CIFAR-10 image classfier using TensorFlow

This design is a small convolution neural network that is trained to identify the 10 image classes of the CIFAR-10 dataset. The dataset is downloaded using the native Keras dataset functions, then trained and evaluated using TensorFlow.

The example demonstrates the following:

• Simple download of CIFAR-10 dataset.
• Scaling of the image data, one-hot encoding of the labels.
• How to define a CNN using the tf.layers API.
• Logging of data for display in TensorBoard.
• Saving the model graph as a protobuf text file.

The code and a Jupyter notebook is available on my Github page.

If you have any questions or comments about this design, please email me at designs@markharvey.info