PointNetVlad-Pytorch

PointNetVlad-Pytorch copied to clipboard

Hi, thanks for your Pytorch implementation of PointNetVLAD. I'm a new learner. When I read the code, I'm confused at PointNetVLAD: https://github.com/cattaneod/PointNetVlad-Pytorch/blob/ff00ff07b17f35db9ddaea15d04c94b491051d4d/models/PointNetVlad.py#L45-L81 According to my view: - `activation` at line...

where2go947

Thanks for your wonderful work, but i find in the file "train_pointnetvlad", the global variable "HARD_NEGATIVES={}" is never updated which means it is useless, is there something wrong here?

Master-cai

Recall@1% on Oxford is higher than that in the paper.

1

Thanks for your great work, the recall@1% on Oxford is higher than that in the paper, which is trained by the default config in your repository. Is it normal?

banxiyan

RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation.

2

line 361, in process_data ob[i] = torch.roll(ob[i], seed, dims=1) RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation. Can you suggest why...

pareespathak

Hi,it is a great work, I want to do a test, can you provide a pre-trained model, thank you!

guoxiantao

The import: `import config as cfg` is missing n the `generate_training_tuples_baseline.py ` script, returning an error when defining the dataset directory name in line 10.

PietroGriffa

Hello, the default training file is oxford. How can I use the University section of the inhouse dataset for training? Thank you very much for your reply!

lkf263