Hi, thank you very much for open sourcing, I am very interested in your paper. I'd like to download the pretrained PointNet model from the GoogleDive you provided, but it seems to require your access.

I can't read the code for tensorflow,do you have pytorch?

Hi! Thank you for opening source this great work! I wonder can you provide your pre-trained weight for LG-GAN which achieved the performance you reported in the paper? (Or similar performance, I want to test a defense method against LG-GAN attack)

Thanks for your excellent work and code. I meet some problems when compiling the TF operators. I can well compile 3d_interpolate and interpolate file, but the other files fail. I use CUDA10.0 Tensorflow 1.14.0. I know three of operators are from PointNet++. Could you tell me where the nn_distance, approxmatch from?

Hi! Recently I'm using your code and I find something strange in your implementation of targeted attack. So here is the code you use to generate adversarial examples on test data, though I'm not familiar with TensorFlow, I think if you run "sess.run()" including g_optim and d_optim, then you'll update the parameters of D and G right? But the feed_dict here is test_data and test_label as shown here, which means you're optimize your GAN on the test data.

I'm just confused about why you need to do so. If understand correctly, LG-GAN generates adversarial examples at one shot, so you don't need to update the parameters in G or D during the generation. Again I'm not quite sure about TensorFlow so please correct me if I'm wrong. Or, is it really a bug? Or out of some special purpose?

Thank you for your excellent work and open source code.
My deep learning environment : Ubuntu 20.04, CUDA 11.4, and tensorflow 2.6.
I downloaded the pointnet_cls model that you provided in Google drive and put it to the directory "checkpoints/pointnet", but something error occurred, namely,

tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

2 root error(s) found.
(0) Not found: Key conv1/biases not found in checkpoint
[[node save/RestoreV2 (defined at lggan.py:201) ]]
(1) Not found: Key conv1/biases not found in checkpoint
[[node save/RestoreV2 (defined at lggan.py:201) ]]
[[save/RestoreV2/_15]]
0 successful operations.
0 derived errors ignored.

when i ran the command "python -u lggan.py --adv_path LGGAN --checkpoints_path LGGAN --log_path LGGAN --tau 1e2".
I am sure that i do not modify any file related to your provided model files, i.e.,

checkpoint
model.cpkt-202080.data-00000-of-00001
model.cpkt-202080.index
model.cpkt-202080.meta

I will greatly appreciate if you could offer me some advises. Thank you :D