Get_transformation and normalize data in fastai v2

Hi all,
i was structure the data when i was using fastai v1 as below.

data = ImageDataBunch.from_folder(path,train = ‘Train’,test= ‘Test’, valid = ‘Validation’,ds_tfms=get_transforms(do_flip=True,flip_vert=True), size=150, bs=64
).normalize(imagenet_stats)

now i am using fastai v2. so how can i get same structure data in fastai v2?

currently i am using below in fastai v2.
data = ImageDataLoaders.from_folder(path,train = ‘Train’,test= ‘Test’, valid = ‘Validation’,bs = 64,item_tfms = Resize(150))

thanks in advance

Hi, I’d suggest you work through the vision tutorial of fastai2, at least the first few chapters. The API changed a lot from fastai1, you should check it out!

1 Like