Can @ycui or someone else help me with a simple example how to use the SDRClassifierRegion to get prediction values?
I had tried to modify some examples provided in the Nupic project but the only one using CLAClassifier is the examples/network/hierarchy_network_demo.py and this example uses the customCompute function.
Which output of TPRegion I should connect with the SDRClassifierRegion? It will be connected to bottomUpIn (default input) or predictedActiveCells?
How to read the predicted values from the 3 outputs of SDRClassifierRegion?
Thank you in advance.
Best Regards,
Ruan Belém
2 Likes
ycui
May 19, 2016, 8:30pm
2
Here is an example that uses Encoder -> SP -> TM -> SDRClassifier for prediction.
## ----------------------------------------------------------------------
# Numenta Platform for Intelligent Computing (NuPIC)
# Copyright (C) 2013-2015, Numenta, Inc. Unless you have an agreement
# with Numenta, Inc., for a separate license for this software code, the
# following terms and conditions apply:
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero Public License version 3 as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU Affero Public License for more details.
#
# You should have received a copy of the GNU Affero Public License
# along with this program. If not, see http://www.gnu.org/licenses.
#
# http://numenta.org/licenses/
# ----------------------------------------------------------------------
This file has been truncated. show original
The parameters can be found in
# ----------------------------------------------------------------------
# Numenta Platform for Intelligent Computing (NuPIC)
# Copyright (C) 2013, Numenta, Inc. Unless you have an agreement
# with Numenta, Inc., for a separate license for this software code, the
# following terms and conditions apply:
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero Public License version 3 as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU Affero Public License for more details.
#
# You should have received a copy of the GNU Affero Public License
# along with this program. If not, see http://www.gnu.org/licenses.
#
# http://numenta.org/licenses/
# ----------------------------------------------------------------------
This file has been truncated. show original
1 Like
Dear @ycui ,
Thank you so much for your prompt answer but, at this time, I’m not using OPF. I am trying to use Network API directly. Do you have any example using the Network API instead OPF?
Best Regards,
Ruan Belém
You could take a look at the test file as an example of using the Network API with SDR classifier:
# ----------------------------------------------------------------------
# Numenta Platform for Intelligent Computing (NuPIC)
# Copyright (C) 2015, Numenta, Inc. Unless you have an agreement
# with Numenta, Inc., for a separate license for this software code, the
# following terms and conditions apply:
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero Public License version 3 as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU Affero Public License for more details.
#
# You should have received a copy of the GNU Affero Public License
# along with this program. If not, see http://www.gnu.org/licenses.
#
# http://numenta.org/licenses/
# ----------------------------------------------------------------------
This file has been truncated. show original
1 Like
Dear @subutai ,
Thank you for your time. This test is really useful.
Best Regards,
Ruan Belém
Sure. @ycui wrote it though