Deep Learning Import and Export

Import and export deep learning networks from TensorFlow™-Keras, Caffe, and the ONNX™ (Open Neural Network Exchange) model format

Import networks and network architectures from TensorFlow-Keras, Caffe, and the ONNX (Open Neural Network Exchange) model format. You can also export a trained Deep Learning Toolbox™ network to the ONNX model format.

Functions

`importKerasNetwork`	Import a pretrained Keras network and weights
`importKerasLayers`	Import layers from Keras network
`importCaffeNetwork`	Import pretrained convolutional neural network models from Caffe
`importCaffeLayers`	Import convolutional neural network layers from Caffe
`importONNXNetwork`	Import pretrained ONNX network
`importONNXLayers`	Import layers from ONNX network
`importONNXFunction`	Import pretrained ONNX network as a function
`exportONNXNetwork`	Export network to ONNX model format
`findPlaceholderLayers`	Find placeholder layers in network architecture imported from Keras or ONNX
`replaceLayer`	Replace layer in layer graph
`assembleNetwork`	Assemble deep learning network from pretrained layers
`PlaceholderLayer`	Layer replacing an unsupported Keras layer, ONNX layer, or unsupported functionality from `functionToLayerGraph`
`ONNXParameters`	Parameters of an imported ONNX network for deep learning
`freezeParameters`	Convert learnable network parameters in `ONNXParameters` to nonlearnable
`unfreezeParameters`	Convert nonlearnable network parameters in `ONNXParameters` to learnable
`addParameter`	Add parameter to `ONNXParameters` object
`removeParameter`	Remove parameter from `ONNXParameters` object

Topics

Assemble Network from Pretrained Keras Layers

This example shows how to import the layers from a pretrained Keras network, replace the unsupported layers with custom layers, and assemble the layers into a network ready for prediction.

Deep Learning Import and Export

Functions

Topics

Deep Learning Toolbox Documentation

Support

Introducing Deep Learning with MATLAB