Issues with Dataloader for imagenet (should I use datasets.ImageFolder or datasets.ImageNet)?

I want to use the pretrained models from pytorch and evaluate them on imagenet val data. That should be fairly straightforward, but I am getting stuck on the dataloader.
I downloaded the imagenet and the folder structure that I have is like this:


First I tried datasets.ImageNet, based on pytorch where it says to use the following

imagenet_data = torchvision.datasets.ImageNet('path/to/imagenet_root/')
data_loader =,

I changed the path_to_imagenet_to /media/SSD2/ILSVRC/ like this

but I get this error:

RuntimeError: The archive ILSVRC2012_devkit_t12.tar.gz is not present in the root directory or is corrupted. You need to download it externally and place it in /media/SSD2/ILSVRC/.

Then I tried using datasets.ImageFolder in the following way:

imagenet_data = torchvision.datasets.ImageFolder('/media/SSD2/ILSVRC/Data/CLS-LOC/val' , transform=transform)
data_loader =,

it kinda works but the labels that generate are garbage.

I was wondering if anyone knows which one of the aforementioned methods can work and how should I do it?

I don’t know how and where you’ve downloaded the ImageNet dataset, but on my system each class uses a separate subfolder, which is needed in order to find all classes.
E.g. the val folder contains:

n01440764  n01824575  n02093754  n02115641  n02457408  n02877765  n03272010  n03710193  n03958227  n04296562  n04597913
n01443537  n01828970  n02093859  n02115913  n02480495  n02879718  n03272562  n03710637  n03961711  n04310018  n04599235
n01484850 ...

where each folder contains the images for this particular class.

I think @seyeeet probably downloaded the Imagenet dataset from kaggle: ImageNet Object Localization Challenge | Kaggle. It’s no longer possible to download it from the original place on the imagenet website, instead the website also only refers to the dataset that is hosted on kaggle. I also downloaded it there and I get the same error when loading it via the torchvision.datasets.ImageNet class.

Are we just using it wrong or has the layout of the ImageNet dataset changed? The error message mentions that the dataloder cannot find ILSVRC2012_devkit_t12.tar.gz - kaggle’s verison of the dataset actually does not contain such an archive.


I guess Kaggle might have changed the data layout and if so I would assume there would be PyTorch scripts to load this new dataset type.
Based on the previous output it seems as if the images are just stored in the test/train/val folders without any subfolders. In that case ImageFolder wouldn’t be compatible, since the class indices won’t be created. If so, I would also assume that a target file is provided additionally.

Thanks, you are right, there’s actually an example script in an official pytorch repo that shows how ImageNet data can be accessed by using ImageFolder, which works for the version of the dataset that’s available on kaggle: examples/imagenet at master · pytorch/examples · GitHub

can you please verify what scrips are you referring to? :slight_smile:

@seyeeet The script that I’m referring to is linked in my reply above: examples/imagenet at master · pytorch/examples · GitHub

That said, I haven’t used the script directly, I simply tried to reuse the code part that sets up the dataloaders which starts here examples/ at master · pytorch/examples · GitHub and that works for me.
Just make sure that you follow the setup instructions that are listed here examples/imagenet at master · pytorch/examples · GitHub. In particular, you have to execute the shell script, that’s mentioned in the last step, inside the val folder (ILSVRC/Data/CLS-LOC/val/). This makes sure that the val folder is structured in a way that can be understood by the ImageFolder class.


Meet the same problem and solve it with
Specifically, to make the val dataset have the same structure as train set, you should run the following commands. It will move all validation pictures to corresponding class subfolders.

cd val/
wget -qO- | bash
1 Like