Train a TensorFlow model locally
In this quickstart, we will run a TensorFlow model with the MNIST dataset locally in AI Tools. The MNIST database has a training set of 60,000 examples, and a test set of 10,000 examples of handwritten digits.
Before you begin, ensure you have the following installed:
Run the following command in a terminal.
pip install tensorflow
or if you have an Nvidia GPU
pip install tensorflow-gpu
NumPy and SciPy
run the following command in a terminal:
pip install numpy scipy
Download sample code
Download this GitHub repository containing samples for getting started with deep learning across TensorFlow, CNTK, Theano and more.
Open a project and train model
Launch Visual Studio Code and select File > Open Folder (Ctrl+K Ctrl+Of)
Select the examples\tensorflow\MNIST subfolder from your local samples repository.
convolutional.pyand press F5 to start.
The output will be printed in the terminal window.
[!TIP] Make sure you've selected correct python environment which has necessary packages (tensorFlow, NumPy, SciPy, etc.) installed.
Use command Python: Select Interpreer to select proper Python interpreter. Refers to Setting Up Python Interpreter for detailed information.