wusuowei_m
wusuowei_m
The running time of mex_fitline is very long. Is it because of the Matlab or the code/algorithm itself? % convert the template edge map into a line representation [lineRep lineMap]...
Could you please provide the code for 6DOF estimation task？ i.e. the code of your paper [1]. [1] Fast Object Localization and Pose Estimation in Heavy Clutter for Robotic Bin...
In mesh _prepare.py: 1. def slide_verts(mesh, prct): edge_points = get_edge_points(mesh) dihedral = dihedral_angle(mesh, edge_points).squeeze() #todo make fixed_division epsilon=0 2. def flip_edges(mesh, prct, faces): ... dihedral = angles_from_faces(mesh, edge_faces[:, 2:], faces)...
Do you report the average incremental accuracy [1] which is the weighted average accuracy of only those classes that have already been trained, such as the code of SDC[2] [https://github.com/yulu0724/SDC-IL/blob/master/test.py](url)...
Hi, I have read your paper "Few-Shot Class-Incremental Learning", it is a very good and interesting work, it is a groundbreaking work, and the experimental results are also very good....
How do you normalize the point sets to be zero mean and within a unit ball? I use the following method, but it seems to be wrong. ` void normalized()...
Authors provided the “data/modelnet40_normal_resampled” on Github, and I find the orientation of the point cloud normal is almost always facing outward. Can you tell me how did you do it?...
How to get the dataset for the 3D Object Classification task in Scannet?[https://github.com/ScanNet/ScanNet/tree/master/Tasks#3d-object-classification](url) @msavva @niessner
I expect to get the result of CCIL+H-Aug 71.66, but I get 68.25. I conduct the following command ``` python main_cifar.py \ --new-classes 10 \ --start-classes 50 \ --cosine \...
Could you please provide more run_demo.sh about other datasets（CUB-200-2011, Flowers-102, Caltech-101, ImageNet-Subset） ? @yulu0724