Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "faa0a6c40c0747ec4efcf9b0488f852f98ce1abc"
Commit c2fe651f authored by zhangshilong's avatar zhangshilong Committed by ChaimZhu
Browse files

refactor directory

parent bc5806ba
Hide whitespace changes
Inline Side-by-side
Showing with 80 additions and 842 deletions
mmdet3d/datasets/nuscenes_mono_dataset.py deleted 100644 → 0
View file @ bc5806ba
# Copyright (c) OpenMMLab. All rights reserved.
import copy
import tempfile
import warnings
from os import path as osp
import mmcv
import numpy as np
import pyquaternion
import torch
from nuscenes.utils.data_classes import Box as NuScenesBox
from mmdet3d.core import bbox3d2result, box3d_multiclass_nms, xywhr2xyxyr
from mmdet3d.registry import DATASETS
from mmdet.datasets import CocoDataset
from ..core import show_multi_modality_result
from ..core.bbox import CameraInstance3DBoxes, get_box_type
from .pipelines import Compose
from .utils import extract_result_dict, get_loading_pipeline
@DATASETS.register_module()
class NuScenesMonoDataset(CocoDataset):
r"""Monocular 3D detection on NuScenes Dataset.
This class serves as the API for experiments on the NuScenes Dataset.
Please refer to `NuScenes Dataset <https://www.nuscenes.org/download>`_
for data downloading.
Args:
ann_file (str): Path of annotation file.
data_root (str): Path of dataset root.
load_interval (int, optional): Interval of loading the dataset. It is
used to uniformly sample the dataset. Defaults to 1.
with_velocity (bool, optional): Whether include velocity prediction
into the experiments. Defaults to True.
modality (dict, optional): Modality to specify the sensor data used
as input. Defaults to None.
box_type_3d (str, optional): Type of 3D box of this dataset.
Based on the `box_type_3d`, the dataset will encapsulate the box
to its original format then converted them to `box_type_3d`.
Defaults to 'Camera' in this class. Available options includes.
- 'LiDAR': Box in LiDAR coordinates.
- 'Depth': Box in depth coordinates, usually for indoor dataset.
- 'Camera': Box in camera coordinates.
eval_version (str, optional): Configuration version of evaluation.
Defaults to 'detection_cvpr_2019'.
use_valid_flag (bool, optional): Whether to use `use_valid_flag` key
in the info file as mask to filter gt_boxes and gt_names.
Defaults to False.
version (str, optional): Dataset version. Defaults to 'v1.0-trainval'.
"""
CLASSES = ('car', 'truck', 'trailer', 'bus', 'construction_vehicle',
'bicycle', 'motorcycle', 'pedestrian', 'traffic_cone',
'barrier')
DefaultAttribute = {
'car': 'vehicle.parked',
'pedestrian': 'pedestrian.moving',
'trailer': 'vehicle.parked',
'truck': 'vehicle.parked',
'bus': 'vehicle.moving',
'motorcycle': 'cycle.without_rider',
'construction_vehicle': 'vehicle.parked',
'bicycle': 'cycle.without_rider',
'barrier': '',
'traffic_cone': '',
}
# https://github.com/nutonomy/nuscenes-devkit/blob/57889ff20678577025326cfc24e57424a829be0a/python-sdk/nuscenes/eval/detection/evaluate.py#L222 # noqa
ErrNameMapping = {
'trans_err': 'mATE',
'scale_err': 'mASE',
'orient_err': 'mAOE',
'vel_err': 'mAVE',
'attr_err': 'mAAE'
}
def __init__(self,
data_root,
load_interval=1,
with_velocity=True,
modality=None,
box_type_3d='Camera',
eval_version='detection_cvpr_2019',
use_valid_flag=False,
version='v1.0-trainval',
**kwargs):
super().__init__(**kwargs)
self.data_root = data_root
self.load_interval = load_interval
self.with_velocity = with_velocity
self.modality = modality
self.box_type_3d, self.box_mode_3d = get_box_type(box_type_3d)
self.eval_version = eval_version
self.use_valid_flag = use_valid_flag
self.bbox_code_size = 9
self.version = version
if self.eval_version is not None:
from nuscenes.eval.detection.config import config_factory
self.eval_detection_configs = config_factory(self.eval_version)
if self.modality is None:
self.modality = dict(
use_camera=True,
use_lidar=False,
use_radar=False,
use_map=False,
use_external=False)
def pre_pipeline(self, results):
"""Initialization before data preparation.
Args:
results (dict): Dict before data preprocessing.
- img_fields (list): Image fields.
- bbox3d_fields (list): 3D bounding boxes fields.
- pts_mask_fields (list): Mask fields of points.
- pts_seg_fields (list): Mask fields of point segments.
- bbox_fields (list): Fields of bounding boxes.
- mask_fields (list): Fields of masks.
- seg_fields (list): Segment fields.
- box_type_3d (str): 3D box type.
- box_mode_3d (str): 3D box mode.
"""
results['img_prefix'] = self.img_prefix
results['seg_prefix'] = self.seg_prefix
results['proposal_file'] = self.proposal_file
results['img_fields'] = []
results['bbox3d_fields'] = []
results['pts_mask_fields'] = []
results['pts_seg_fields'] = []
results['bbox_fields'] = []
results['mask_fields'] = []
results['seg_fields'] = []
results['box_type_3d'] = self.box_type_3d
results['box_mode_3d'] = self.box_mode_3d
def _parse_ann_info(self, img_info, ann_info):
"""Parse bbox annotation.
Args:
img_info (list[dict]): Image info.
ann_info (list[dict]): Annotation info of an image.
Returns:
dict: A dict containing the following keys: bboxes, labels,
gt_bboxes_3d, gt_labels_3d, attr_labels, centers2d,
depths, bboxes_ignore, masks, seg_map
"""
gt_bboxes = []
gt_labels = []
attr_labels = []
gt_bboxes_ignore = []
gt_masks_ann = []
gt_bboxes_cam3d = []
centers2d = []
depths = []
for i, ann in enumerate(ann_info):
if ann.get('ignore', False):
continue
x1, y1, w, h = ann['bbox']
inter_w = max(0, min(x1 + w, img_info['width']) - max(x1, 0))
inter_h = max(0, min(y1 + h, img_info['height']) - max(y1, 0))
if inter_w * inter_h == 0:
continue
if ann['area'] <= 0 or w < 1 or h < 1:
continue
if ann['category_id'] not in self.cat_ids:
continue
bbox = [x1, y1, x1 + w, y1 + h]
if ann.get('iscrowd', False):
gt_bboxes_ignore.append(bbox)
else:
gt_bboxes.append(bbox)
gt_labels.append(self.cat2label[ann['category_id']])
attr_labels.append(ann['attribute_id'])
gt_masks_ann.append(ann.get('segmentation', None))
# 3D annotations in camera coordinates
bbox_cam3d = np.array(ann['bbox_cam3d']).reshape(1, -1)
velo_cam3d = np.array(ann['velo_cam3d']).reshape(1, 2)
nan_mask = np.isnan(velo_cam3d[:, 0])
velo_cam3d[nan_mask] = [0.0, 0.0]
bbox_cam3d = np.concatenate([bbox_cam3d, velo_cam3d], axis=-1)
gt_bboxes_cam3d.append(bbox_cam3d.squeeze())
# 2.5D annotations in camera coordinates
center2d = ann['center2d'][:2]
depth = ann['center2d'][2]
centers2d.append(center2d)
depths.append(depth)
if gt_bboxes:
gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
gt_labels = np.array(gt_labels, dtype=np.int64)
attr_labels = np.array(attr_labels, dtype=np.int64)
else:
gt_bboxes = np.zeros((0, 4), dtype=np.float32)
gt_labels = np.array([], dtype=np.int64)
attr_labels = np.array([], dtype=np.int64)
if gt_bboxes_cam3d:
gt_bboxes_cam3d = np.array(gt_bboxes_cam3d, dtype=np.float32)
centers2d = np.array(centers2d, dtype=np.float32)
depths = np.array(depths, dtype=np.float32)
else:
gt_bboxes_cam3d = np.zeros((0, self.bbox_code_size),
dtype=np.float32)
centers2d = np.zeros((0, 2), dtype=np.float32)
depths = np.zeros((0), dtype=np.float32)
gt_bboxes_cam3d = CameraInstance3DBoxes(
gt_bboxes_cam3d,
box_dim=gt_bboxes_cam3d.shape[-1],
origin=(0.5, 0.5, 0.5))
gt_labels_3d = copy.deepcopy(gt_labels)
if gt_bboxes_ignore:
gt_bboxes_ignore = np.array(gt_bboxes_ignore, dtype=np.float32)
else:
gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
seg_map = img_info['filename'].replace('jpg', 'png')
ann = dict(
bboxes=gt_bboxes,
labels=gt_labels,
gt_bboxes_3d=gt_bboxes_cam3d,
gt_labels_3d=gt_labels_3d,
attr_labels=attr_labels,
centers2d=centers2d,
depths=depths,
bboxes_ignore=gt_bboxes_ignore,
masks=gt_masks_ann,
seg_map=seg_map)
return ann
def get_attr_name(self, attr_idx, label_name):
"""Get attribute from predicted index.
This is a workaround to predict attribute when the predicted velocity
is not reliable. We map the predicted attribute index to the one
in the attribute set. If it is consistent with the category, we will
keep it. Otherwise, we will use the default attribute.
Args:
attr_idx (int): Attribute index.
label_name (str): Predicted category name.
Returns:
str: Predicted attribute name.
"""
# TODO: Simplify the variable name
AttrMapping_rev2 = [
'cycle.with_rider', 'cycle.without_rider', 'pedestrian.moving',
'pedestrian.standing', 'pedestrian.sitting_lying_down',
'vehicle.moving', 'vehicle.parked', 'vehicle.stopped', 'None'
]
if label_name == 'car' or label_name == 'bus' \
or label_name == 'truck' or label_name == 'trailer' \
or label_name == 'construction_vehicle':
if AttrMapping_rev2[attr_idx] == 'vehicle.moving' or \
AttrMapping_rev2[attr_idx] == 'vehicle.parked' or \
AttrMapping_rev2[attr_idx] == 'vehicle.stopped':
return AttrMapping_rev2[attr_idx]
else:
return NuScenesMonoDataset.DefaultAttribute[label_name]
elif label_name == 'pedestrian':
if AttrMapping_rev2[attr_idx] == 'pedestrian.moving' or \
AttrMapping_rev2[attr_idx] == 'pedestrian.standing' or \
AttrMapping_rev2[attr_idx] == \
'pedestrian.sitting_lying_down':
return AttrMapping_rev2[attr_idx]
else:
return NuScenesMonoDataset.DefaultAttribute[label_name]
elif label_name == 'bicycle' or label_name == 'motorcycle':
if AttrMapping_rev2[attr_idx] == 'cycle.with_rider' or \
AttrMapping_rev2[attr_idx] == 'cycle.without_rider':
return AttrMapping_rev2[attr_idx]
else:
return NuScenesMonoDataset.DefaultAttribute[label_name]
else:
return NuScenesMonoDataset.DefaultAttribute[label_name]
def _format_bbox(self, results, jsonfile_prefix=None):
"""Convert the results to the standard format.
Args:
results (list[dict]): Testing results of the dataset.
jsonfile_prefix (str): The prefix of the output jsonfile.
You can specify the output directory/filename by
modifying the jsonfile_prefix. Default: None.
Returns:
str: Path of the output json file.
"""
nusc_annos = {}
mapped_class_names = self.CLASSES
print('Start to convert detection format...')
CAM_NUM = 6
for sample_id, det in enumerate(mmcv.track_iter_progress(results)):
if sample_id % CAM_NUM == 0:
boxes_per_frame = []
attrs_per_frame = []
# need to merge results from images of the same sample
annos = []
boxes, attrs = output_to_nusc_box(det)
sample_token = self.data_infos[sample_id]['token']
boxes, attrs = cam_nusc_box_to_global(self.data_infos[sample_id],
boxes, attrs,
mapped_class_names,
self.eval_detection_configs,
self.eval_version)
boxes_per_frame.extend(boxes)
attrs_per_frame.extend(attrs)
# Remove redundant predictions caused by overlap of images
if (sample_id + 1) % CAM_NUM != 0:
continue
boxes = global_nusc_box_to_cam(
self.data_infos[sample_id + 1 - CAM_NUM], boxes_per_frame,
mapped_class_names, self.eval_detection_configs,
self.eval_version)
cam_boxes3d, scores, labels = nusc_box_to_cam_box3d(boxes)
# box nms 3d over 6 images in a frame
# TODO: move this global setting into config
nms_cfg = dict(
use_rotate_nms=True,
nms_across_levels=False,
nms_pre=4096,
nms_thr=0.05,
score_thr=0.01,
min_bbox_size=0,
max_per_frame=500)
from mmcv import Config
nms_cfg = Config(nms_cfg)
cam_boxes3d_for_nms = xywhr2xyxyr(cam_boxes3d.bev)
boxes3d = cam_boxes3d.tensor
# generate attr scores from attr labels
attrs = labels.new_tensor([attr for attr in attrs_per_frame])
boxes3d, scores, labels, attrs = box3d_multiclass_nms(
boxes3d,
cam_boxes3d_for_nms,
scores,
nms_cfg.score_thr,
nms_cfg.max_per_frame,
nms_cfg,
mlvl_attr_scores=attrs)
cam_boxes3d = CameraInstance3DBoxes(boxes3d, box_dim=9)
det = bbox3d2result(cam_boxes3d, scores, labels, attrs)
boxes, attrs = output_to_nusc_box(det)
boxes, attrs = cam_nusc_box_to_global(
self.data_infos[sample_id + 1 - CAM_NUM], boxes, attrs,
mapped_class_names, self.eval_detection_configs,
self.eval_version)
for i, box in enumerate(boxes):
name = mapped_class_names[box.label]
attr = self.get_attr_name(attrs[i], name)
nusc_anno = dict(
sample_token=sample_token,
translation=box.center.tolist(),
size=box.wlh.tolist(),
rotation=box.orientation.elements.tolist(),
velocity=box.velocity[:2].tolist(),
detection_name=name,
detection_score=box.score,
attribute_name=attr)
annos.append(nusc_anno)
# other views results of the same frame should be concatenated
if sample_token in nusc_annos:
nusc_annos[sample_token].extend(annos)
else:
nusc_annos[sample_token] = annos
nusc_submissions = {
'meta': self.modality,
'results': nusc_annos,
}
mmcv.mkdir_or_exist(jsonfile_prefix)
res_path = osp.join(jsonfile_prefix, 'results_nusc.json')
print('Results writes to', res_path)
mmcv.dump(nusc_submissions, res_path)
return res_path
def _evaluate_single(self,
result_path,
logger=None,
metric='bbox',
result_name='img_bbox'):
"""Evaluation for a single model in nuScenes protocol.
Args:
result_path (str): Path of the result file.
logger (logging.Logger | str, optional): Logger used for printing
related information during evaluation. Default: None.
metric (str, optional): Metric name used for evaluation.
Default: 'bbox'.
result_name (str, optional): Result name in the metric prefix.
Default: 'img_bbox'.
Returns:
dict: Dictionary of evaluation details.
"""
from nuscenes import NuScenes
from nuscenes.eval.detection.evaluate import NuScenesEval
output_dir = osp.join(*osp.split(result_path)[:-1])
nusc = NuScenes(
version=self.version, dataroot=self.data_root, verbose=False)
eval_set_map = {
'v1.0-mini': 'mini_val',
'v1.0-trainval': 'val',
}
nusc_eval = NuScenesEval(
nusc,
config=self.eval_detection_configs,
result_path=result_path,
eval_set=eval_set_map[self.version],
output_dir=output_dir,
verbose=False)
nusc_eval.main(render_curves=True)
# record metrics
metrics = mmcv.load(osp.join(output_dir, 'metrics_summary.json'))
detail = dict()
metric_prefix = f'{result_name}_NuScenes'
for name in self.CLASSES:
for k, v in metrics['label_aps'][name].items():
val = float('{:.4f}'.format(v))
detail['{}/{}_AP_dist_{}'.format(metric_prefix, name, k)] = val
for k, v in metrics['label_tp_errors'][name].items():
val = float('{:.4f}'.format(v))
detail['{}/{}_{}'.format(metric_prefix, name, k)] = val
for k, v in metrics['tp_errors'].items():
val = float('{:.4f}'.format(v))
detail['{}/{}'.format(metric_prefix,
self.ErrNameMapping[k])] = val
detail['{}/NDS'.format(metric_prefix)] = metrics['nd_score']
detail['{}/mAP'.format(metric_prefix)] = metrics['mean_ap']
return detail
def format_results(self, results, jsonfile_prefix=None, **kwargs):
"""Format the results to json (standard format for COCO evaluation).
Args:
results (list[tuple | numpy.ndarray]): Testing results of the
dataset.
jsonfile_prefix (str): The prefix of json files. It includes
the file path and the prefix of filename, e.g., "a/b/prefix".
If not specified, a temp file will be created. Default: None.
Returns:
tuple: (result_files, tmp_dir), result_files is a dict containing
the json filepaths, tmp_dir is the temporal directory created
for saving json files when jsonfile_prefix is not specified.
"""
assert isinstance(results, list), 'results must be a list'
assert len(results) == len(self), (
'The length of results is not equal to the dataset len: {} != {}'.
format(len(results), len(self)))
if jsonfile_prefix is None:
tmp_dir = tempfile.TemporaryDirectory()
jsonfile_prefix = osp.join(tmp_dir.name, 'results')
else:
tmp_dir = None
# currently the output prediction results could be in two formats
# 1. list of dict('boxes_3d': ..., 'scores_3d': ..., 'labels_3d': ...)
# 2. list of dict('pts_bbox' or 'img_bbox':
# dict('boxes_3d': ..., 'scores_3d': ..., 'labels_3d': ...))
# this is a workaround to enable evaluation of both formats on nuScenes
# refer to https://github.com/open-mmlab/mmdetection3d/issues/449
if not ('pts_bbox' in results[0] or 'img_bbox' in results[0]):
result_files = self._format_bbox(results, jsonfile_prefix)
else:
# should take the inner dict out of 'pts_bbox' or 'img_bbox' dict
result_files = dict()
for name in results[0]:
# not evaluate 2D predictions on nuScenes
if '2d' in name:
continue
print(f'\nFormating bboxes of {name}')
results_ = [out[name] for out in results]
tmp_file_ = osp.join(jsonfile_prefix, name)
result_files.update(
{name: self._format_bbox(results_, tmp_file_)})
return result_files, tmp_dir
def evaluate(self,
results,
metric='bbox',
logger=None,
jsonfile_prefix=None,
result_names=['img_bbox'],
show=False,
out_dir=None,
pipeline=None):
"""Evaluation in nuScenes protocol.
Args:
results (list[dict]): Testing results of the dataset.
metric (str | list[str], optional): Metrics to be evaluated.
Default: 'bbox'.
logger (logging.Logger | str, optional): Logger used for printing
related information during evaluation. Default: None.
jsonfile_prefix (str): The prefix of json files. It includes
the file path and the prefix of filename, e.g., "a/b/prefix".
If not specified, a temp file will be created. Default: None.
result_names (list[str], optional): Result names in the
metric prefix. Default: ['img_bbox'].
show (bool, optional): Whether to visualize.
Default: False.
out_dir (str, optional): Path to save the visualization results.
Default: None.
pipeline (list[dict], optional): raw data loading for showing.
Default: None.
Returns:
dict[str, float]: Results of each evaluation metric.
"""
result_files, tmp_dir = self.format_results(results, jsonfile_prefix)
if isinstance(result_files, dict):
results_dict = dict()
for name in result_names:
print('Evaluating bboxes of {}'.format(name))
ret_dict = self._evaluate_single(result_files[name])
results_dict.update(ret_dict)
elif isinstance(result_files, str):
results_dict = self._evaluate_single(result_files)
if tmp_dir is not None:
tmp_dir.cleanup()
if show or out_dir:
self.show(results, out_dir, pipeline=pipeline)
return results_dict
def _extract_data(self, index, pipeline, key, load_annos=False):
"""Load data using input pipeline and extract data according to key.
Args:
index (int): Index for accessing the target data.
pipeline (:obj:`Compose`): Composed data loading pipeline.
key (str | list[str]): One single or a list of data key.
load_annos (bool): Whether to load data annotations.
If True, need to set self.test_mode as False before loading.
Returns:
np.ndarray | torch.Tensor | list[np.ndarray | torch.Tensor]:
A single or a list of loaded data.
"""
assert pipeline is not None, 'data loading pipeline is not provided'
img_info = self.data_infos[index]
input_dict = dict(img_info=img_info)
if load_annos:
ann_info = self.get_ann_info(index)
input_dict.update(dict(ann_info=ann_info))
self.pre_pipeline(input_dict)
example = pipeline(input_dict)
# extract data items according to keys
if isinstance(key, str):
data = extract_result_dict(example, key)
else:
data = [extract_result_dict(example, k) for k in key]
return data
def _get_pipeline(self, pipeline):
"""Get data loading pipeline in self.show/evaluate function.
Args:
pipeline (list[dict]): Input pipeline. If None is given,
get from self.pipeline.
"""
if pipeline is None:
if not hasattr(self, 'pipeline') or self.pipeline is None:
warnings.warn(
'Use default pipeline for data loading, this may cause '
'errors when data is on ceph')
return self._build_default_pipeline()
loading_pipeline = get_loading_pipeline(self.pipeline.transforms)
return Compose(loading_pipeline)
return Compose(pipeline)
def _build_default_pipeline(self):
"""Build the default pipeline for this dataset."""
pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='DefaultFormatBundle3D',
class_names=self.CLASSES,
with_label=False),
dict(type='Collect3D', keys=['img'])
]
return Compose(pipeline)
def show(self, results, out_dir, show=False, pipeline=None):
"""Results visualization.
Args:
results (list[dict]): List of bounding boxes results.
out_dir (str): Output directory of visualization result.
show (bool): Whether to visualize the results online.
Default: False.
pipeline (list[dict], optional): raw data loading for showing.
Default: None.
"""
assert out_dir is not None, 'Expect out_dir, got none.'
pipeline = self._get_pipeline(pipeline)
for i, result in enumerate(results):
if 'img_bbox' in result.keys():
result = result['img_bbox']
data_info = self.data_infos[i]
img_path = data_info['file_name']
file_name = osp.split(img_path)[-1].split('.')[0]
img, img_metas = self._extract_data(i, pipeline,
['img', 'img_metas'])
# need to transpose channel to first dim
img = img.numpy().transpose(1, 2, 0)
gt_bboxes = self.get_ann_info(i)['gt_bboxes_3d']
pred_bboxes = result['boxes_3d']
show_multi_modality_result(
img,
gt_bboxes,
pred_bboxes,
img_metas['cam2img'],
out_dir,
file_name,
box_mode='camera',
show=show)
def output_to_nusc_box(detection):
"""Convert the output to the box class in the nuScenes.
Args:
detection (dict): Detection results.
- boxes_3d (:obj:`BaseInstance3DBoxes`): Detection bbox.
- scores_3d (torch.Tensor): Detection scores.
- labels_3d (torch.Tensor): Predicted box labels.
- attrs_3d (torch.Tensor, optional): Predicted attributes.
Returns:
list[:obj:`NuScenesBox`]: List of standard NuScenesBoxes.
"""
box3d = detection['boxes_3d']
scores = detection['scores_3d'].numpy()
labels = detection['labels_3d'].numpy()
attrs = None
if 'attrs_3d' in detection:
attrs = detection['attrs_3d'].numpy()
box_gravity_center = box3d.gravity_center.numpy()
box_dims = box3d.dims.numpy()
box_yaw = box3d.yaw.numpy()
# convert the dim/rot to nuscbox convention
box_dims[:, [0, 1, 2]] = box_dims[:, [2, 0, 1]]
box_yaw = -box_yaw
box_list = []
for i in range(len(box3d)):
q1 = pyquaternion.Quaternion(axis=[0, 0, 1], radians=box_yaw[i])
q2 = pyquaternion.Quaternion(axis=[1, 0, 0], radians=np.pi / 2)
quat = q2 * q1
velocity = (box3d.tensor[i, 7], 0.0, box3d.tensor[i, 8])
box = NuScenesBox(
box_gravity_center[i],
box_dims[i],
quat,
label=labels[i],
score=scores[i],
velocity=velocity)
box_list.append(box)
return box_list, attrs
def cam_nusc_box_to_global(info,
boxes,
attrs,
classes,
eval_configs,
eval_version='detection_cvpr_2019'):
"""Convert the box from camera to global coordinate.
Args:
info (dict): Info for a specific sample data, including the
calibration information.
boxes (list[:obj:`NuScenesBox`]): List of predicted NuScenesBoxes.
classes (list[str]): Mapped classes in the evaluation.
eval_configs (object): Evaluation configuration object.
eval_version (str, optional): Evaluation version.
Default: 'detection_cvpr_2019'
Returns:
list: List of standard NuScenesBoxes in the global
coordinate.
"""
box_list = []
attr_list = []
for (box, attr) in zip(boxes, attrs):
# Move box to ego vehicle coord system
box.rotate(pyquaternion.Quaternion(info['cam2ego_rotation']))
box.translate(np.array(info['cam2ego_translation']))
# filter det in ego.
cls_range_map = eval_configs.class_range
radius = np.linalg.norm(box.center[:2], 2)
det_range = cls_range_map[classes[box.label]]
if radius > det_range:
continue
# Move box to global coord system
box.rotate(pyquaternion.Quaternion(info['ego2global_rotation']))
box.translate(np.array(info['ego2global_translation']))
box_list.append(box)
attr_list.append(attr)
return box_list, attr_list
def global_nusc_box_to_cam(info,
boxes,
classes,
eval_configs,
eval_version='detection_cvpr_2019'):
"""Convert the box from global to camera coordinate.
Args:
info (dict): Info for a specific sample data, including the
calibration information.
boxes (list[:obj:`NuScenesBox`]): List of predicted NuScenesBoxes.
classes (list[str]): Mapped classes in the evaluation.
eval_configs (object): Evaluation configuration object.
eval_version (str, optional): Evaluation version.
Default: 'detection_cvpr_2019'
Returns:
list: List of standard NuScenesBoxes in the global
coordinate.
"""
box_list = []
for box in boxes:
# Move box to ego vehicle coord system
box.translate(-np.array(info['ego2global_translation']))
box.rotate(
pyquaternion.Quaternion(info['ego2global_rotation']).inverse)
# filter det in ego.
cls_range_map = eval_configs.class_range
radius = np.linalg.norm(box.center[:2], 2)
det_range = cls_range_map[classes[box.label]]
if radius > det_range:
continue
# Move box to camera coord system
box.translate(-np.array(info['cam2ego_translation']))
box.rotate(pyquaternion.Quaternion(info['cam2ego_rotation']).inverse)
box_list.append(box)
return box_list
def nusc_box_to_cam_box3d(boxes):
"""Convert boxes from :obj:`NuScenesBox` to :obj:`CameraInstance3DBoxes`.
Args:
boxes (list[:obj:`NuScenesBox`]): List of predicted NuScenesBoxes.
Returns:
tuple (:obj:`CameraInstance3DBoxes` | torch.Tensor | torch.Tensor):
Converted 3D bounding boxes, scores and labels.
"""
locs = torch.Tensor([b.center for b in boxes]).view(-1, 3)
dims = torch.Tensor([b.wlh for b in boxes]).view(-1, 3)
rots = torch.Tensor([b.orientation.yaw_pitch_roll[0]
for b in boxes]).view(-1, 1)
velocity = torch.Tensor([b.velocity[0::2] for b in boxes]).view(-1, 2)
# convert nusbox to cambox convention
dims[:, [0, 1, 2]] = dims[:, [1, 2, 0]]
rots = -rots
boxes_3d = torch.cat([locs, dims, rots, velocity], dim=1).cuda()
cam_boxes3d = CameraInstance3DBoxes(
boxes_3d, box_dim=9, origin=(0.5, 0.5, 0.5))
scores = torch.Tensor([b.score for b in boxes]).cuda()
labels = torch.LongTensor([b.label for b in boxes]).cuda()
nms_scores = scores.new_zeros(scores.shape[0], 10 + 1)
indices = labels.new_tensor(list(range(scores.shape[0])))
nms_scores[indices, labels] = scores
return cam_boxes3d, nms_scores, labels
mmdet3d/datasets/s3dis_dataset.py
View file @ c2fe651f
......@@ -4,11 +4,11 @@ from typing import Callable, List, Optional, Union
import numpy as np
from mmdet3d.core.bbox import DepthInstance3DBoxes
from mmdet3d.registry import DATASETS
from mmdet3d.structures import DepthInstance3DBoxes
from .det3d_dataset import Det3DDataset
from .pipelines import Compose
from .seg3d_dataset import Seg3DDataset
from .transforms import Compose
@DATASETS.register_module()
......@@ -118,7 +118,7 @@ class S3DISDataset(Det3DDataset):
Returns:
dict: Data information that will be passed to the data
preprocessing pipelines. It includes the following keys:
preprocessing transforms. It includes the following keys:
- pts_filename (str): Filename of point clouds.
- file_name (str): Filename of point clouds.
......
mmdet3d/datasets/scannet_dataset.py
View file @ c2fe651f
......@@ -5,8 +5,8 @@ from typing import Callable, List, Optional, Union
import numpy as np
from mmdet3d.core.bbox import DepthInstance3DBoxes
from mmdet3d.registry import DATASETS
from mmdet3d.structures import DepthInstance3DBoxes
from .det3d_dataset import Det3DDataset
from .seg3d_dataset import Seg3DDataset
......@@ -111,7 +111,7 @@ class ScanNetDataset(Det3DDataset):
Returns:
dict: Data information that will be passed to the data
preprocessing pipelines. It includes the following keys:
preprocessing transforms. It includes the following keys:
"""
info['axis_align_matrix'] = self._get_axis_align_matrix(info)
info['pts_instance_mask_path'] = osp.join(
......
mmdet3d/datasets/seg3d_dataset.py
View file @ c2fe651f
......@@ -242,7 +242,7 @@ class Seg3DDataset(BaseDataset):
# use it in PointSegClassMapping pipeline
info['label_mapping'] = self.label_mapping
# 'eval_ann_info' will be updated in loading pipelines
# 'eval_ann_info' will be updated in loading transforms
if self.test_mode and self.load_eval_anns:
info['eval_ann_info'] = dict()
......
mmdet3d/datasets/sunrgbd_dataset.py
View file @ c2fe651f
......@@ -5,8 +5,8 @@ from typing import Callable, List, Optional, Union
import numpy as np
from mmdet3d.core.bbox import DepthInstance3DBoxes
from mmdet3d.registry import DATASETS
from mmdet3d.structures import DepthInstance3DBoxes
from .det3d_dataset import Det3DDataset
......
mmdet3d/datasets/pipelines/data_augment_utils.py → mmdet3d/datasets/transforms/data_augment_utils.py
View file @ c2fe651f
......@@ -5,7 +5,7 @@ import numba
import numpy as np
from numba.core.errors import NumbaPerformanceWarning
from mmdet3d.core.bbox import box_np_ops
from mmdet3d.structures.ops import box_np_ops
warnings.filterwarnings('ignore', category=NumbaPerformanceWarning)
......
mmdet3d/datasets/pipelines/dbsampler.py → mmdet3d/datasets/transforms/dbsampler.py
View file @ c2fe651f
......@@ -6,9 +6,9 @@ import warnings
import mmcv
import numpy as np
from mmdet3d.core.bbox import box_np_ops
from mmdet3d.datasets.pipelines import data_augment_utils
from mmdet3d.datasets.transforms import data_augment_utils
from mmdet3d.registry import TRANSFORMS
from mmdet3d.structures.ops import box_np_ops
class BatchSampler:
......
mmdet3d/datasets/pipelines/formating.py → mmdet3d/datasets/transforms/formating.py
View file @ c2fe651f
......@@ -8,10 +8,9 @@ from mmcv import BaseTransform
from mmengine import InstanceData
from numpy import dtype
from mmdet3d.core import Det3DDataSample, PointData
from mmdet3d.core.bbox import BaseInstance3DBoxes
from mmdet3d.core.points import BasePoints
from mmdet3d.registry import TRANSFORMS
from mmdet3d.structures import BaseInstance3DBoxes, Det3DDataSample, PointData
from mmdet3d.structures.points import BasePoints
def to_tensor(
......
mmdet3d/datasets/pipelines/loading.py → mmdet3d/datasets/transforms/loading.py
View file @ c2fe651f
......@@ -6,9 +6,9 @@ import numpy as np
from mmcv.transforms import LoadImageFromFile
from mmcv.transforms.base import BaseTransform
from mmdet3d.core.points import BasePoints, get_points_type
from mmdet3d.registry import TRANSFORMS
from mmdet.datasets.pipelines import LoadAnnotations
from mmdet3d.structures.points import BasePoints, get_points_type
from mmdet.datasets.transforms import LoadAnnotations
@TRANSFORMS.register_module()
......@@ -760,12 +760,6 @@ class LoadAnnotations3D(LoadAnnotations):
else:
results['gt_bboxes'] = np.array(
gt_bboxes, dtype=np.float32).reshape((-1, 4))
if self.denorm_bbox:
bbox_num = results['gt_bboxes'].shape[0]
if bbox_num != 0:
h, w = results['img_shape']
results['gt_bboxes'][:, 0::2] *= w
results['gt_bboxes'][:, 1::2] *= h
if 'eval_ann_info' in results:
results['eval_ann_info']['gt_bboxes'] = results['gt_bboxes']
......
mmdet3d/datasets/pipelines/transforms_3d.py → mmdet3d/datasets/transforms/transforms_3d.py
View file @ c2fe651f
......@@ -8,12 +8,13 @@ import numpy as np
from mmcv import is_tuple_of
from mmcv.transforms import BaseTransform
from mmdet3d.core import VoxelGenerator
from mmdet3d.core.bbox import (CameraInstance3DBoxes, DepthInstance3DBoxes,
LiDARInstance3DBoxes, box_np_ops)
from mmdet3d.core.points import BasePoints
from mmdet3d.models.task_modules import VoxelGenerator
from mmdet3d.registry import TRANSFORMS
from mmdet.datasets.pipelines import RandomFlip
from mmdet3d.structures import (CameraInstance3DBoxes, DepthInstance3DBoxes,
LiDARInstance3DBoxes)
from mmdet3d.structures.ops import box_np_ops
from mmdet3d.structures.points import BasePoints
from mmdet.datasets.transforms import RandomFlip
from .data_augment_utils import noise_per_object_v3_
......
mmdet3d/datasets/utils.py
View file @ c2fe651f
......@@ -5,16 +5,15 @@ from mmcv.transforms import LoadImageFromFile
from pyquaternion import Quaternion
# yapf: disable
from mmdet3d.datasets.pipelines import (LoadAnnotations3D,
LoadImageFromFileMono3D,
LoadMultiViewImageFromFiles,
LoadPointsFromFile,
LoadPointsFromMultiSweeps,
MultiScaleFlipAug3D, Pack3DDetInputs,
PointSegClassMapping)
from mmdet3d.datasets.transforms import (LoadAnnotations3D,
LoadImageFromFileMono3D,
LoadMultiViewImageFromFiles,
LoadPointsFromFile,
LoadPointsFromMultiSweeps,
MultiScaleFlipAug3D, Pack3DDetInputs,
PointSegClassMapping)
# yapf: enable
from mmdet3d.registry import TRANSFORMS
from mmdet.datasets.pipelines import MultiScaleFlipAug
def is_loading_function(transform):
......@@ -41,12 +40,12 @@ def is_loading_function(transform):
return False
if obj_cls in loading_functions:
return True
if obj_cls in (MultiScaleFlipAug3D, MultiScaleFlipAug):
if obj_cls in (MultiScaleFlipAug3D, ):
return None
elif callable(transform):
if isinstance(transform, loading_functions):
return True
if isinstance(transform, (MultiScaleFlipAug3D, MultiScaleFlipAug)):
if isinstance(transform, (MultiScaleFlipAug3D)):
return None
return False
......@@ -63,7 +62,7 @@ def get_loading_pipeline(pipeline):
keep loading image, points and annotations related configuration.
Examples:
>>> pipelines = [
>>> transforms = [
... dict(type='LoadPointsFromFile',
... coord_type='LIDAR', load_dim=4, use_dim=4),
... dict(type='LoadImageFromFile'),
......@@ -94,7 +93,7 @@ def get_loading_pipeline(pipeline):
... keys=['points', 'img', 'gt_bboxes_3d', 'gt_labels_3d'])
... ]
>>> assert expected_pipelines == \
... get_loading_pipeline(pipelines)
... get_loading_pipeline(transforms)
"""
loading_pipeline = []
for transform in pipeline:
......
mmdet3d/datasets/waymo_dataset.py
View file @ c2fe651f
......@@ -9,7 +9,7 @@ import torch
from mmcv.utils import print_log
from mmdet3d.registry import DATASETS
from ..core.bbox import Box3DMode, points_cam2img
from mmdet3d.structures import Box3DMode, points_cam2img
from .kitti_dataset import KittiDataset
......@@ -188,7 +188,7 @@ class WaymoDataset(KittiDataset):
pklfile_prefix,
submission_prefix)
if 'waymo' in data_format:
from ..core.evaluation.waymo_utils.prediction_kitti_to_waymo import \
from mmdet3d.evaluation.functional.waymo_utils import \
KITTI2Waymo # noqa
waymo_root = osp.join(
self.data_root.split('kitti_format')[0], 'waymo_format')
......@@ -257,7 +257,7 @@ class WaymoDataset(KittiDataset):
pklfile_prefix,
submission_prefix,
data_format='kitti')
from mmdet3d.core.evaluation import kitti_eval
from mmdet3d.evaluation import kitti_eval
gt_annos = [info['annos'] for info in self.data_infos]
if isinstance(result_files, dict):
......
mmdet3d/engine/__init__.py 0 → 100644
View file @ c2fe651f
# Copyright (c) OpenMMLab. All rights reserved.
from .scheduler import BetasSchedulerMixin, CosineAnnealingBetas
__all__ = ['BetasSchedulerMixin', 'CosineAnnealingBetas']
mmdet3d/evaluation/__init__.py 0 → 100644
View file @ c2fe651f
# Copyright (c) OpenMMLab. All rights reserved.
from mmdet3d.evaluation.functional.kitti_utils import (do_eval, eval_class,
kitti_eval,
kitti_eval_coco_style)
from .functional import (aggregate_predictions, average_precision,
eval_det_cls, eval_map_recall, fast_hist, get_acc,
get_acc_cls, get_classwise_aps, get_single_class_aps,
indoor_eval, instance_seg_eval, load_lyft_gts,
load_lyft_predictions, lyft_eval, per_class_iou,
rename_gt, seg_eval)
from .metrics import (IndoorMetric, InstanceSegMetric, KittiMetric, LyftMetric,
NuScenesMetric, SegMetric)
__all__ = [
'kitti_eval_coco_style', 'kitti_eval', 'indoor_eval', 'lyft_eval',
'seg_eval', 'instance_seg_eval', 'average_precision', 'eval_det_cls',
'eval_map_recall', 'indoor_eval', 'aggregate_predictions', 'rename_gt',
'instance_seg_eval', 'load_lyft_gts', 'load_lyft_predictions', 'lyft_eval',
'get_classwise_aps', 'get_single_class_aps', 'fast_hist', 'per_class_iou',
'get_acc', 'get_acc_cls', 'seg_eval', 'KittiMetric', 'NuScenesMetric',
'IndoorMetric', 'LyftMetric', 'SegMetric', 'InstanceSegMetric',
'eval_class', 'do_eval'
]
mmdet3d/evaluation/functional/__init__.py 0 → 100644
View file @ c2fe651f
# Copyright (c) OpenMMLab. All rights reserved.
from .indoor_eval import (average_precision, eval_det_cls, eval_map_recall,
indoor_eval)
from .instance_seg_eval import (aggregate_predictions, instance_seg_eval,
rename_gt)
from .kitti_utils import do_eval, kitti_eval, kitti_eval_coco_style
from .lyft_eval import (get_classwise_aps, get_single_class_aps, load_lyft_gts,
load_lyft_predictions, lyft_eval)
from .scannet_utils import evaluate_matches, scannet_eval
from .seg_eval import fast_hist, get_acc, get_acc_cls, per_class_iou, seg_eval
__all__ = [
'average_precision', 'eval_det_cls', 'eval_map_recall', 'indoor_eval',
'aggregate_predictions', 'rename_gt', 'instance_seg_eval', 'load_lyft_gts',
'load_lyft_predictions', 'lyft_eval', 'get_classwise_aps',
'get_single_class_aps', 'fast_hist', 'per_class_iou', 'get_acc',
'get_acc_cls', 'seg_eval', 'kitti_eval', 'kitti_eval_coco_style',
'scannet_eval', 'evaluate_matches', 'do_eval'
]
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment