[fbsync] Update stanford-cars docs with more elaborate instructions for download=False (#8620)

Reviewed By: vmoens

Differential Revision: D68021990

fbshipit-source-id: 3fa6ac3c7e6310310571e5b96ebdfe59b09a7a53

Co-authored-by: Nicolas Hug <[email protected]>
Co-authored-by: Nicolas Hug <[email protected]>

Author: NicolasHug

torchvision/datasets/stanford_cars.py

@@ -15,6 +15,7 @@ class StanfordCars(VisionDataset):
     has been split roughly in a 50-50 split
 
     The original URL is https://ai.stanford.edu/~jkrause/cars/car_dataset.html, but it is broken.
+    Follow the instructions in ``download`` argument to obtain and use the dataset offline.
 
     .. note::
 
@@ -29,8 +30,12 @@ class StanfordCars(VisionDataset):
             target and transforms it.
         download (bool, optional): This parameter exists for backward compatibility but it does not
             download the dataset, since the original URL is not available anymore. The dataset
-            seems to be available on Kaggle so you can try to manually download it using
-            `these instructions <https://github.com/pytorch/vision/issues/7545#issuecomment-1631441616>`_.
+            seems to be available on Kaggle so you can try to manually download and configure it using
+            `these instructions <https://github.com/pytorch/vision/issues/7545#issuecomment-1631441616>`_,
+            or use an integrated
+            `dataset on Kaggle <https://github.com/pytorch/vision/issues/7545#issuecomment-2282674373>`_.
+            In both cases, first download and configure the dataset locally, and use the dataset with
+            ``"download=False"``.
     """
 
     def __init__(