This example shows how to use the deep learning API to perform numeric classification using the Python Keras library. The model is of sequential type and is compiled using the optimizer provided by Keras. Trained using the mnist dataset, this model recognizes and classifies numbers you draw on the front panel.
This example compiles and trains the model defined in main.py. The model uses a mnist dataset of 28x28 size images provided by Keras and outputs the result by predicting the number drawn on the front panel.
Hardware and Software Requirements
LabVIEW 2018 64-bit and later
Python 3.6 64-bit
TensorFlow Python library.
Keras Python library.
Steps to Implement or Execute Code
Make sure you have TensorFlow and Keras installed in your Python environment.
Open mnist Keras.vi.
Run the VI. After the model has been compiled and trained, the Status indicator changes to "Model_Predicting".
Drag the mouse into the draw pane to draw a number and the model will output the prediction.