search

NVlabs / NVAE

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)
https://arxiv.org/abs/2007.03898
Other
999 stars 163 forks source link

Problem while converting tfrecord to lmdb data AttributeError: 'bytes' object has no attribute 'cpu' #49

Open nitec427 opened 8 months ago

nitec427 commented 8 months ago

Hey, I am trying to train your https://github.com/NVlabs/denoising-diffusion-gan Denoising Diffusion GAN model and my image size is 256. However, the problem is that repository recommends this repository to download and extract celeb as a lmdb file. However, when I try to run the script as it is described, I am getting the following error.

Screenshot 2023-11-17 at 17 16 12

Can you fix the problem. I can see that tfrecords repository has been archived but may be the problem is different. Thanks a lot.

LinWeiJeff commented 7 months ago

Hey, I am trying to train your https://github.com/NVlabs/denoising-diffusion-gan Denoising Diffusion GAN model and my image size is 256. However, the problem is that repository recommends this repository to download and extract celeb as a lmdb file. However, when I try to run the script as it is described, I am getting the following error. Screenshot 2023-11-17 at 17 16 12

Can you fix the problem. I can see that tfrecords repository has been archived but may be the problem is different. Thanks a lot.

@nitec427 hello, I'm encountering the same problem, too. Did you solve this problem?

nitec427 commented 7 months ago

@LinWeiJeff Hi, Unfortunately, I couldn't solve my problem back then and continued with another dataset

sumorday commented 6 months ago

Same issue here

sumorday commented 6 months ago

im = data['data'][0] it works