Visiallization problem

[Steven0928]

python monoscene/scripts/visualization/kitti_vis_pred.py +file=/home/robotlab/reserch/Kittirelated/shared_dir/OccDepth-main/output/kitti/08/000000.pkl +dataset=kitti
Traceback (most recent call last):
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/importlib_metadata/__init__.py", line 292, in __getitem__
    return next(iter(self.select(name=name)))
StopIteration

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "monoscene/scripts/visualization/kitti_vis_pred.py", line 6, in <module>
    from mayavi import mlab
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/mayavi/mlab.py", line 15, in <module>
    from mayavi.core.common import process_ui_events
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/mayavi/core/common.py", line 21, in <module>
    from pyface import api as pyface
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/pyface/api.py", line 13, in <module>
    from .about_dialog import AboutDialog
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/pyface/about_dialog.py", line 15, in <module>
    from .toolkit import toolkit_object
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/pyface/toolkit.py", line 23, in <module>
    toolkit = toolkit_object = find_toolkit("pyface.toolkits")
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/pyface/base_toolkit.py", line 282, in find_toolkit
    return import_toolkit(ETSConfig.toolkit, entry_point)
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/pyface/base_toolkit.py", line 216, in import_toolkit
    entry_point_group = importlib_metadata.entry_points()[entry_point]
  File "/home/robotlab/anaconda3/envs/occdepth/lib/python3.7/site-packages/importlib_metadata/__init__.py", line 294, in __getitem__
    raise KeyError(name)
KeyError: 'pyface.toolkits'

Is it a Qt problem?
How can I solve it ?
Thanks a lot

[anhquancao]

Hi @Steven0928,
Seems like mayavi error. Did you follow this to install mayavi?

[Steven0928]

Sure I did , but it still reporting error like I mentioned above. :(

[anhquancao]

I think you can use Open3D instead. It is simpler and less error to install. Here is the code I use:

import open3d as o3d

def get_grid_coords(dims, resolution):
  '''
  :param dims: the dimensions of the grid [x, y, z] (i.e. [256, 256, 32])
  :return coords_grid: is the center coords of voxels in the grid
  '''

  # The sensor in centered in X (we go to dims/2 + 1 for the histogramdd)
  g_xx = np.arange(0, dims[0] + 1)
  # The sensor is in Y=0 (we go to dims + 1 for the histogramdd)
  g_yy = np.arange(0, dims[1] + 1)
  # The sensor is in Z=1.73. I observed that the ground was to voxel levels above the grid bottom, so Z pose is at 10
  # if bottom voxel is 0. If we want the sensor to be at (0, 0, 0), then the bottom in z is -10, top is 22
  # (we go to 22 + 1 for the histogramdd)
  # ATTENTION.. Is 11 for old grids.. 10 for new grids (v1.1) (https://github.com/PRBonn/semantic-kitti-api/issues/49)
  sensor_pose = 10
  g_zz = np.arange(0, dims[2] + 1)

  # Obtaining the grid with coords...
  xx, yy, zz = np.meshgrid(g_xx[:-1], g_yy[:-1], g_zz[:-1])

  coords_grid = np.array([xx.flatten(), yy.flatten(), zz.flatten()]).T
  coords_grid = coords_grid.astype(np.float)

  coords_grid = (coords_grid * resolution) + resolution/2

  temp = np.copy(coords_grid)
  temp[:, 0] = coords_grid[:, 1]
  temp[:, 1] = coords_grid[:, 0]
  coords_grid = np.copy(temp)

  return coords_grid, g_xx, g_yy, g_zz

def draw_semantic_open3d(
    voxels,
    cam_param_path="",
    voxel_size=0.2):    

    colors = np.array([
        [0  , 0  , 0, 255],
        [100, 150, 245, 255],
        [100, 230, 245, 255],
        [30, 60, 150, 255],
        [80, 30, 180, 255],
        [100, 80, 250, 255],
        [255, 30, 30, 255],
        [255, 40, 200, 255],
        [150, 30, 90, 255],
        [255, 0, 255, 255],
        [255, 150, 255, 255],
        [75, 0, 75, 255],
        [175, 0, 75, 255],
        [255, 200, 0, 255],
        [255, 120, 50, 255],
        [0, 175, 0, 255],
        [135, 60, 0, 255],
        [150, 240, 80, 255],
        [255, 240, 150, 255],
        [255, 0, 0, 255]]) / 255.0


    grid_coords, _, _, _ = get_grid_coords([voxels.shape[0], voxels.shape[1], voxels.shape[2]], voxel_size)    

    points = np.vstack([grid_coords.T, voxels.reshape(-1)]).T

    # Obtaining voxels with semantic class
    points = points[(points[:, 3] != 0) & (points[:, 3] != 255)] # remove empty voxel and unknown class

    colors = np.take_along_axis(colors, points[:, 3].astype(np.int32).reshape(-1, 1), axis=0)
    
    vis = o3d.visualization.Visualizer()
    vis.create_window(width=1200, height=600)
    ctr = vis.get_view_control()
    param = o3d.io.read_pinhole_camera_parameters(cam_param_path)

    pcd = o3d.geometry.PointCloud()
    pcd.points = o3d.utility.Vector3dVector(points[:, :3])
    pcd.colors = o3d.utility.Vector3dVector(colors[:, :3])
    pcd.estimate_normals()
    vis.add_geometry(pcd)

    ctr.convert_from_pinhole_camera_parameters(param)

    vis.run()  # user changes the view and press "q" to terminate
    param = vis.get_view_control().convert_to_pinhole_camera_parameters()
    o3d.io.write_pinhole_camera_parameters(cam_param_path, param)

[Steven0928]

Thanks!
It works!

[anhquancao]

Perfect!

[AniketDhar]

What is the "cam_param_path" for Kitti-360 dataset?

[anhquancao]

Hi @AniketDhar, I don't remember how did I got the params but I set them directly in the code.

[AniketDhar]

Hi @AniketDhar, I don't remember how did I got the params but I set them directly in the code.

Thanks for the quick response. I saw a filepath, so I expected there might be a json file that I am missing somewhere. But just to be clear, for the Open3D visualizer, you set the camera parameters into a file and load that to o3d.io.read_pinhole_camera_parameters(cam_param_path). Is that correct?

[anhquancao]

ah I understand what you mean. You can provide an arbitrary filepath, if the file is not exist, a camera parameter config file will be saved there.