multi_object_datasets icon indicating copy to clipboard operation
multi_object_datasets copied to clipboard

Multi-object image datasets with ground-truth segmentation masks and generative factors.

Results 10 multi_object_datasets issues
Sort by recently updated
recently updated
newest added

Thank you for your wonderful work. Regarding the CATER_withmask dataset, the data in the mask is not binary (ideally it should be 255 or 0). Can you check this, it...

I am having issues loading the CATER dataset files. I get the following error: tensorflow.python.framework.errors_impl.DataLossError: corrupted record at 0 [Op:IteratorGetNext] (test1) [ashah20@ai11 cater]$ I have tried to load using various...

Code in 'README.md' works well in 'multi_dsprites_colored_on_colored.tfrecords'. However, it doesn't work well in 'multi_dsprites_binarized.tfrecords' and 'multi_dsprites_colored_on_grayscale.tfrecords'. In the code ```python from multi_object_datasets import multi_dsprites import tensorflow as tf tf_records_path =...

Hi, it seems there are 19 unique Tetrominoes shapes (counting discrete rotations) and not 17 as stated > you should consider fixing the typo in this repo and in the...

All fields seem to be padded with zeros up to 11 objects. How to find out the true number of objects?

I wrote an unpacker that saves the images/masks in the folders (for ease of interop with PyTorch): https://github.com/vadimkantorov/yet_another_pytorch_slot_attention/blob/master/clevr_with_masks.py#L66 . But the unpacker keeps running beyond 85K images. How many images...

In the paper `Multi-Object Representation Learning with Iterative Variational Inference Klaus` (**IODINE**) 1. The paper claims there are 70000 images for CLEVR but there are 100000+ images in its tfrecords...

Hello. According to the comment: ``` # The case where n_true_groups == n_pred_groups == 1 needs to be # special-cased (to return 1) as the above formula gives a divide-by-zero....

Dear Authors, Will it be possible for you to provide the code for generating segmentation masks for CLEVR images?