Could you release your whole training dataset of CelebA, i.e. CelebA_crop_resize_128?

[BostonLobster]

Hi! Thanks very much for releasing your code.

But I have one more question: could you release your whole training dataset of CelebA? I saw it in generate_dataset_csv.py, in which there is something called CelebA_crop_resize_128.

Since CelebA has too many (200k+) images, I don't know which images are used in your training. So if at your convenience, could you upload the CelebA_crop_resize_128 set onto Google drive so that I can download?

[bhushan23]

@BostonLobster I don't have access to server anymore. But, I will check if I can get the dataset.
I randomly curated images from the dataset, you can do the same and re-train your model.
Using same set of images for training is not mandatory.

[BostonLobster]

@bhushan23 Thanks for your reply.

If so, could you share the method how you crop and resize the images to 128? I am stucking in how to process that.