pointnet
pointnet copied to clipboard
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
I'm having difficulties to understand what are the inputs and outputs for the training and testing scripts. I trained the NN with the S3SID data as in the example, and...
When I run python train.py --log_dir log6 --test_area 6,it will download ‘modelnet40_ply_hdf5_2048.zip’ every time what is this use for ?Can I download it just once?
thank charlesq34 for the code. I get a pointcloud data from realsense camera but how can I do the semantic segmentation with my own data after training. Could you give...
('/home/jianl/pointnet/pointnet-master/data/Stanford3dDataset_v1.2_Aligned_Version/Area_6/pantry_1/Annotations', 'ERROR!!')
In train.py in sem_seg folders, there is a .txt file needed called all_files.txt in indoor3d_sem_seg_hdf5_data, However, after I finished the gen_indoor3d_h5.py,there is no file named all_files.txt in that folders. Have...
Hi, thanks for the nice work! As in [#41](https://github.com/charlesq34/pointnet/issues/41), I would like to train on point clouds with very different density. I exchanged `tf_util.max_pool2d` with `tf.reduce_max` as @charlesq34 suggested. However,...
Hello, in the preparation of semantically segmented data sets, I would like to ask how the. SEG file is generated.I would appreciate it if you could answer my question.
Hello , Any help on how to achieve zero-mean and normalization on a custom data-set is appreciated. Thanks, Christine
Hey there, I have a Nuscenes point cloud dataset available and I will like to make use of it inside this Project. I looked at the `data_prep_util.py` script, however, I...