nuScenes-panoptic v1.0 release (nutonomy#628)

* nuScenes-panoptic v1.0 code release, challenge announcement

* Add LSTQ panoptic tracking metric

* Fix jenkins failure

* Address review comments

* Address review comments

README.md

@@ -10,6 +10,7 @@ Welcome to the devkit of the [nuScenes](https://www.nuscenes.org/nuscenes) and [
   - [Getting started with nuImages](#getting-started-with-nuimages)
 - [nuScenes](#nuscenes)
   - [nuScenes setup](#nuscenes-setup)
+  - [nuScenes-panoptic](#nuscenes-panoptic)
   - [nuScenes-lidarseg](#nuscenes-lidarseg)
   - [Prediction challenge](#prediction-challenge)
   - [CAN bus expansion](#can-bus-expansion)
@@ -20,6 +21,7 @@ Welcome to the devkit of the [nuScenes](https://www.nuscenes.org/nuscenes) and [
 - [Citation](#citation)
 
 ## Changelog
+- Jul. 29, 2020: Devkit v1.2.0: nuScenes-panoptic v1.0 code, NeurIPS challenge announcement.
 - Apr. 5, 2021: Devkit v1.1.3: Bug fixes and pip requirements.
 - Nov. 23, 2020: Devkit v1.1.2: Release map-expansion v1.3 with lidar basemap.
 - Nov. 9, 2020: Devkit v1.1.1: Lidarseg evaluation code, NeurIPS challenge announcement.
@@ -97,14 +99,23 @@ Eventually you should have the following folder structure:
 ```
 If you want to use another folder, specify the `dataroot` parameter of the NuScenes class (see tutorial).
 
+### nuScenes-panoptic
+In August 2021 we published [nuScenes-panoptic](https://www.nuscenes.org/nuscenes) which contains the panoptic
+labels of the point clouds for the approximately 40,000 keyframes in nuScenes.
+To install nuScenes-panoptic, please follow these steps:
+- Download the dataset from the [Download page](https://www.nuscenes.org/download),
+- Extract the `panoptic` and `v1.0-*` folders to your nuScenes root directory (e.g. `/data/sets/nuscenes/panoptic`, `/data/sets/nuscenes/v1.0-*`).
+- Get the latest version of the nuscenes-devkit.
+- Get started with the [tutorial](https://github.com/nutonomy/nuscenes-devkit/blob/master/python-sdk/tutorials/nuscenes_lidarseg_panoptic_tutorial.ipynb).
+
 ### nuScenes-lidarseg
 In August 2020 we published [nuScenes-lidarseg](https://www.nuscenes.org/nuscenes#lidarseg) which contains the semantic labels of the point clouds for the approximately 40,000 keyframes in nuScenes.
 To install nuScenes-lidarseg, please follow these steps:
 - Download the dataset from the [Download page](https://www.nuscenes.org/download),
 - Extract the `lidarseg` and `v1.0-*` folders to your nuScenes root directory (e.g. `/data/sets/nuscenes/lidarseg`, `/data/sets/nuscenes/v1.0-*`).
 - Get the latest version of the nuscenes-devkit.
 - If you already have a previous version of the devkit, update the pip requirements (see [details](https://github.com/nutonomy/nuscenes-devkit/blob/master/docs/installation.md)): `pip install -r setup/requirements.txt`
-- Get started with the [tutorial](https://github.com/nutonomy/nuscenes-devkit/blob/master/python-sdk/tutorials/nuscenes_lidarseg_tutorial.ipynb).
+- Get started with the [tutorial](https://github.com/nutonomy/nuscenes-devkit/blob/master/python-sdk/tutorials/nuscenes_lidarseg_panoptic_tutorial.ipynb).
 
 ### Prediction challenge
 In March 2020 we released code for the nuScenes prediction challenge.

python-sdk/nuscenes/eval/lidarseg/README.md

@@ -104,7 +104,7 @@ The folder structure of the results should be as follows:
                                 the submission
 ```
 
-The contents of the `submision.json` file and `test` folder are defined below: 
+The contents of the `submission.json` file and `test` folder are defined below:
 * The `submission.json` file includes meta data `meta` on the type of inputs used for this method.
   ```
   "meta": {

python-sdk/nuscenes/eval/lidarseg/evaluate.py

@@ -3,11 +3,11 @@
 import os
 from typing import Dict
 
-import numpy as np
 from tqdm import tqdm
 
 from nuscenes import NuScenes
-from nuscenes.eval.lidarseg.utils import LidarsegClassMapper, ConfusionMatrix, get_samples_in_eval_set, load_bin_file
+from nuscenes.eval.lidarseg.utils import ConfusionMatrix, LidarsegClassMapper, get_samples_in_eval_set
+from nuscenes.utils.data_io import load_bin_file
 
 
 class LidarSegEval:

python-sdk/nuscenes/eval/lidarseg/render.py

@@ -10,8 +10,9 @@
 
 from nuscenes import NuScenes
 from nuscenes.eval.lidarseg.evaluate import LidarSegEval
-from nuscenes.eval.lidarseg.utils import ConfusionMatrix, LidarsegClassMapper, load_bin_file, LidarSegPointCloud
-from nuscenes.lidarseg.lidarseg_utils import colormap_to_colors, create_lidarseg_legend, get_labels_in_coloring
+from nuscenes.eval.lidarseg.utils import ConfusionMatrix, LidarsegClassMapper
+from nuscenes.lidarseg.lidarseg_utils import colormap_to_colors
+from nuscenes.utils.data_classes import LidarSegPointCloud
 
 
 class LidarSegEvalStratified(LidarSegEval):

python-sdk/nuscenes/eval/lidarseg/utils.py

@@ -1,12 +1,7 @@
-import os
 from typing import Dict, List, Tuple
 
-from matplotlib import axes
 import numpy as np
-
 from nuscenes import NuScenes
-from nuscenes.lidarseg.lidarseg_utils import colormap_to_colors, create_lidarseg_legend, get_labels_in_coloring
-from nuscenes.utils.data_classes import LidarPointCloud
 from nuscenes.utils.splits import create_splits_scenes
 
 
@@ -357,78 +352,3 @@ def get_samples_in_eval_set(nusc: NuScenes, eval_set: str) -> List[str]:
                                        'but only {} keyframes were processed'.format(total_num_samples, i)
 
     return samples
-
-
-def load_bin_file(bin_path: str) -> np.ndarray:
-    """
-    Loads a .bin file containing the labels.
-    :param bin_path: Path to the .bin file.
-    :return: An array containing the labels.
-    """
-    assert os.path.exists(bin_path), 'Error: Unable to find {}.'.format(bin_path)
-    bin_content = np.fromfile(bin_path, dtype=np.uint8)
-    assert len(bin_content) > 0, 'Error: {} is empty.'.format(bin_path)
-
-    return bin_content
-
-
-class LidarSegPointCloud:
-    """
-    Class for a point cloud.
-    """
-    def __init__(self, points_path: str = None, labels_path: str = None):
-        """
-        Initialize a LidarSegPointCloud object.
-        :param points_path: Path to the bin file containing the x, y, z and intensity of the points in the point cloud.
-        :param labels_path: Path to the bin file containing the labels of the points in the point cloud.
-        """
-        self.points, self.labels = None, None
-        if points_path:
-            self.load_points(points_path)
-        if labels_path:
-            self.load_labels(labels_path)
-
-    def load_points(self, path: str) -> None:
-        """
-        Loads the x, y, z and intensity of the points in the point cloud.
-        :param path: Path to the bin file containing the x, y, z and intensity of the points in the point cloud.
-        """
-        self.points = LidarPointCloud.from_file(path).points.T  # [N, 4], where N is the number of points.
-        if self.labels is not None:
-            assert len(self.points) == len(self.labels), 'Error: There are {} points in the point cloud, ' \
-                                                         'but {} labels'.format(len(self.points), len(self.labels))
-
-    def load_labels(self, path: str) -> None:
-        """
-        Loads the labels of the points in the point cloud.
-        :param path: Path to the bin file containing the labels of the points in the point cloud.
-        """
-        self.labels = load_bin_file(path)
-        if self.points is not None:
-            assert len(self.points) == len(self.labels), 'Error: There are {} points in the point cloud, ' \
-                                                         'but {} labels'.format(len(self.points), len(self.labels))
-
-    def render(self, name2color: Dict[str, Tuple[int]],
-               name2id: Dict[str, int],
-               ax: axes.Axes,
-               title: str = None,
-               dot_size: int = 5) -> axes.Axes:
-        """
-        Renders a point cloud onto an axes.
-        :param name2color: The mapping from class name to class color.
-        :param name2id: A dictionary containing the mapping from class names to class indices.
-        :param ax: Axes onto which to render.
-        :param title: Title of the plot.
-        :param dot_size: Scatter plot dot size.
-        :return: The axes onto which the point cloud has been rendered.
-        """
-        colors = colormap_to_colors(name2color, name2id)
-        ax.scatter(self.points[:, 0], self.points[:, 1], c=colors[self.labels], s=dot_size)
-
-        id2name = {idx: name for name, idx in name2id.items()}
-        create_lidarseg_legend(self.labels, id2name, name2color, ax=ax)
-
-        if title:
-            ax.set_title(title)
-
-        return ax