Jie Wang

Ok，thanks for your reply. If not allowed, would you release the settings of the backbone for task of object detection?

You're so welcome. Thanks for your attempt.

i use different seed and max result. Indeed, I think 'farthest = torch.randint(0, N, (B,), dtype=torch.long).to(device) * 0' is wrong. (in models/curvenet_utils.py). Could you please check the codes

In addition, i failed to translate or jitter input, it indeed output different results, but results are very bad(about 5%). I check the RS-CNN code, i find they use the...