Parameter to choose the amount of data to train?

data = ImageClassifierData.from_paths(PATH, tfms=tfms)
learn = ConvLearner.pretrained(arch, data, precompute=True)

Here all the images in the PATH will be used to train the model.


Is there any parameter to choose the percentage of images from PATH for training.

This might be helpful for some quick testing or to those working on CPU.

You could always use a python script to copy a random subset of the images in PATH to some other PATH.