Skip to content

GitLab

"torchvision/git@developer.sourcefind.cn:OpenDAS/vision.git" did not exist on "36c85c79a1e42f2129434d6d7866dafff1872bd0"
Commit c9b69f5a authored by ZwwWayne's avatar ZwwWayne Committed by ChaimZhu
Browse files

Clean unit tests

parent a34823dc
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 2522 deletions
tests/test_core/test_data_struct/test_det_data_sample.py → tests/test_core/test_data_structure/test_det_data_sample.py
View file @ c9b69f5a
...@@ -3,9 +3,7 @@ from unittest import TestCase ...@@ -3,9 +3,7 @@ from unittest import TestCase
import numpy as np import numpy as np
import pytest import pytest
import torch import torch
# TODO: will use real PixelData once it is added in mmengine from mmengine.data import InstanceData, PixelData
from mmengine.data import BaseDataElement as PixelData
from mmengine.data import InstanceData
from mmdet3d.core import Det3DDataSample from mmdet3d.core import Det3DDataSample
......
tests/test_data/test_datasets/test_dataset_wrappers.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
import torch
from mmdet3d.datasets.builder import build_dataset
def test_getitem():
np.random.seed(1)
torch.manual_seed(1)
point_cloud_range = [-50, -50, -5, 50, 50, 3]
file_client_args = dict(backend='disk')
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=9,
use_dim=[0, 1, 2, 3, 4],
file_client_args=file_client_args,
pad_empty_sweeps=True,
remove_close=True,
test_mode=True),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
# dict(type='ObjectSample', db_sampler=db_sampler),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.3925, 0.3925],
scale_ratio_range=[0.95, 1.05],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectNameFilter', classes=class_names),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
input_modality = dict(
use_lidar=True,
use_camera=False,
use_radar=False,
use_map=False,
use_external=False)
dataset_cfg = dict(
type='CBGSDataset',
dataset=dict(
type='NuScenesDataset',
data_root='tests/data/nuscenes',
ann_file='tests/data/nuscenes/nus_info.pkl',
pipeline=pipeline,
classes=class_names,
modality=input_modality,
test_mode=False,
use_valid_flag=True,
# we use box_type_3d='LiDAR' in kitti and nuscenes dataset
# and box_type_3d='Depth' in sunrgbd and scannet dataset.
box_type_3d='LiDAR'))
nus_dataset = build_dataset(dataset_cfg)
assert len(nus_dataset) == 20
data = nus_dataset[0]
assert data['img_metas'].data['flip'] is True
assert data['img_metas'].data['pcd_horizontal_flip'] is True
assert data['points']._data.shape == (537, 5)
data = nus_dataset[2]
assert data['img_metas'].data['flip'] is False
assert data['img_metas'].data['pcd_horizontal_flip'] is False
assert data['points']._data.shape == (901, 5)
tests/test_data/test_datasets/test_kitti_dataset.py deleted 100644 → 0
View file @ a34823dc
This diff is collapsed.
tests/test_data/test_datasets/test_kitti_mono_dataset.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import mmcv
import numpy as np
import pytest
import torch
from mmdet3d.datasets import KittiMonoDataset
def test_getitem():
np.random.seed(0)
class_names = ['Pedestrian', 'Cyclist', 'Car']
img_norm_cfg = dict(
mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='LoadAnnotations3D',
with_bbox=True,
with_label=True,
with_attr_label=False,
with_bbox_3d=True,
with_label_3d=True,
with_bbox_depth=True),
dict(type='Resize', img_scale=(1242, 375), keep_ratio=True),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=1.0),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'gt_bboxes_3d',
'gt_labels_3d', 'centers2d', 'depths'
]),
]
kitti_dataset = KittiMonoDataset(
ann_file='tests/data/kitti/kitti_infos_mono3d.coco.json',
info_file='tests/data/kitti/kitti_infos_mono3d.pkl',
pipeline=pipeline,
data_root='tests/data/kitti/',
img_prefix='tests/data/kitti/',
test_mode=False)
data = kitti_dataset[0]
img_metas = data['img_metas']._data
filename = img_metas['filename']
img_shape = img_metas['img_shape']
pad_shape = img_metas['pad_shape']
flip = img_metas['flip']
bboxes = data['gt_bboxes']._data
labels3d = data['gt_labels_3d']._data
labels = data['gt_labels']._data
centers2d = data['centers2d']._data
depths = data['depths']._data
expected_filename = 'tests/data/kitti/training/image_2/000007.png'
expected_img_shape = (375, 1242, 3)
expected_pad_shape = (384, 1248, 3)
expected_flip = True
expected_bboxes = torch.tensor([[625.3445, 175.0120, 676.5177, 224.9605],
[729.5906, 179.8571, 760.1503, 202.5390],
[676.7557, 175.7334, 699.7753, 193.9447],
[886.5021, 176.1380, 911.1581, 213.8148]])
expected_labels = torch.tensor([2, 2, 2, 1])
expected_centers2d = torch.tensor([[650.6185, 198.3731],
[744.2711, 190.7532],
[687.8787, 184.5331],
[898.4750, 194.4337]])
expected_depths = torch.tensor([25.0127, 47.5527, 60.5227, 34.0927])
assert filename == expected_filename
assert img_shape == expected_img_shape
assert pad_shape == expected_pad_shape
assert flip == expected_flip
assert torch.allclose(bboxes, expected_bboxes, 1e-5)
assert torch.all(labels == expected_labels)
assert torch.all(labels3d == expected_labels)
assert torch.allclose(centers2d, expected_centers2d, 1e-5)
assert torch.allclose(depths, expected_depths, 1e-5)
def test_format_results():
root_path = 'tests/data/kitti/'
info_file = 'tests/data/kitti/kitti_infos_mono3d.pkl'
ann_file = 'tests/data/kitti/kitti_infos_mono3d.coco.json'
class_names = ['Pedestrian', 'Cyclist', 'Car']
pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='LoadAnnotations3D',
with_bbox=True,
with_label=True,
with_attr_label=False,
with_bbox_3d=True,
with_label_3d=True,
with_bbox_depth=True),
dict(type='Resize', img_scale=(1242, 375), keep_ratio=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'gt_bboxes_3d',
'gt_labels_3d', 'centers2d', 'depths'
]),
]
kitti_dataset = KittiMonoDataset(
ann_file=ann_file,
info_file=info_file,
pipeline=pipeline,
data_root=root_path,
test_mode=True)
# format 3D detection results
results = mmcv.load('tests/data/kitti/mono3d_sample_results.pkl')
result_files, tmp_dir = kitti_dataset.format_results(results)
result_data = result_files['img_bbox']
assert len(result_data) == 1
assert len(result_data[0]['name']) == 4
det = result_data[0]
expected_bbox = torch.tensor([[565.4989, 175.02547, 616.70184, 225.00565],
[481.85907, 179.8642, 512.43414, 202.5624],
[542.23157, 175.73912, 565.26263, 193.96303],
[330.8572, 176.1482, 355.53937, 213.8469]])
expected_dims = torch.tensor([[3.201, 1.6110001, 1.661],
[3.701, 1.401, 1.511],
[4.051, 1.4610001, 1.661],
[1.9510001, 1.7210001, 0.501]])
expected_rotation = torch.tensor([-1.59, 1.55, 1.56, 1.54])
expected_detname = ['Car', 'Car', 'Car', 'Cyclist']
assert torch.allclose(torch.from_numpy(det['bbox']), expected_bbox, 1e-5)
assert torch.allclose(
torch.from_numpy(det['dimensions']), expected_dims, 1e-5)
assert torch.allclose(
torch.from_numpy(det['rotation_y']), expected_rotation, 1e-5)
assert det['name'].tolist() == expected_detname
# format 2D detection results
results = mmcv.load('tests/data/kitti/mono3d_sample_results2d.pkl')
result_files, tmp_dir = kitti_dataset.format_results(results)
result_data = result_files['img_bbox2d']
assert len(result_data) == 1
assert len(result_data[0]['name']) == 4
det = result_data[0]
expected_bbox = torch.tensor(
[[330.84191493, 176.13804312, 355.49885373, 213.81578769],
[565.48227204, 175.01202566, 616.65650883, 224.96147091],
[481.84967085, 179.85710612, 512.41043776, 202.54001526],
[542.22471517, 175.73341152, 565.24534908, 193.94568878]])
expected_dims = torch.tensor([[0., 0., 0.], [0., 0., 0.], [0., 0., 0.],
[0., 0., 0.]])
expected_rotation = torch.tensor([0., 0., 0., 0.])
expected_detname = ['Cyclist', 'Car', 'Car', 'Car']
assert torch.allclose(
torch.from_numpy(det['bbox']).float(), expected_bbox, 1e-5)
assert torch.allclose(
torch.from_numpy(det['dimensions']).float(), expected_dims, 1e-5)
assert torch.allclose(
torch.from_numpy(det['rotation_y']).float(), expected_rotation, 1e-5)
assert det['name'].tolist() == expected_detname
def test_evaluate():
if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda')
root_path = 'tests/data/kitti/'
info_file = 'tests/data/kitti/kitti_infos_mono3d.pkl'
ann_file = 'tests/data/kitti/kitti_infos_mono3d.coco.json'
class_names = ['Pedestrian', 'Cyclist', 'Car']
pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='LoadAnnotations3D',
with_bbox=True,
with_label=True,
with_attr_label=False,
with_bbox_3d=True,
with_label_3d=True,
with_bbox_depth=True),
dict(type='Resize', img_scale=(1242, 375), keep_ratio=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'gt_bboxes_3d',
'gt_labels_3d', 'centers2d', 'depths'
]),
]
kitti_dataset = KittiMonoDataset(
ann_file=ann_file,
info_file=info_file,
pipeline=pipeline,
data_root=root_path,
test_mode=True)
# format 3D detection results
results = mmcv.load('tests/data/kitti/mono3d_sample_results.pkl')
results2d = mmcv.load('tests/data/kitti/mono3d_sample_results2d.pkl')
results[0]['img_bbox2d'] = results2d[0]['img_bbox2d']
metric = ['mAP']
ap_dict = kitti_dataset.evaluate(results, metric)
assert np.isclose(ap_dict['img_bbox/KITTI/Overall_3D_AP11_easy'], 3.0303)
assert np.isclose(ap_dict['img_bbox/KITTI/Overall_3D_AP11_moderate'],
6.0606)
assert np.isclose(ap_dict['img_bbox/KITTI/Overall_3D_AP11_hard'], 6.0606)
assert np.isclose(ap_dict['img_bbox2d/KITTI/Overall_2D_AP11_easy'], 3.0303)
assert np.isclose(ap_dict['img_bbox2d/KITTI/Overall_2D_AP11_moderate'],
6.0606)
assert np.isclose(ap_dict['img_bbox2d/KITTI/Overall_2D_AP11_hard'], 6.0606)
tests/test_data/test_datasets/test_lyft_dataset.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import tempfile
import mmcv
import numpy as np
import torch
from mmdet3d.core import limit_period
from mmdet3d.datasets import LyftDataset
def test_getitem():
np.random.seed(0)
torch.manual_seed(0)
root_path = './tests/data/lyft'
# in coordinate system refactor, this test file is modified
ann_file = './tests/data/lyft/lyft_infos.pkl'
class_names = ('car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle',
'motorcycle', 'bicycle', 'pedestrian', 'animal')
point_cloud_range = [-80, -80, -10, 80, 80, 10]
pipelines = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=2,
file_client_args=dict(backend='disk')),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.523599, 0.523599],
scale_ratio_range=[0.85, 1.15],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(type='PointsRangeFilter', point_cloud_range=point_cloud_range),
dict(type='ObjectRangeFilter', point_cloud_range=point_cloud_range),
dict(type='PointShuffle'),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
lyft_dataset = LyftDataset(ann_file, pipelines, root_path)
data = lyft_dataset[0]
points = data['points']._data
gt_bboxes_3d = data['gt_bboxes_3d']._data
gt_labels_3d = data['gt_labels_3d']._data
pts_filename = data['img_metas']._data['pts_filename']
pcd_horizontal_flip = data['img_metas']._data['pcd_horizontal_flip']
pcd_scale_factor = data['img_metas']._data['pcd_scale_factor']
pcd_rotation = data['img_metas']._data['pcd_rotation']
pcd_rotation_angle = data['img_metas']._data['pcd_rotation_angle']
sample_idx = data['img_metas']._data['sample_idx']
# coord sys refactor
pcd_rotation_expected = np.array([[0.99869376, 0.05109515, 0.],
[-0.05109515, 0.99869376, 0.],
[0., 0., 1.]])
assert pts_filename == \
'tests/data/lyft/lidar/host-a017_lidar1_1236118886901125926.bin'
assert pcd_horizontal_flip is True
assert abs(pcd_scale_factor - 1.0645568099117257) < 1e-5
assert np.allclose(pcd_rotation, pcd_rotation_expected, 1e-3)
assert sample_idx == \
'b98a05255ba2632e957884758cb31f0e6fcc8d3cd6ee76b6d0ba55b72f08fc54'
expected_points = torch.tensor([[61.4785, -3.7393, 6.7699, 0.4001],
[47.7904, -3.9887, 6.0926, 0.0000],
[52.5683, -4.2178, 6.7179, 0.0000],
[52.4867, -4.0315, 6.7057, 0.0000],
[59.8372, -1.7366, 6.5864, 0.4001],
[53.0842, -3.7064, 6.7811, 0.0000],
[60.5549, -3.4978, 6.6578, 0.4001],
[59.1695, -1.2910, 7.0296, 0.2000],
[53.0702, -3.8868, 6.7807, 0.0000],
[47.9579, -4.1648, 5.6219, 0.2000],
[59.8226, -1.5522, 6.5867, 0.4001],
[61.2858, -4.2254, 7.3089, 0.2000],
[49.9896, -4.5202, 5.8823, 0.2000],
[61.4597, -4.6402, 7.3340, 0.2000],
[59.8244, -1.3499, 6.5895, 0.4001]])
expected_gt_bboxes_3d = torch.tensor(
[[63.2257, 17.5206, -0.6307, 2.0109, 5.1652, 1.9471, -1.5868],
[-25.3804, 27.4598, -2.3297, 2.7412, 8.4792, 3.4343, -1.5939],
[-15.2098, -7.0109, -2.2566, 0.7931, 0.8410, 1.7916, 1.5090]])
expected_gt_labels = np.array([0, 4, 7])
original_classes = lyft_dataset.CLASSES
# manually go through pipeline
expected_points[:, :3] = (
(expected_points[:, :3] * torch.tensor([1, -1, 1]))
@ pcd_rotation_expected @ pcd_rotation_expected) * torch.tensor(
[1, -1, 1])
expected_gt_bboxes_3d[:, :3] = (
(expected_gt_bboxes_3d[:, :3] * torch.tensor([1, -1, 1]))
@ pcd_rotation_expected @ pcd_rotation_expected) * torch.tensor(
[1, -1, 1])
expected_gt_bboxes_3d[:, 3:6] = expected_gt_bboxes_3d[:, [4, 3, 5]]
expected_gt_bboxes_3d[:, 6:] = -expected_gt_bboxes_3d[:, 6:] \
- np.pi / 2 - pcd_rotation_angle * 2
expected_gt_bboxes_3d[:, 6:] = limit_period(
expected_gt_bboxes_3d[:, 6:], period=np.pi * 2)
assert torch.allclose(points, expected_points, 1e-2)
assert torch.allclose(gt_bboxes_3d.tensor, expected_gt_bboxes_3d, 1e-3)
assert np.all(gt_labels_3d.numpy() == expected_gt_labels)
assert original_classes == class_names
lyft_dataset = LyftDataset(
ann_file, None, root_path, classes=['car', 'pedestrian'])
assert lyft_dataset.CLASSES != original_classes
assert lyft_dataset.CLASSES == ['car', 'pedestrian']
lyft_dataset = LyftDataset(
ann_file, None, root_path, classes=('car', 'pedestrian'))
assert lyft_dataset.CLASSES != original_classes
assert lyft_dataset.CLASSES == ('car', 'pedestrian')
import tempfile
with tempfile.TemporaryDirectory() as tmpdir:
path = tmpdir + 'classes.txt'
with open(path, 'w') as f:
f.write('car\npedestrian\n')
lyft_dataset = LyftDataset(ann_file, None, root_path, classes=path)
assert lyft_dataset.CLASSES != original_classes
assert lyft_dataset.CLASSES == ['car', 'pedestrian']
def test_evaluate():
root_path = './tests/data/lyft'
# in coordinate system refactor, this test file is modified
ann_file = './tests/data/lyft/lyft_infos_val.pkl'
lyft_dataset = LyftDataset(ann_file, None, root_path)
# in coordinate system refactor, this test file is modified
results = mmcv.load('./tests/data/lyft/sample_results.pkl')
ap_dict = lyft_dataset.evaluate(results, 'bbox')
car_precision = ap_dict['pts_bbox_Lyft/car_AP']
assert car_precision == 0.6
def test_show():
from os import path as osp
import mmcv
from mmdet3d.core.bbox import LiDARInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/lyft'
ann_file = './tests/data/lyft/lyft_infos.pkl'
class_names = ('car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle',
'motorcycle', 'bicycle', 'pedestrian', 'animal')
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
kitti_dataset = LyftDataset(ann_file, None, root_path)
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[46.1218, -4.6496, -0.9275, 1.4442, 0.5316, 1.7450, -2.7457],
[33.3189, 0.1981, 0.3136, 1.2301, 0.5656, 1.7985, 3.1401],
[46.1366, -4.6404, -0.9510, 1.6501, 0.5162, 1.7540, -2.9486],
[33.2646, 0.2297, 0.3446, 1.3365, 0.5746, 1.7947, -3.1138],
[58.9079, 16.6272, -1.5829, 3.9313, 1.5656, 1.4899, -3.1213]]))
scores_3d = torch.tensor([0.1815, 0.1663, 0.5792, 0.2194, 0.2780])
labels_3d = torch.tensor([0, 0, 1, 1, 2])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [dict(pts_bbox=result)]
kitti_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
file_name = 'host-a017_lidar1_1236118886901125926'
pts_file_path = osp.join(temp_dir, file_name, f'{file_name}_points.obj')
gt_file_path = osp.join(temp_dir, file_name, f'{file_name}_gt.obj')
pred_file_path = osp.join(temp_dir, file_name, f'{file_name}_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
tests/test_data/test_datasets/test_nuscene_dataset.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import tempfile
import numpy as np
import torch
from mmdet3d.datasets import NuScenesDataset
def test_getitem():
np.random.seed(0)
point_cloud_range = [-50, -50, -5, 50, 50, 3]
file_client_args = dict(backend='disk')
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=file_client_args),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=2,
file_client_args=file_client_args),
dict(
type='MultiScaleFlipAug3D',
img_scale=(1333, 800),
pts_scale_ratio=1,
flip=False,
transforms=[
dict(
type='GlobalRotScaleTrans',
rot_range=[0, 0],
scale_ratio_range=[1., 1.],
translation_std=[0, 0, 0]),
dict(type='RandomFlip3D'),
dict(
type='PointsRangeFilter',
point_cloud_range=point_cloud_range),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
])
]
nus_dataset = NuScenesDataset(
'tests/data/nuscenes/nus_info.pkl',
pipeline,
'tests/data/nuscenes',
test_mode=True)
data = nus_dataset[0]
assert data['img_metas'][0].data['flip'] is False
assert data['img_metas'][0].data['pcd_horizontal_flip'] is False
assert data['points'][0]._data.shape == (100, 4)
data = nus_dataset[1]
assert data['img_metas'][0].data['flip'] is False
assert data['img_metas'][0].data['pcd_horizontal_flip'] is False
assert data['points'][0]._data.shape == (597, 4)
def test_show():
from os import path as osp
import mmcv
from mmdet3d.core.bbox import LiDARInstance3DBoxes
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=5,
use_dim=5,
file_client_args=dict(backend='disk')),
dict(
type='LoadPointsFromMultiSweeps',
sweeps_num=10,
file_client_args=dict(backend='disk')),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['points'])
]
nus_dataset = NuScenesDataset('tests/data/nuscenes/nus_info.pkl', None,
'tests/data/nuscenes')
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[46.1218, -4.6496, -0.9275, 0.5316, 1.4442, 1.7450, 1.1749],
[33.3189, 0.1981, 0.3136, 0.5656, 1.2301, 1.7985, 1.5723],
[46.1366, -4.6404, -0.9510, 0.5162, 1.6501, 1.7540, 1.3778],
[33.2646, 0.2297, 0.3446, 0.5746, 1.3365, 1.7947, 1.5430],
[58.9079, 16.6272, -1.5829, 1.5656, 3.9313, 1.4899, 1.5505]]))
scores_3d = torch.tensor([0.1815, 0.1663, 0.5792, 0.2194, 0.2780])
labels_3d = torch.tensor([0, 0, 1, 1, 2])
result = dict(boxes_3d=boxes_3d, scores_3d=scores_3d, labels_3d=labels_3d)
results = [dict(pts_bbox=result)]
nus_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
file_name = 'n015-2018-08-02-17-16-37+0800__LIDAR_TOP__1533201470948018'
pts_file_path = osp.join(temp_dir, file_name, f'{file_name}_points.obj')
gt_file_path = osp.join(temp_dir, file_name, f'{file_name}_gt.obj')
pred_file_path = osp.join(temp_dir, file_name, f'{file_name}_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
tests/test_data/test_datasets/test_nuscenes_mono_dataset.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import tempfile
from os import path as osp
import mmcv
import numpy as np
import pytest
import torch
from mmdet3d.datasets import NuScenesMonoDataset
def test_getitem():
np.random.seed(0)
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
img_norm_cfg = dict(
mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='LoadAnnotations3D',
with_bbox=True,
with_label=True,
with_attr_label=True,
with_bbox_3d=True,
with_label_3d=True,
with_bbox_depth=True),
dict(type='Resize', img_scale=(1600, 900), keep_ratio=True),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=1.0),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'attr_labels', 'gt_bboxes_3d',
'gt_labels_3d', 'centers2d', 'depths'
]),
]
nus_dataset = NuScenesMonoDataset(
ann_file='tests/data/nuscenes/nus_infos_mono3d.coco.json',
pipeline=pipeline,
data_root='tests/data/nuscenes/',
img_prefix='tests/data/nuscenes/',
test_mode=False)
data = nus_dataset[0]
img_metas = data['img_metas']._data
filename = img_metas['filename']
img_shape = img_metas['img_shape']
pad_shape = img_metas['pad_shape']
flip = img_metas['flip']
bboxes = data['gt_bboxes']._data
attrs = data['attr_labels']._data
labels3d = data['gt_labels_3d']._data
labels = data['gt_labels']._data
centers2d = data['centers2d']._data
depths = data['depths']._data
expected_filename = 'tests/data/nuscenes/samples/CAM_BACK_LEFT/' + \
'n015-2018-07-18-11-07-57+0800__CAM_BACK_LEFT__1531883530447423.jpg'
expected_img_shape = (900, 1600, 3)
expected_pad_shape = (928, 1600, 3)
expected_flip = True
expected_bboxes = torch.tensor([[485.4207, 513.7568, 515.4637, 576.1393],
[748.9482, 512.0452, 776.4941, 571.6310],
[432.1318, 427.8805, 508.4290, 578.1468],
[367.3779, 427.7682, 439.4244, 578.8904],
[592.8713, 515.0040, 623.4984, 575.0945]])
expected_attr_labels = torch.tensor([8, 8, 4, 4, 8])
expected_labels = torch.tensor([8, 8, 7, 7, 8])
expected_centers2d = torch.tensor([[500.6090, 544.6358],
[762.8789, 541.5280],
[471.1633, 502.2295],
[404.1957, 502.5908],
[608.3627, 544.7317]])
expected_depths = torch.tensor(
[15.3193, 15.6073, 14.7567, 14.8803, 15.4923])
assert filename == expected_filename
assert img_shape == expected_img_shape
assert pad_shape == expected_pad_shape
assert flip == expected_flip
assert torch.allclose(bboxes, expected_bboxes, 1e-5)
assert torch.all(attrs == expected_attr_labels)
assert torch.all(labels == expected_labels)
assert torch.all(labels3d == expected_labels)
assert torch.allclose(centers2d, expected_centers2d, 1e-5)
assert torch.allclose(depths, expected_depths, 1e-5)
def test_format_results():
if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda')
root_path = 'tests/data/nuscenes/'
ann_file = 'tests/data/nuscenes/nus_infos_mono3d.coco.json'
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='LoadAnnotations3D',
with_bbox=True,
with_label=True,
with_attr_label=True,
with_bbox_3d=True,
with_label_3d=True,
with_bbox_depth=True),
dict(type='Resize', img_scale=(1600, 900), keep_ratio=True),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'img', 'gt_bboxes', 'gt_labels', 'attr_labels', 'gt_bboxes_3d',
'gt_labels_3d', 'centers2d', 'depths'
]),
]
nus_dataset = NuScenesMonoDataset(
ann_file=ann_file,
pipeline=pipeline,
data_root=root_path,
test_mode=True)
results = mmcv.load('tests/data/nuscenes/mono3d_sample_results.pkl')
result_files, tmp_dir = nus_dataset.format_results(results)
result_data = mmcv.load(result_files['img_bbox'])
assert len(result_data['results'].keys()) == 1
assert len(result_data['results']['e93e98b63d3b40209056d129dc53ceee']) == 8
det = result_data['results']['e93e98b63d3b40209056d129dc53ceee'][0]
expected_token = 'e93e98b63d3b40209056d129dc53ceee'
expected_trans = torch.tensor(
[1018.753821915645, 605.190386124652, 0.7266818822266328])
expected_size = torch.tensor([1.440000057220459, 1.6380000114440918, 4.25])
expected_rotation = torch.tensor([-0.5717, -0.0014, 0.0170, -0.8203])
expected_detname = 'car'
expected_attr = 'vehicle.moving'
assert det['sample_token'] == expected_token
assert torch.allclose(
torch.tensor(det['translation']), expected_trans, 1e-5)
assert torch.allclose(torch.tensor(det['size']), expected_size, 1e-5)
assert torch.allclose(
torch.tensor(det['rotation']), expected_rotation, atol=1e-4)
assert det['detection_name'] == expected_detname
assert det['attribute_name'] == expected_attr
def test_show():
root_path = 'tests/data/nuscenes/'
ann_file = 'tests/data/nuscenes/nus_infos_mono3d.coco.json'
class_names = [
'car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'
]
eval_pipeline = [
dict(type='LoadImageFromFileMono3D'),
dict(
type='DefaultFormatBundle3D',
class_names=class_names,
with_label=False),
dict(type='Collect3D', keys=['img'])
]
nus_dataset = NuScenesMonoDataset(
data_root=root_path,
ann_file=ann_file,
img_prefix='tests/data/nuscenes/',
test_mode=True,
pipeline=eval_pipeline)
results = mmcv.load('tests/data/nuscenes/mono3d_sample_results.pkl')
results = [results[0]]
# show with eval_pipeline
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
nus_dataset.show(results, temp_dir, show=False)
file_name = 'n015-2018-07-18-11-07-57+0800__' \
'CAM_BACK_LEFT__1531883530447423'
img_file_path = osp.join(temp_dir, file_name, f'{file_name}_img.png')
gt_file_path = osp.join(temp_dir, file_name, f'{file_name}_gt.png')
pred_file_path = osp.join(temp_dir, file_name, f'{file_name}_pred.png')
mmcv.check_file_exist(img_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
tests/test_data/test_datasets/test_s3dis_dataset.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
import pytest
import torch
from mmdet3d.datasets import S3DISDataset, S3DISSegDataset
def test_getitem():
np.random.seed(0)
root_path = './tests/data/s3dis/'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
class_names = ('table', 'chair', 'sofa', 'bookcase', 'board')
pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(type='LoadAnnotations3D', with_bbox_3d=True, with_label_3d=True),
dict(type='PointSample', num_points=40000),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
s3dis_dataset = S3DISDataset(
data_root=root_path, ann_file=ann_file, pipeline=pipeline)
data = s3dis_dataset[0]
points = data['points']._data
gt_bboxes_3d = data['gt_bboxes_3d']._data
gt_labels_3d = data['gt_labels_3d']._data
expected_gt_bboxes_3d = torch.tensor(
[[2.3080, 2.4175, 0.2010, 0.8820, 0.8690, 0.6970, 0.0000],
[2.4730, 0.7090, 0.2010, 0.9080, 0.9620, 0.7030, 0.0000],
[5.3235, 0.4910, 0.0740, 0.8410, 0.9020, 0.8790, 0.0000]])
expected_gt_labels = np.array([1, 1, 3, 1, 2, 0, 0, 0, 3])
assert tuple(points.shape) == (40000, 6)
assert torch.allclose(gt_bboxes_3d[:3].tensor, expected_gt_bboxes_3d, 1e-2)
assert np.all(gt_labels_3d.numpy() == expected_gt_labels)
def test_evaluate():
if not torch.cuda.is_available():
pytest.skip()
from mmdet3d.core.bbox.structures import DepthInstance3DBoxes
root_path = './tests/data/s3dis'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
s3dis_dataset = S3DISDataset(root_path, ann_file)
results = []
pred_boxes = dict()
pred_boxes['boxes_3d'] = DepthInstance3DBoxes(
torch.tensor([[2.3080, 2.4175, 0.2010, 0.8820, 0.8690, 0.6970, 0.0000],
[2.4730, 0.7090, 0.2010, 0.9080, 0.9620, 0.7030, 0.0000],
[5.3235, 0.4910, 0.0740, 0.8410, 0.9020, 0.8790,
0.0000]]))
pred_boxes['labels_3d'] = torch.tensor([1, 1, 3])
pred_boxes['scores_3d'] = torch.tensor([0.5, 1.0, 1.0])
results.append(pred_boxes)
ret_dict = s3dis_dataset.evaluate(results)
assert abs(ret_dict['chair_AP_0.25'] - 0.666) < 0.01
assert abs(ret_dict['chair_AP_0.50'] - 0.666) < 0.01
assert abs(ret_dict['bookcase_AP_0.25'] - 0.5) < 0.01
assert abs(ret_dict['bookcase_AP_0.50'] - 0.5) < 0.01
def test_seg_getitem():
np.random.seed(0)
root_path = './tests/data/s3dis/'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
class_names = ('ceiling', 'floor', 'wall', 'beam', 'column', 'window',
'door', 'table', 'chair', 'sofa', 'bookcase', 'board',
'clutter')
palette = [[0, 255, 0], [0, 0, 255], [0, 255, 255], [255, 255, 0],
[255, 0, 255], [100, 100, 255], [200, 200, 100],
[170, 120, 200], [255, 0, 0], [200, 100, 100], [10, 200, 100],
[200, 200, 200], [50, 50, 50]]
scene_idxs = [0 for _ in range(20)]
pipelines = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
use_color=True,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(
type='LoadAnnotations3D',
with_bbox_3d=False,
with_label_3d=False,
with_mask_3d=False,
with_seg_3d=True),
dict(
type='PointSegClassMapping',
valid_cat_ids=tuple(range(len(class_names))),
max_cat_id=13),
dict(
type='IndoorPatchPointSample',
num_points=5,
block_size=1.0,
ignore_index=len(class_names),
use_normalized_coord=True,
enlarge_size=0.2,
min_unique_num=None),
dict(type='NormalizePointsColor', color_mean=None),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=['points', 'pts_semantic_mask'],
meta_keys=['file_name', 'sample_idx'])
]
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=ann_file,
pipeline=pipelines,
classes=None,
palette=None,
modality=None,
test_mode=False,
ignore_index=None,
scene_idxs=scene_idxs)
data = s3dis_dataset[0]
points = data['points']._data
pts_semantic_mask = data['pts_semantic_mask']._data
file_name = data['img_metas']._data['file_name']
sample_idx = data['img_metas']._data['sample_idx']
assert file_name == './tests/data/s3dis/points/Area_1_office_2.bin'
assert sample_idx == 'Area_1_office_2'
expected_points = torch.tensor([[
0.0000, 0.0000, 3.1720, 0.4706, 0.4431, 0.3725, 0.4624, 0.7502, 0.9543
], [
0.2880, -0.5900, 0.0650, 0.3451, 0.3373, 0.3490, 0.5119, 0.5518, 0.0196
], [
0.1570, 0.6000, 3.1700, 0.4941, 0.4667, 0.3569, 0.4893, 0.9519, 0.9537
], [
-0.1320, 0.3950, 0.2720, 0.3216, 0.2863, 0.2275, 0.4397, 0.8830, 0.0818
],
[
-0.4860, -0.0640, 3.1710, 0.3843,
0.3725, 0.3059, 0.3789, 0.7286, 0.9540
]])
expected_pts_semantic_mask = np.array([0, 1, 0, 8, 0])
original_classes = s3dis_dataset.CLASSES
original_palette = s3dis_dataset.PALETTE
assert s3dis_dataset.CLASSES == class_names
assert s3dis_dataset.ignore_index == 13
assert torch.allclose(points, expected_points, 1e-2)
assert np.all(pts_semantic_mask.numpy() == expected_pts_semantic_mask)
assert original_classes == class_names
assert original_palette == palette
assert s3dis_dataset.scene_idxs.dtype == np.int32
assert np.all(s3dis_dataset.scene_idxs == np.array(scene_idxs))
# test dataset with selected classes
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=ann_file,
pipeline=None,
classes=['beam', 'window'],
scene_idxs=scene_idxs)
label_map = {i: 13 for i in range(14)}
label_map.update({3: 0, 5: 1})
assert s3dis_dataset.CLASSES != original_classes
assert s3dis_dataset.CLASSES == ['beam', 'window']
assert s3dis_dataset.PALETTE == [palette[3], palette[5]]
assert s3dis_dataset.VALID_CLASS_IDS == [3, 5]
assert s3dis_dataset.label_map == label_map
assert s3dis_dataset.label2cat == {0: 'beam', 1: 'window'}
# test load classes from file
import tempfile
with tempfile.TemporaryDirectory() as tmpdir:
path = tmpdir + 'classes.txt'
with open(path, 'w') as f:
f.write('beam\nwindow\n')
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=ann_file,
pipeline=None,
classes=path,
scene_idxs=scene_idxs)
assert s3dis_dataset.CLASSES != original_classes
assert s3dis_dataset.CLASSES == ['beam', 'window']
assert s3dis_dataset.PALETTE == [palette[3], palette[5]]
assert s3dis_dataset.VALID_CLASS_IDS == [3, 5]
assert s3dis_dataset.label_map == label_map
assert s3dis_dataset.label2cat == {0: 'beam', 1: 'window'}
# test scene_idxs in dataset
# we should input scene_idxs in train mode
with pytest.raises(NotImplementedError):
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=ann_file,
pipeline=None,
scene_idxs=None)
# test mode
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=ann_file,
pipeline=None,
test_mode=True,
scene_idxs=scene_idxs)
assert np.all(s3dis_dataset.scene_idxs == np.array([0]))
def test_seg_evaluate():
if not torch.cuda.is_available():
pytest.skip()
root_path = './tests/data/s3dis'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
s3dis_dataset = S3DISSegDataset(
data_root=root_path, ann_files=ann_file, test_mode=True)
results = []
pred_sem_mask = dict(
semantic_mask=torch.tensor([
2, 3, 1, 2, 2, 6, 1, 0, 1, 1, 9, 12, 3, 0, 2, 0, 2, 0, 8, 3, 1, 2,
0, 2, 1, 7, 2, 10, 2, 0, 0, 0, 2, 3, 2, 2, 2, 2, 2, 3, 0, 0, 4, 6,
7, 2, 1, 2, 0, 1, 7, 0, 2, 2, 2, 0, 2, 2, 1, 12, 0, 2, 2, 2, 2, 7,
2, 2, 0, 2, 6, 2, 12, 6, 3, 12, 2, 1, 6, 1, 2, 6, 8, 2, 10, 1, 11,
0, 6, 9, 4, 3, 0, 0, 12, 1, 1, 5, 3, 2
]).long())
results.append(pred_sem_mask)
ret_dict = s3dis_dataset.evaluate(results)
assert abs(ret_dict['miou'] - 0.7625) < 0.01
assert abs(ret_dict['acc'] - 0.9) < 0.01
assert abs(ret_dict['acc_cls'] - 0.9074) < 0.01
def test_seg_show():
import tempfile
from os import path as osp
import mmcv
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
root_path = './tests/data/s3dis'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
s3dis_dataset = S3DISSegDataset(
data_root=root_path, ann_files=ann_file, scene_idxs=[0])
result = dict(
semantic_mask=torch.tensor([
2, 2, 1, 2, 2, 5, 1, 0, 1, 1, 9, 12, 3, 0, 2, 0, 2, 0, 8, 2, 0, 2,
0, 2, 1, 7, 2, 10, 2, 0, 0, 0, 2, 2, 2, 2, 2, 1, 2, 2, 0, 0, 4, 6,
7, 2, 1, 2, 0, 1, 7, 0, 2, 2, 2, 0, 2, 2, 1, 12, 0, 2, 2, 2, 2, 7,
2, 2, 0, 2, 6, 2, 12, 6, 2, 12, 2, 1, 6, 1, 2, 6, 8, 2, 10, 1, 10,
0, 6, 9, 4, 3, 0, 0, 12, 1, 1, 5, 2, 2
]).long())
results = [result]
s3dis_dataset.show(results, temp_dir, show=False)
pts_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_points.obj')
gt_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_gt.obj')
pred_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
# test show with pipeline
tmp_dir = tempfile.TemporaryDirectory()
temp_dir = tmp_dir.name
class_names = ('ceiling', 'floor', 'wall', 'beam', 'column', 'window',
'door', 'table', 'chair', 'sofa', 'bookcase', 'board',
'clutter')
eval_pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='DEPTH',
shift_height=False,
use_color=True,
load_dim=6,
use_dim=[0, 1, 2, 3, 4, 5]),
dict(
type='LoadAnnotations3D',
with_bbox_3d=False,
with_label_3d=False,
with_mask_3d=False,
with_seg_3d=True),
dict(
type='PointSegClassMapping',
valid_cat_ids=tuple(range(len(class_names))),
max_cat_id=13),
dict(
type='DefaultFormatBundle3D',
with_label=False,
class_names=class_names),
dict(type='Collect3D', keys=['points', 'pts_semantic_mask'])
]
s3dis_dataset.show(results, temp_dir, show=False, pipeline=eval_pipeline)
pts_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_points.obj')
gt_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_gt.obj')
pred_file_path = osp.join(temp_dir, 'Area_1_office_2',
'Area_1_office_2_pred.obj')
mmcv.check_file_exist(pts_file_path)
mmcv.check_file_exist(gt_file_path)
mmcv.check_file_exist(pred_file_path)
tmp_dir.cleanup()
def test_multi_areas():
# S3DIS dataset has 6 areas, we often train on several of them
# need to verify the concat function of S3DISSegDataset
root_path = './tests/data/s3dis'
ann_file = './tests/data/s3dis/s3dis_infos.pkl'
class_names = ('ceiling', 'floor', 'wall', 'beam', 'column', 'window',
'door', 'table', 'chair', 'sofa', 'bookcase', 'board',
'clutter')
palette = [[0, 255, 0], [0, 0, 255], [0, 255, 255], [255, 255, 0],
[255, 0, 255], [100, 100, 255], [200, 200, 100],
[170, 120, 200], [255, 0, 0], [200, 100, 100], [10, 200, 100],
[200, 200, 200], [50, 50, 50]]
scene_idxs = [0 for _ in range(20)]
# repeat
repeat_num = 3
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=[ann_file for _ in range(repeat_num)],
scene_idxs=scene_idxs)
assert s3dis_dataset.CLASSES == class_names
assert s3dis_dataset.PALETTE == palette
assert len(s3dis_dataset.data_infos) == repeat_num
assert np.all(s3dis_dataset.scene_idxs == np.concatenate(
[np.array(scene_idxs) + i for i in range(repeat_num)]))
# different scene_idxs input
s3dis_dataset = S3DISSegDataset(
data_root=root_path,
ann_files=[ann_file for _ in range(repeat_num)],
scene_idxs=[[0, 0, 1, 2, 2], [0, 1, 2, 3, 3, 4], [0, 1, 1, 2, 2, 2]])
assert np.all(s3dis_dataset.scene_idxs == np.array(
[0, 0, 1, 2, 2, 3, 4, 5, 6, 6, 7, 8, 9, 9, 10, 10, 10]))
tests/test_data/test_datasets/test_scannet_dataset.py deleted 100644 → 0
View file @ a34823dc
This diff is collapsed.
tests/test_data/test_datasets/test_semantickitti_dataset.py deleted 100644 → 0
View file @ a34823dc
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
from mmdet3d.datasets import SemanticKITTIDataset
def test_getitem():
np.random.seed(0)
root_path = './tests/data/semantickitti/'
ann_file = './tests/data/semantickitti/semantickitti_infos.pkl'
class_names = ('unlabeled', 'car', 'bicycle', 'motorcycle', 'truck', 'bus',
'person', 'bicyclist', 'motorcyclist', 'road', 'parking',
'sidewalk', 'other-ground', 'building', 'fence',
'vegetation', 'trunck', 'terrian', 'pole', 'traffic-sign')
pipelines = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
shift_height=True,
load_dim=4,
use_dim=[0, 1, 2]),
dict(
type='LoadAnnotations3D',
with_bbox_3d=False,
with_label_3d=False,
with_mask_3d=False,
with_seg_3d=True,
seg_3d_dtype=np.int32),
dict(
type='RandomFlip3D',
sync_2d=False,
flip_ratio_bev_horizontal=1.0,
flip_ratio_bev_vertical=1.0),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.087266, 0.087266],
scale_ratio_range=[1.0, 1.0],
shift_height=True),
dict(type='DefaultFormatBundle3D', class_names=class_names),
dict(
type='Collect3D',
keys=[
'points',
'pts_semantic_mask',
],
meta_keys=['file_name', 'sample_idx', 'pcd_rotation']),
]
semantickitti_dataset = SemanticKITTIDataset(root_path, ann_file,
pipelines)
data = semantickitti_dataset[0]
assert data['points']._data.shape[0] == data[
'pts_semantic_mask']._data.shape[0]
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