Hi. Currently, I’m using learn.validate() to get the accuracy result for my classifier:
path = '/content/food-101/images'
data_test = ImageList.from_folder(path).split_by_folder(train='train', valid='test').label_from_re(file_parse).transform(size=224).databunch()
learn.load('stage-3')
learn.validate(data_test.valid_dl)
I would like to use learn.TTA() but I haven’t seen a straightforward example of how to apply my existing test set like I’m doing above.