DataBlock x shape - torch.Size([64, 3, 224, 224])

Part 1 (2020)
1

Hi Friends,
Have a beginners question
In the DataBlock in Chapted 5 Image Classification - Pets
x.shape is torch.Size([64, 3, 224, 224])
Whats the 3 rows in this? (64 is batch size, 224 x 224 is image tensor)
Does 3 mean train, valid, test data sets? I may be wrong.
Snippet below…

pets = DataBlock(blocks = (ImageBlock, CategoryBlock),
get_items=get_image_files,
splitter=RandomSplitter(seed=42),
get_y=using_attr(RegexLabeller(r’(.+)_\d+.jpg$’), ‘name’),
item_tfms=Resize(460),
batch_tfms=aug_transforms(size=224, min_scale=0.75))
dls = pets.dataloaders(path/“images”)

x,y = dls.one_batch()

x.shape
torch.Size([64, 3, 224, 224])

2

Three means it’s a three channel image, RGB. So it’s:

Batch Size, N channels, width, height

3

Thanks Zachary. Yes RGB 3 channels make sense :slight_smile: