I was training a faster r-cnn for two weeks and, somehow, it crashed last night.. I was saving the checkpoints after each epoch but now, if I try to start a new training with the last one (or any other) I receive:
Error using vision.internal.cnn.rcnnDatasetStatistics>iGetRPNSoftmaxLayerSource (line 125)
Expected one output from a curly brace or dot indexing expression, but there were 0 results.
Error in vision.internal.cnn.rcnnDatasetStatistics (line 17)
params.RPNSoftmaxLayerSource = iGetRPNSoftmaxLayerSource(analysis);
Error in trainFasterRCNNObjectDetector>iCollectImageInfo (line 1674)
imageInfo = vision.internal.cnn.rcnnDatasetStatistics(trainingData, rpnLayerGraph, imageInfoParams);
Error in trainFasterRCNNObjectDetector (line 423)
[imageInfo,trainingData,options] = iCollectImageInfo(trainingData, rpn, iStageOneParams(params), params, options);
And the detector object seems to be empty:
fasterRCNNObjectDetector with properties:
ModelName: 'MCs'
Network: []
AnchorBoxes: [3×2 double]
ClassNames: {}
MinObjectSize: [16 16]
Can't I resume training with these chechpoints where it left off? And, if not, what went wrong during the saving of these checkpoints?! I don't know if it matters but I was training with the Training method "four-step".
Please, please, any help??
