This is an
implementation report of the article ‘How to run Keras model on Movidius NCS’. You can read the article at:
‘Source code for this post available on my GitHub
repo - keras_mnist.’
Statement
works OK:
The
importance of this example is: it trains
a weight file and a json graph file using Keras. Then it converts these to a tensor flow
model. It loads the graph file to the
Movidius NCS stick. At the end it runs
the test example, a number picture(number 6) on the NCS.
Some details
about implementation problems I had:
A through
README is available.
- ‘Optionally, copy this folder into your NCSDK2
directory along with other TensorFlow examples. ncsdk/examples/tensorflow/keras_mnist
- Plug NCS to a USB port on the
host machine.
- Run command - make all
- Run command - make run
But the
copying is not optional. Because:
MAKEFILE
does:
prereqs:
(cd
../../data/ilsvrc12; make)
Make all produced the KERAS model with a long
output but with the problem:
Training
finished. If you want to retrain the model, delete 'weights.h5' and
'model.json' files.
(test -f
weights.h5 && test -f model.json) || (echo "Please run \'make
train\' first.")
test -f
TF_Model/tf_model.meta || ./convert-mnist.py
from: can't
read /var/mail/keras.models
from: can't
read /var/mail/keras
./convert-mnist.py:
8: ./convert-mnist.py: model_file: not found
./convert-mnist.py:
9: ./convert-mnist.py: weights_file: not found
./convert-mnist.py:
11: ./convert-mnist.py: Syntax error: "(" unexpected
Makefile:45:
recipe for target 'weights' failed
make: ***
[weights] Error 2
The solution
was to install KERAS with:
Pip3 install
keras
It did
another error which I corrected with putting at the top of convert-mnist.py
And at the
top of makeFile:
#!
/usr/bin/python3.5
After this I
got the error: ImportError: cannot import name '_validate_lengths'
Icorrected this by first:
Pip3 install numpy
And then because of its sideeffect I
installed:
Pip3 scikit-image
The result is:
arsaral@ars:~/ncsdk/ncappzoo-ncsdk2/apps/keras_mnist-master$
make run
(test -f
weights.h5 && test -f model.json) || python3 ./train-mnist.py
Training
finished. If you want to retrain the model, delete 'weights.h5' and
'model.json' files.
(test -f
weights.h5 && test -f model.json) || (echo "Please run \'make
train\' first.")
test -f
TF_Model/tf_model.meta || ./convert-mnist.py
test -f
graph || mvNCCompile -s 12 TF_Model/tf_model.meta -in=conv2d_1_input
-on=dense_2/Softmax
python3
./predict-mnist-ncsdk2.py
/usr/local/lib/python3.5/dist-packages/mvnc/mvncapi.py:416:
DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves
surprisingly on unicode inputs. Use frombuffer instead
tensor = numpy.fromstring(tensor.raw,
dtype=numpy.float32)
NCS
[8.3982944e-05 0.0000000e+00 0.0000000e+00
0.0000000e+00 0.0000000e+00
2.1958351e-04 9.9804688e-01 0.0000000e+00
1.2531281e-03 0.0000000e+00]
Predicted: 6
The inferred
picture is:
