Do matlab has build-in mnist dataset for CNN training? If I load it as dlarray, how do I train it with CNN?
13 views (last 30 days)
Show older comments
Runcong Kuang
on 3 Aug 2022
Commented: Walter Roberson
on 5 Aug 2022
Is the 'toolbox/nnet/nndemos/nndatasets/DigitDataset' MNIST dataset?
It just contains 1000 samples for each label.
MNIST should have 60k training and 10k testing data.
If I use the dataset downloaded and loaded by 'processImagesMNIST' in "examples/nnet/main" according to this, it gives dlarray.
It is not in the format for the imagedatastore.
My current workaround is to convert dlarray to numeric array by extractdata, and then feed it to trainNetwork function.
Any other advice?
Thanks.
0 Comments
Accepted Answer
Walter Roberson
on 3 Aug 2022
Edited: Walter Roberson
on 5 Aug 2022
No it does not. The download link is given at https://www.mathworks.com/help/deeplearning/ug/data-sets-for-deep-learning.html
2 Comments
Walter Roberson
on 5 Aug 2022
No, if you
openExample('nnet/GeneratingHanddrawnDigitsUsingAVariationalAutoencoderVAEExample')
and then look at processImagesMNIST.m in that directory, you will see that the function reads an MNIST image and returns a 28 x 28 x 1 x something double precision value.
More 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!