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.
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 |
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.