How to test trained fasterRCNN

2 visualizzazioni (ultimi 30 giorni)
Pawel Habrzyk
Pawel Habrzyk il 6 Mar 2020
So I've been trying to train a fasterRCNN, but unfortunetly test it on my dataset.
I am aplllying the same transformation to both trainingData and testData, but it doesn't work.
My log:
Invalid transform function defined on datastore.
Invalid transform function defined on datastore.
The cause of the error was:
Error using bboxresize>iParseInputs (line 89)
The value of 'bboxA' is invalid. Expected input number 1, bboxA, to be integer-valued.
Error in bboxresize (line 49)
params = iParseInputs(bboxA,scale);
Error in untitled>preprocessData (line 97)
data{2} = bboxresize(data{2},scale);
Error in untitled>@(data)preprocessData(data,inputSize) (line 73)
testData= transform(testData,@(data)preprocessData(data,inputSize));
Error in matlab.io.datastore.TransformedDatastore/read (line 148)
data = self.Transforms{ii}(data);
Error in nnet.internal.cnn.DataLoader/manageReadQueue (line 161)
data = read(self.Datastore);
Error in nnet.internal.cnn.DataLoader/nextBatch (line 88)
manageReadQueue(self);
Error in nnet.internal.cnn.GeneralDatastoreDispatcher/readNextBatchIntoCache (line 350)
data = nextBatch(this.DataLoader);
Error in nnet.internal.cnn.GeneralDatastoreDispatcher/next (line 307)
this.readNextBatchIntoCache();
Error in DAGNetwork/activationsMIMO (line 162)
X = dispatcher.next();
Error in vision.internal.cnn.fastrcnn.detectUsingDatastore (line 14)
[features, regression, proposals] = network.activationsMIMO(ds,...
Error in fasterRCNNObjectDetector/detect (line 535)
varargout{1} = vision.internal.cnn.fastrcnn.detectUsingDatastore(ds, this.Network, dataMap, layerOut, params);
Error in untitled (line 76)
detectionResults = detect(detector,testData,'MinibatchSize',1);
23 rethrow(ME);
Your MATLAB session has timed out. All license keys have been returned.
>> detectionResults = detect(detector,testData,'MinibatchSize',1);
Invalid transform function defined on datastore.
The cause of the error was:
Error using bboxresize>iParseInputs (line 89)
The value of 'bboxA' is invalid. Expected input number 1, bboxA, to be integer-valued.
Error in bboxresize (line 49)
params = iParseInputs(bboxA,scale);
Error in untitled>preprocessData (line 97)
data{2} = bboxresize(data{2},scale);
Error in untitled>@(data)preprocessData(data,inputSize) (line 73)
testData= transform(testData,@(data)preprocessData(data,inputSize));
Error in matlab.io.datastore.TransformedDatastore/read (line 148)
data = self.Transforms{ii}(data);
Error in nnet.internal.cnn.DataLoader/manageReadQueue (line 161)
data = read(self.Datastore);
Error in nnet.internal.cnn.DataLoader/nextBatch (line 88)
manageReadQueue(self);
Error in nnet.internal.cnn.GeneralDatastoreDispatcher/readNextBatchIntoCache (line 350)
data = nextBatch(this.DataLoader);
Error in nnet.internal.cnn.GeneralDatastoreDispatcher/next (line 307)
this.readNextBatchIntoCache();
Error in DAGNetwork/activationsMIMO (line 162)
X = dispatcher.next();
Error in vision.internal.cnn.fastrcnn.detectUsingDatastore (line 14)
[features, regression, proposals] = network.activationsMIMO(ds,...
Error in fasterRCNNObjectDetector/detect (line 535)
varargout{1} = vision.internal.cnn.fastrcnn.detectUsingDatastore(ds, this.Network, dataMap, layerOut, params);
23 rethrow(ME);
>> testData
testData =
TransformedDatastore with properties:
UnderlyingDatastore: [1×1 matlab.io.datastore.CombinedDatastore]
Transforms: {@(data)preprocessData(data,inputSize)}
IncludeInfo: 0
  1 Commento
Sai Bhargav Avula
Sai Bhargav Avula il 26 Mar 2020
Can you share the transforms that was applied on the datastore object?

Accedi per commentare.

Risposte (0)

Categorie

Scopri di più su Statistics and Machine Learning Toolbox in Help Center e File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by