k-han / dtc Goto Github PK

Hello I happened to see your work on calculating the accuracy for unsupervised clustering using bipartie method (ranking system). Does this repository also include on how to calculate precision/recall? If not, do you have any tips on how to calculate those metrics? Thanks in advance

[resolved]

Thank you for the code.

There is a RuntimeError getting raised because apparently the code is not able to find the images of ImageNet.

The error is raised when calling ImageFolder class, from within imagenetloader.py, specifically, inside the object ImageNetLoader30. Upon having a closer look at ImageNetLoader30, I found the following line:
samples_30 = make_dataset(path+'images/{}'.format(subfolder), classes_30, class_to_idx_30),
where path = './data/datasets/ImageNet', and subfolder = 'train'.

And when viewing samples_30 after this line, I get nothing but an empty array.
That's why when ImageFolder is called with this empty array as shown in the following line
dataset = ImageFolder(transform=transform, samples=samples_30)

, it prompts the mentioned error.

Does that mean that in the path directory, we should manually create a folder called train (possibly for testing and validation too) and populate it with the images belonging to the categories described by the WNIDs?

I thought that that would be done automatically as part of the pipeline but as the error is getting raised, maybe it is not?

Thank you in advance.

Ahmad

How do I train or fine tune on custom dataset ?
@k-han