From 4472508e509642aa585bfa036311d4ebbd9c6874 Mon Sep 17 00:00:00 2001 From: Nikita Date: Wed, 13 Apr 2022 12:32:51 +0300 Subject: [PATCH] Fix FGVCAircraft dataset documentation There is a mistake in FGVCAircraft dataset documentation. If you load dataset and sum up 'trainval' and 'test' splits, there are not 10 200, but 10 000 images. Also mistake is in the number of classes: if we choose `annotation_level` to be `variant`, then unique number of classes is going to be not 102, but 100, and with `manufacturer` level it is not 41, but 30. --- torchvision/datasets/fgvc_aircraft.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/torchvision/datasets/fgvc_aircraft.py b/torchvision/datasets/fgvc_aircraft.py index d0bbf586639..2e4993361ca 100644 --- a/torchvision/datasets/fgvc_aircraft.py +++ b/torchvision/datasets/fgvc_aircraft.py @@ -12,15 +12,15 @@ class FGVCAircraft(VisionDataset): """`FGVC Aircraft `_ Dataset. - The dataset contains 10,200 images of aircraft, with 100 images for each of 102 + The dataset contains 10,000 images of aircraft, with 100 images for each of 100 different aircraft model variants, most of which are airplanes. Aircraft models are organized in a three-levels hierarchy. The three levels, from finer to coarser, are: - ``variant``, e.g. Boeing 737-700. A variant collapses all the models that are visually - indistinguishable into one class. The dataset comprises 102 different variants. + indistinguishable into one class. The dataset comprises 100 different variants. - ``family``, e.g. Boeing 737. The dataset comprises 70 different families. - - ``manufacturer``, e.g. Boeing. The dataset comprises 41 different manufacturers. + - ``manufacturer``, e.g. Boeing. The dataset comprises 30 different manufacturers. Args: root (string): Root directory of the FGVC Aircraft dataset.