MATLAB: Is ‘BOOL’ datatype of initializer not supported by importONNXLayers in R2019a

batchmulticlassnonmaxsuppressionboolgetinitializerdataimportonnxlayersimportonnxnetworkinitializerpadorclipboxlisttranslateonnx

I have converted "ssd_mobilnet_v1_fpn_coco" to ONNX from https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md.

Then I try to load it, but it fails:

>> layers = importONNXLayers('ssd_mobilenet.onnx','OutputLayerType','classification','ImportWeights',true)
Error using nnet.internal.cnn.onnx.translateONNX>getInitializerData (line 347)
The datatype of initializer 'Postprocessor/BatchMultiClassNonMaxSuppression/map/while/PadOrClipBoxList/cond/cond/pred_id/_174__cf__177:0' ('BOOL') is not supported yet.

Why is 'BOOL' datatype of initializer not supported by importONNXLayers?

Best Answer

This is currently not supported. The development team is aware of this and they may improve the functionality of "importONNXNetwork" and "importONNXLayers" in a future MATLAB release such that this datatype of initializer is supported.

Related Solutions

MATLAB: Do I get an error when I try to train a DAG network on multiple GPU’s

This functionality is supported as of MATLAB R2018a. Unfortunately, there is no workaround for previous versions.

MATLAB: How to generate code for the deep neural network with ScalingLayer

The workaround is to substitute the 'ScalingLayer' with an 'nnet.onnx.layer.ElementwiseAffineLayer'. However, this would involve using a attached p-coded script ('getNetworkFromRepresentation.p') to extract the network from the 'rlLayerRepresentation' object. The steps are outlined in the script below:

%%load agent MAT file
load agent
%%get actor representation (contains scalingLayer) from saved agent
actor = getActor(saved_agent);
%%get the new network with codegen-supported layer
actorNetwork = getNetworkFromRepresentation(actor);
newActorNetwork = actorNetwork;
% replace any scalingLayer with nnet.onnx.layer.ElementwiseAffineLayer. The
% name, scale, bias values of old scalingLayer are transfered to the new
% layer
for ct = 1:numel(newActorNetwork.Layers)
    if isa(newActorNetwork.Layers(ct),'rl.layer.ScalingLayer')
        newLayer = nnet.onnx.layer.ElementwiseAffineLayer(...
            newActorNetwork.Layers(ct).Name,...
            newActorNetwork.Layers(ct).Scale,...
            newActorNetwork.Layers(ct).Bias);
        newActorNetwork = replaceLayer(newActorNetwork,newActorNetwork.Layers(ct).Name,newLayer);
    end
end
%%recreate the representation with net network
actionLayerName      = newActorNetwork.Layers(end).Name;
observationLayerName = newActorNetwork.Layers(1).Name;
actionInfo      = actor.ActionInfo;
observationInfo = actor.ObservationInfo;
newActor = rlRepresentation(newActorNetwork,observationInfo,actionInfo,...
    'Observation',observationLayerName,'Action',actionLayerName,actor.Options);
saved_agent = setActor(saved_agent,newActor);
%%codegen
generatePolicyFunction(saved_agent)
cfg = coder.gpuConfig('mex');
cfg.TargetLang = 'C++';
cfg.GpuConfig.Enabled = true;
cfg.DeepLearningConfig = coder.DeepLearningConfig('cudnn');
argstr = '{ones(4,1)}';
codegen('-config','cfg','evaluatePolicy','-args',argstr,'-report');

Notes:

You are free to use the 'getNetworkFromRepresentation.p' script as you wish.
You will need to install the 'Deep Learning Toolbox Converter for ONNX Model Format support package'.

Best Answer

Related Solutions

MATLAB: Do I get an error when I try to train a DAG network on multiple GPU’s

MATLAB: How to generate code for the deep neural network with ScalingLayer

Related Question