Yolov3 error while training in MATLAB 2020a
3 views (last 30 days)
Show older comments
Hi,
I was trying to train with yolov3. I tried with the example code and dataset. it works perfectly.
Then I tried with my own dataset(with only one class). am getting following error.
Invalid transform function defined on datastore.
The cause of the error was:
Error using imresize
Expected input number 1, A, to be nonempty.
Error in imresize>parsePreMethodArgs (line 389)
validateattributes(A, {'single', ...
Error in imresize>parseInputs (line 273)
parsePreMethodArgs(varargin, method_arg_idx, first_param_string_idx);
Error in imresize (line 152)
params = parseInputs(args{:});
Error in preprocessData (line 14)
I = im2single(imresize(I,targetSize(1:2)));
Error in yolov3_train_2020a>@(data)preprocessData(data,networkInputSize) (line 57)
preprocessedTrainingData = transform(augmentedTrainingData, @(data)preprocessData(data, networkInputSize));
Error in matlab.io.datastore.TransformedDatastore/applyTransforms (line 489)
data = ds.Transforms{ii}(data);
Error in matlab.io.datastore.TransformedDatastore/read (line 162)
[data, info] = ds.applyTransforms(data, info);
Error in yolov3_train_2020a (line 126)
data = read(preprocessedTrainingData);
What could be the reason for the above error. I can assure that I have formatted the image datastore and box label datastore correctly, because I was able to train yolov2 with the same data.
1 Comment
Madhav Thakker
on 9 Feb 2021
Hi Sanjeev,
Error using imresize
Expected input number 1, A, to be nonempty.
The error says that the input is empty. Can you confirm if the path of images are correct?
Answers (0)
See Also
Categories
Find more on Image Data Workflows in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!