How to use an image datastore for an image regression with custom pre-processing steps?

I want to train a deep learning network (CNN) for predicting numeric arrays (i.e., response variable) using input images and have followed this image-regression documentation example.

Please run the following command in the command window of MATLAB R2020a to access the release-specific documentation:

>> web(fullfile(docroot, 'deeplearning/ug/train-a-convolutional-neural-network-for-regression.html'))

The above example loads all images (after pre-processing) in a 4D-array in memory at once before network training. Loading 50k images is not feasible for me. 

I have also checked the "augmentedImageDatastore," which resolves the memory issue. However, during pre-processing, I want to crop each image using individual crop parameters, which the "augmentedImageDatastore" does not support.

Please run the following command in the command window of MATLAB R2020a to access the release-specific documentation for "augmentedImageDatastore":

>> web(fullfile(docroot, 'deeplearning/ref/augmentedimagedatastore.html'))

Please suggest a workaround to achieve this workflow. 

Answer 1

[MathWorks Support Team]

This can be achieved by saving metadata for all samples in MAT-files, and then creating a "fileDatastore" using a custom read function.

As a workaround, please try the following steps:

1) Save metadata such as "imgFilename", "cropData", and "responseData" related to each sample in an individual MAT-file. A script can be created to automate this process.

2) Create a datastore for input images by providing the folder path that stores all MAT-files. Either "fileDatastore" or "imageDatastore" can be used with a custom read function "ReadFcn".

imds = fileDatastore(pathToFolder,'FileExtensions','.mat','ReadFcn',@matImgRead); %imds = imageDatastore(pathToFolder,'FileExtensions','.mat','ReadFcn',@matImgRead);
function img = matImgRead(filename) data = load(filename); img = imread(data.imgFilename); img = imcrop(img,data.cropData); img = imresize(img,[28 28]); end 

3) Create a datastore for the response variable as well.

responseds = fileDatastore(pathToFolder,'FileExtensions','.mat','ReadFcn',@(filename) load(filename, 'responseData')); 

4) The image and the response variable datastores can then be combined. The "combine" function concatenates the outputs from the datastores.

combinedds = combine(imds, responseds); 

Please follow the below link to search for the required information regarding the current release:

https://www.mathworks.com/help/