产品和环境
本部分要求填写创建该范例所需的产品和操作系统。
如要下载NI软件（包括以下所示产品），请访问ni.com/downloads。
代码和文档
添加附件
Description
Description-Separate-1
Overview
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.
Description
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.
Additional Information or References
Front Panel:
Jinho Choi
Staff Technical Support Engineer
Description-Separate-2
NI社区“代码范例交流区”(Example Code Exchange)中的代码范例已获得MIT许可。
