i am facing invalid bounding boxes while training faster rcnn on multiclasses

hi every on. i am facing invalid bounding boxes problem while training faster rcnn how can i remove this error. my code is a attached with file . This is my error Invalid transform function defined on datastore.

The cause of the error was:

Error using vision.internal.cnn.validation.checkTrainingBoxes Training data from a read of the input datastore contains invalid bounding boxes. Bounding boxes must be non-empty, fully contained within their associated image and must have positive width and height. Use datastore transform method and remove invalid bounding boxes.

Error in vision.internal.cnn.fastrcnn.validateImagesAndBoxesTransform (line 20) boxes = vision.internal.cnn.validation.checkTrainingBoxes(images, boxes);

Error in trainFasterRCNNObjectDetector>@(data)vision.internal.cnn.fastrcnn.validateImagesAndBoxesTransform(data,params.ColorPreprocessing) (line 1754) transformFcn = @(data)vision.internal.cnn.fastrcnn.validateImagesAndBoxesTransform(data,params.ColorPreprocessing);

Error in matlab.io.datastore.TransformedDatastore/applyTransforms (line 723) data = ds.Transforms{ii}(data);

Error in matlab.io.datastore.TransformedDatastore/read (line 235) [data, info] = ds.applyTransforms(data, info);

Error in vision.internal.cnn.rcnnDatasetStatistics>readThroughAndGetInformation (line 72) batch = read(datastore);

Error in vision.internal.cnn.rcnnDatasetStatistics (line 29) out = readThroughAndGetInformation(datastore, params, layerGraph);

Error in trainFasterRCNNObjectDetector>iCollectImageInfo (line 1761) imageInfo = vision.internal.cnn.rcnnDatasetStatistics(trainingData, rpnLayerGraph, imageInfoParams);

Error in trainFasterRCNNObjectDetector (line 459) [imageInfo,trainingData,options] = iCollectImageInfo(trainingData, fastRCNN, iRPNParamsEndToEnd(params), params, options);

Error in FASTERRCNN (line 73) [detector , info ]= trainFasterRCNNObjectDetector(trainingDataForEstimation, lgraph, options);

Answer 1

[Walter Roberson]

As already discussed at https://www.mathworks.com/matlabcentral/answers/2052067-invalid-bounding-boxes-problem-while-using-faster-rcnn#comment_2975842 you can use helperSanitizeBoxes to remove bad boxes.

[ahmad]

I am using it but still error appears

[Walter Roberson]

Sanitize after resizing the boxes. When the target size is smaller than the original size, a box can get resized from acceptable to not acceptable.

[ahmad]

Still not working same error not removeing in valid boxes