Skip to content
Keras to Tensorflow test for Neural Compute Stick 2
Branch: master
Clone or download
Latest commit 06a689a Oct 22, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
IR_model full model w/ batchnorm Mar 14, 2019
data [ImgBot] Optimize images Mar 11, 2019
logs new keras model, succesfully loaded Mar 14, 2019
.gitignore update gitignore Mar 14, 2019 new keras model, succesfully loaded Mar 14, 2019 cleanup Mar 14, 2019 cleanup Mar 14, 2019
output_expected.npy graph compiled for ncs2 Mar 9, 2019 removed useless comment Mar 15, 2019 Readme redacted Mar 14, 2019

Keras to Tensorflow to IR model (NCS2)


Convert a Keras or a Tensorflow model to IR files ready to be used with the Neural Compute Stick 2


For that you want to have OpenVino installed and python 3.5 at least. For the python requirements, see the "Requirements" section.

File structure

How to use

Keras to Tensorflow conversion

If you have a Keras .h5 file, use to create a Tensorflow .pb file.


that will take the Keras file situated in Keras_model/model.h5 and create a .pb file in TF_model/tf_model.pb.

Tensorflow to IR conversion

If you didn't had a .pb model before now you should have one. We'll use the model optimizer to convert the file. --data_type FP16 --framework tf --input_model TF_model/tf_model.pb --model_name IR_model --output_dir IR_model/ --input_shape [1,28,28,1] --input conv2d_1_input --output activation_6/Softmax

Runing the inference on the NCS2

Now you can run the inference on the NCS2. For that use the


This file load the IR model, read and convert the data/6.jpg and feed it for classification.

If everything goes fine, you should see something like this:

    [ INFO ] Loading network files:
    [ INFO ] Preparing input blobs
    1 1 28 28
    (28, 28)
    (1, 28, 28)
    [ INFO ] Loading model to the plugin
    [ INFO ] Starting inference (1 iterations)
    [ INFO ] Average running time of one iteration: 1.8284320831298828 ms
    [ INFO ] Processing output blob
    [[0. 0. 0. 0. 0. 0. 1. 0. 0. 0.]]

The last line is the class vector. We have a 1 at index 6, so the image has been correctly classified.


    pip install -r requirements.txt
You can’t perform that action at this time.