
graph, which would allow different types of models to be utilised.
At the moment in my repository only a single hidden layer is utilised with
no convolutional
layers.
cheers
C
Hi,
The classification accuracy looks good! But some questions:
Will you compare the performance with non-tensorflow machine learning
algorithms such as boosted decision trees or support vector machines
(e.g. provided by scikit-learn or xgboost)?
Your model is a deep neural network, so there is
Hi Everyone,
I've just posted a blog article on what I've been working on
recently - https://signalsintelligence.wordpress.com/2016/06/24/tensorflow/
I'm now going to work on making a block for GNU Radio, which makes use of
TensorFlow to classify signals.
cheers
Chris
__
Here's an example block that's very similar to what you want to do.
https://github.com/gnuradio/gnuradio/blob/master/gr-dtv/lib/catv/catv_frame_sync_enc_bb_impl.cc
Note the use of set_output_multiple() and the forecast function.
Ron
On 06/28/2016 10:48 AM, Olivier Goyette wrote:
I did a simpl
Hi Olivier,
I can't find anything in your code that checks if you actually print
valid data. See [0] for a description of C++ GNU Radio blocks and how
they work.
Since you use a block of type 'block', make sure you get an idea of
'general_work' parameters, its return value and 'consume_each'
14 matches
Mail list logo
