Hi all… I’m working on multi-level image classification problem and using followings to create Data bunch…
data = ImageDataBunch.from_folder(path, train=".", valid_pct=0.1, ds_tfms=get_transforms(), size=224, num_workers=4).normalize(imagenet_stats)
Ths problem is that prediction file is not having the image name but series of integers starting 0 , 1 ,2 ,3 etc…which is not matching with the image names in training set and order both. (Pls note that image names are in text not numbers). In short I’m looking for a way to map ‘learn.get_pred’ output with learn.data.train_ds.to_df(). Pls suggest what can done here…