I have a questions regarding the aug_transforms.
Adopted from the camvid example in walkwithfastai I would like to apply aug_transforms for my segementation images and masks. In my case these are satellite images and rotation makes sense.
I split the validation images from textfiles with paths as in lesson 4 from walkwithfastai
Then I load the DataBlock with:
satim = DataBlock(blocks=(ImageBlock, MaskBlock(codes)),
get_items=get_image_files,
splitter=FileSplitter(path/‘valid.txt’),
get_y=get_msk,
batch_tfms=[*aug_transforms(max_rotate=180), Normalize.from_stats(*imagenet_stats)])
I do understand that item_tfms happens on the CPU and batch_tfms on the GPU. My question is, if in case of images, does this increase the amount of different images used for training? For example if I use aug_transforms(max_rotate=180) an image is rotated between 0 and 180 degrees. How can I control the amount of rotations for one image? For example I want every image to be used with 5 different rotations, how can that be achieved?