Stanford cars fastai v3

[vtecftwy (Etienne)]

Tried the same thing and I realized that the stanford car dataset home page offers two different options:

1. Two image datasets (train and test) with their own labels as .mat file each

• train images at http://imagenet.stanford.edu/internal/car196/cars_train.tgz
• test images at http://imagenet.stanford.edu/internal/car196/cars_test.tgz
• metadata (labels and bounding box info) at https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz

2. A consolidated set of images (train and test) with its consolidated .mat file

• all images at http://imagenet.stanford.edu/internal/car196/car_ims.tgz
• metadata (labels, …) at http://imagenet.stanford.edu/internal/car196/cars_annos.mat

It appears that the data downloaded at with URLs.CARS downloads the train and test folders from the first set but then uses the consolidated cars_annos.mat.mat file instead of two .mat files.

To make it work, you must also download the proper .mat files by using untar_data with the url https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz.

I left a notebook with the full code here