ImageClassifierData.from_csv

(Amit Mukherjee) #1

Hi all,

I have a training set and validation set seperately. So from Lecture - 2. I don’t want use random 20% set from traning set (as I already have validation set), So how can I calculate val_idxs from validation set.

tfms = tfms_from_model(arch, sz, aug_tfms=transforms_side_on, max_zoom=1.1)
data = ImageClassifierData.from_csv(PATH, ‘train’, f’{PATH}labels.csv’, test_name=‘test’,
val_idxs=val_idxs, suffix=’.jpg’, tfms=tfms, bs=bs)

0 Likes