Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "f434d1f5d0a7e75f5a289b8350f2fe7b4487148f"
Unverified Commit d7067e44 authored by Wenwei Zhang's avatar Wenwei Zhang Committed by GitHub
Browse files

Bump version to v1.1.0rc2 

Bump to v1.1.0rc2
parents 28fe73d2 fb0e57e5
Show whitespace changes
Inline Side-by-side
Showing with 403 additions and 214 deletions
tests/test_models/test_detectors/test_imvotenet.py
View file @ d7067e44
......@@ -4,8 +4,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestImvoteNet(unittest.TestCase):
......@@ -15,12 +15,12 @@ class TestImvoteNet(unittest.TestCase):
assert hasattr(mmdet3d.models, 'ImVoteNet')
DefaultScope.get_instance('test_imvotenet_img', scope_name='mmdet3d')
_setup_seed(0)
votenet_net_cfg = _get_detector_cfg(
setup_seed(0)
votenet_net_cfg = get_detector_cfg(
'imvotenet/imvotenet_faster-rcnn-r50_fpn_4xb2_sunrgbd-3d.py')
model = MODELS.build(votenet_net_cfg)
packed_inputs = _create_detector_inputs(
packed_inputs = create_detector_inputs(
with_points=False, with_img=True, img_size=128)
if torch.cuda.is_available():
......@@ -49,12 +49,12 @@ class TestImvoteNet(unittest.TestCase):
assert hasattr(mmdet3d.models, 'ImVoteNet')
DefaultScope.get_instance('test_imvotenet', scope_name='mmdet3d')
_setup_seed(0)
votenet_net_cfg = _get_detector_cfg(
setup_seed(0)
votenet_net_cfg = get_detector_cfg(
'imvotenet/imvotenet_stage2_8xb16_sunrgbd-3d.py')
model = MODELS.build(votenet_net_cfg)
packed_inputs = _create_detector_inputs(
packed_inputs = create_detector_inputs(
with_points=True,
with_img=True,
img_size=128,
......
tests/test_models/test_detectors/test_imvoxelnet.py
View file @ d7067e44
......@@ -4,8 +4,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestImVoxelNet(unittest.TestCase):
......@@ -15,12 +15,12 @@ class TestImVoxelNet(unittest.TestCase):
assert hasattr(mmdet3d.models, 'ImVoxelNet')
DefaultScope.get_instance('test_ImVoxelNet', scope_name='mmdet3d')
_setup_seed(0)
imvoxel_net_cfg = _get_detector_cfg(
setup_seed(0)
imvoxel_net_cfg = get_detector_cfg(
'imvoxelnet/imvoxelnet_8xb4_kitti-3d-car.py')
model = MODELS.build(imvoxel_net_cfg)
num_gt_instance = 1
packed_inputs = _create_detector_inputs(
packed_inputs = create_detector_inputs(
with_points=False,
with_img=True,
img_size=(128, 128),
......
tests/test_models/test_detectors/test_mvxnet.py
View file @ d7067e44
......@@ -4,8 +4,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestMVXNet(unittest.TestCase):
......@@ -15,14 +15,14 @@ class TestMVXNet(unittest.TestCase):
assert hasattr(mmdet3d.models, 'DynamicMVXFasterRCNN')
_setup_seed(0)
setup_seed(0)
DefaultScope.get_instance('test_mvxnet', scope_name='mmdet3d')
mvx_net_cfg = _get_detector_cfg(
mvx_net_cfg = get_detector_cfg(
'mvxnet/mvxnet_fpn_dv_second_secfpn_8xb2-80e_kitti-3d-3class.py' # noqa
)
model = MODELS.build(mvx_net_cfg)
num_gt_instance = 1
packed_inputs = _create_detector_inputs(
packed_inputs = create_detector_inputs(
with_img=False, num_gt_instance=num_gt_instance, points_feat_dim=4)
if torch.cuda.is_available():
......
tests/test_models/test_detectors/test_parta2.py
View file @ d7067e44
......@@ -4,8 +4,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestPartA2(unittest.TestCase):
......@@ -15,18 +15,17 @@ class TestPartA2(unittest.TestCase):
assert hasattr(mmdet3d.models, 'PartA2')
DefaultScope.get_instance('test_parta2', scope_name='mmdet3d')
_setup_seed(0)
parta2_cfg = _get_detector_cfg(
'parta2/PartA2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py')
setup_seed(0)
parta2_cfg = get_detector_cfg(
'parta2/parta2_hv_secfpn_8xb2-cyclic-80e_kitti-3d-3class.py')
model = MODELS.build(parta2_cfg)
num_gt_instance = 2
packed_inputs = _create_detector_inputs(
num_gt_instance=num_gt_instance)
packed_inputs = create_detector_inputs(num_gt_instance=num_gt_instance)
# TODO: Support aug data test
# aug_packed_inputs = [
# _create_detector_inputs(num_gt_instance=num_gt_instance),
# _create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# create_detector_inputs(num_gt_instance=num_gt_instance),
# create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# ]
# test_aug_test
# metainfo = {
......
tests/test_models/test_detectors/test_pointrcnn.py
View file @ d7067e44
......@@ -4,8 +4,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestPointRCNN(unittest.TestCase):
......@@ -15,12 +15,12 @@ class TestPointRCNN(unittest.TestCase):
assert hasattr(mmdet3d.models, 'PointRCNN')
DefaultScope.get_instance('test_pointrcnn', scope_name='mmdet3d')
_setup_seed(0)
pointrcnn_cfg = _get_detector_cfg(
setup_seed(0)
pointrcnn_cfg = get_detector_cfg(
'point_rcnn/point-rcnn_8xb2_kitti-3d-3class.py')
model = MODELS.build(pointrcnn_cfg)
num_gt_instance = 2
packed_inputs = _create_detector_inputs(
packed_inputs = create_detector_inputs(
num_points=10101, num_gt_instance=num_gt_instance)
if torch.cuda.is_available():
......
tests/test_models/test_detectors/test_pvrcnn.py 0 → 100644
View file @ d7067e44
import unittest
import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestPVRCNN(unittest.TestCase):
def test_pvrcnn(self):
import mmdet3d.models
assert hasattr(mmdet3d.models, 'PointVoxelRCNN')
DefaultScope.get_instance('test_pvrcnn', scope_name='mmdet3d')
setup_seed(0)
pvrcnn_cfg = get_detector_cfg(
'pv_rcnn/pv_rcnn_8xb2-80e_kitti-3d-3class.py')
model = MODELS.build(pvrcnn_cfg)
num_gt_instance = 2
packed_inputs = create_detector_inputs(num_gt_instance=num_gt_instance)
# TODO: Support aug data test
# aug_packed_inputs = [
# create_detector_inputs(num_gt_instance=num_gt_instance),
# create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# ]
# test_aug_test
# metainfo = {
# 'pcd_scale_factor': 1,
# 'pcd_horizontal_flip': 1,
# 'pcd_vertical_flip': 1,
# 'box_type_3d': LiDARInstance3DBoxes
# }
# for item in aug_packed_inputs:
# for batch_id in len(item['data_samples']):
# item['data_samples'][batch_id].set_metainfo(metainfo)
if torch.cuda.is_available():
model = model.cuda()
# test simple_test
with torch.no_grad():
data = model.data_preprocessor(packed_inputs, True)
torch.cuda.empty_cache()
results = model.forward(**data, mode='predict')
self.assertEqual(len(results), 1)
self.assertIn('bboxes_3d', results[0].pred_instances_3d)
self.assertIn('scores_3d', results[0].pred_instances_3d)
self.assertIn('labels_3d', results[0].pred_instances_3d)
# save the memory
with torch.no_grad():
losses = model.forward(**data, mode='loss')
torch.cuda.empty_cache()
self.assertGreater(losses['loss_rpn_cls'][0], 0)
self.assertGreaterEqual(losses['loss_rpn_bbox'][0], 0)
self.assertGreaterEqual(losses['loss_rpn_dir'][0], 0)
self.assertGreater(losses['loss_semantic'], 0)
self.assertGreaterEqual(losses['loss_bbox'], 0)
self.assertGreaterEqual(losses['loss_cls'], 0)
self.assertGreaterEqual(losses['loss_corner'], 0)
tests/test_models/test_detectors/test_sassd.py 0 → 100644
View file @ d7067e44
import unittest
import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestSDSSD(unittest.TestCase):
def test_3dssd(self):
import mmdet3d.models
assert hasattr(mmdet3d.models, 'SASSD')
DefaultScope.get_instance('test_sassd', scope_name='mmdet3d')
setup_seed(0)
voxel_net_cfg = get_detector_cfg(
'sassd/sassd_8xb6-80e_kitti-3d-3class.py')
model = MODELS.build(voxel_net_cfg)
num_gt_instance = 3
packed_inputs = create_detector_inputs(
num_gt_instance=num_gt_instance, num_classes=1)
if torch.cuda.is_available():
model = model.cuda()
# test simple_test
with torch.no_grad():
data = model.data_preprocessor(packed_inputs, True)
torch.cuda.empty_cache()
results = model.forward(**data, mode='predict')
self.assertEqual(len(results), 1)
self.assertIn('bboxes_3d', results[0].pred_instances_3d)
self.assertIn('scores_3d', results[0].pred_instances_3d)
self.assertIn('labels_3d', results[0].pred_instances_3d)
losses = model.forward(**data, mode='loss')
self.assertGreaterEqual(losses['loss_dir'][0], 0)
self.assertGreaterEqual(losses['loss_bbox'][0], 0)
self.assertGreaterEqual(losses['loss_cls'][0], 0)
self.assertGreater(losses['aux_loss_cls'][0], 0)
self.assertGreater(losses['aux_loss_reg'][0], 0)
tests/test_models/test_detectors/test_votenet.py
View file @ d7067e44
......@@ -4,8 +4,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestVotenet(unittest.TestCase):
......@@ -15,18 +15,16 @@ class TestVotenet(unittest.TestCase):
assert hasattr(mmdet3d.models, 'VoteNet')
DefaultScope.get_instance('test_vote_net', scope_name='mmdet3d')
_setup_seed(0)
voxel_net_cfg = _get_detector_cfg(
'votenet/votenet_8xb16_sunrgbd-3d.py')
setup_seed(0)
voxel_net_cfg = get_detector_cfg('votenet/votenet_8xb16_sunrgbd-3d.py')
model = MODELS.build(voxel_net_cfg)
num_gt_instance = 50
packed_inputs = _create_detector_inputs(
num_gt_instance=num_gt_instance)
packed_inputs = create_detector_inputs(num_gt_instance=num_gt_instance)
# TODO: Support aug test
# aug_data = [
# _create_detector_inputs(num_gt_instance=num_gt_instance),
# _create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# create_detector_inputs(num_gt_instance=num_gt_instance),
# create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# ]
# # test_aug_test
# metainfo = {
......
tests/test_models/test_detectors/test_voxelnet.py
View file @ d7067e44
......@@ -5,8 +5,8 @@ import torch
from mmengine import DefaultScope
from mmdet3d.registry import MODELS
from tests.utils.model_utils import (_create_detector_inputs,
_get_detector_cfg, _setup_seed)
from mmdet3d.testing import (create_detector_inputs, get_detector_cfg,
setup_seed)
class TestVoxelNet(unittest.TestCase):
......@@ -16,18 +16,17 @@ class TestVoxelNet(unittest.TestCase):
assert hasattr(mmdet3d.models, 'VoxelNet')
DefaultScope.get_instance('test_voxelnet', scope_name='mmdet3d')
_setup_seed(0)
pointpillars_cfg = _get_detector_cfg(
setup_seed(0)
pointpillars_cfg = get_detector_cfg(
'pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py')
model = MODELS.build(pointpillars_cfg)
num_gt_instance = 2
packed_inputs = _create_detector_inputs(
num_gt_instance=num_gt_instance)
packed_inputs = create_detector_inputs(num_gt_instance=num_gt_instance)
# TODO: Support aug_test
# aug_data = [
# _create_detector_inputs(num_gt_instance=num_gt_instance),
# _create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# create_detector_inputs(num_gt_instance=num_gt_instance),
# create_detector_inputs(num_gt_instance=num_gt_instance + 1)
# ]
# # test_aug_test
# metainfo = {
......
tests/test_models/test_losses/test_rotated_iou_loss.py 0 → 100644
View file @ d7067e44
# Copyright (c) OpenMMLab. All rights reserved.
import numpy as np
import torch
from mmdet3d.models.losses import RotatedIoU3DLoss
def test_rotated_iou_3d_loss():
if not torch.cuda.is_available():
return
boxes1 = torch.tensor([[.5, .5, .5, 1., 1., 1., .0],
[.5, .5, .5, 1., 1., 1., .0],
[.5, .5, .5, 1., 1., 1., .0],
[.5, .5, .5, 1., 1., 1., .0],
[.5, .5, .5, 1., 1., 1., .0]]).cuda()
boxes2 = torch.tensor([[.5, .5, .5, 1., 1., 1., .0],
[.5, .5, .5, 1., 1., 2., np.pi / 2],
[.5, .5, .5, 1., 1., 1., np.pi / 4],
[1., 1., 1., 1., 1., 1., .0],
[-1.5, -1.5, -1.5, 2.5, 2.5, 2.5, .0]]).cuda()
expect_ious = 1 - torch.tensor([[1., .5, .7071, 1 / 15, .0]]).cuda()
ious = RotatedIoU3DLoss(reduction='none')(boxes1, boxes2)
assert torch.allclose(ious, expect_ious, atol=1e-4)
tests/test_models/test_necks/test_second_fpn.py
View file @ d7067e44
......@@ -45,8 +45,8 @@ def test_centerpoint_fpn():
second_cfg = dict(
type='SECOND',
in_channels=64,
out_channels=[64, 128, 256],
in_channels=2,
out_channels=[2, 2, 2],
layer_nums=[3, 5, 5],
layer_strides=[2, 2, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
......@@ -57,8 +57,8 @@ def test_centerpoint_fpn():
# centerpoint usage of fpn
centerpoint_fpn_cfg = dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
out_channels=[128, 128, 128],
in_channels=[2, 2, 2],
out_channels=[2, 2, 2],
upsample_strides=[0.5, 1, 2],
norm_cfg=dict(type='BN', eps=1e-3, momentum=0.01),
upsample_cfg=dict(type='deconv', bias=False),
......@@ -67,17 +67,17 @@ def test_centerpoint_fpn():
# original usage of fpn
fpn_cfg = dict(
type='SECONDFPN',
in_channels=[64, 128, 256],
in_channels=[2, 2, 2],
upsample_strides=[1, 2, 4],
out_channels=[128, 128, 128])
out_channels=[2, 2, 2])
second_fpn = build_neck(fpn_cfg)
centerpoint_second_fpn = build_neck(centerpoint_fpn_cfg)
input = torch.rand([4, 64, 512, 512])
input = torch.rand([2, 2, 32, 32])
sec_output = second(input)
centerpoint_output = centerpoint_second_fpn(sec_output)
second_output = second_fpn(sec_output)
assert centerpoint_output[0].shape == torch.Size([4, 384, 128, 128])
assert second_output[0].shape == torch.Size([4, 384, 256, 256])
assert centerpoint_output[0].shape == torch.Size([2, 6, 8, 8])
assert second_output[0].shape == torch.Size([2, 6, 16, 16])
tests/test_models/test_task_modules/test_anchor/test_anchor_3d_generator.py
View file @ d7067e44
......@@ -45,10 +45,10 @@ def test_anchor_3d_range_generator():
'\nrotations=[0, 1.57],\nreshape_out=False,' \
'\nsize_per_range=True)'
assert repr_str == expected_repr_str
featmap_size = (256, 256)
featmap_size = (8, 8)
mr_anchors = anchor_generator.single_level_grid_anchors(
featmap_size, 1.1, device=device)
assert mr_anchors.shape == torch.Size([1, 256, 256, 3, 2, 7])
assert mr_anchors.shape == torch.Size([1, 8, 8, 3, 2, 7])
def test_aligned_anchor_generator():
......@@ -80,108 +80,108 @@ def test_aligned_anchor_generator():
size_per_range=False,
reshape_out=True)
featmap_sizes = [(256, 256), (128, 128), (64, 64)]
featmap_sizes = [(16, 16), (8, 8), (4, 4)]
anchor_generator = TASK_UTILS.build(anchor_generator_cfg)
assert anchor_generator.num_base_anchors == 8
# check base anchors
expected_grid_anchors = [
torch.tensor([[
-51.0000, -51.0000, -1.8000, 2.5981, 0.8660, 1.0000, 0.0000,
-48.0000, -48.0000, -1.8000, 2.5981, 0.8660, 1.0000, 0.0000,
0.0000, 0.0000
],
[
-51.0000, -51.0000, -1.8000, 0.4000, 0.4000, 1.0000,
-48.0000, -48.0000, -1.8000, 0.4000, 0.4000, 1.0000,
1.5700, 0.0000, 0.0000
],
[
-50.6000, -51.0000, -1.8000, 0.4000, 0.4000, 1.0000,
-41.6000, -48.0000, -1.8000, 0.4000, 0.4000, 1.0000,
0.0000, 0.0000, 0.0000
],
[
-50.2000, -51.0000, -1.8000, 1.0000, 1.0000, 1.0000,
-35.2000, -48.0000, -1.8000, 1.0000, 1.0000, 1.0000,
1.5700, 0.0000, 0.0000
],
[
-49.8000, -51.0000, -1.8000, 1.0000, 1.0000, 1.0000,
-28.8000, -48.0000, -1.8000, 1.0000, 1.0000, 1.0000,
0.0000, 0.0000, 0.0000
],
[
-49.4000, -51.0000, -1.8000, 1.7321, 0.5774, 1.0000,
-22.4000, -48.0000, -1.8000, 1.7321, 0.5774, 1.0000,
1.5700, 0.0000, 0.0000
],
[
-49.0000, -51.0000, -1.8000, 1.7321, 0.5774, 1.0000,
-16.0000, -48.0000, -1.8000, 1.7321, 0.5774, 1.0000,
0.0000, 0.0000, 0.0000
],
[
-48.6000, -51.0000, -1.8000, 2.5981, 0.8660, 1.0000,
-9.6000, -48.0000, -1.8000, 2.5981, 0.8660, 1.0000,
1.5700, 0.0000, 0.0000
]],
device=device),
torch.tensor([[
-50.8000, -50.8000, -1.8000, 5.1962, 1.7320, 2.0000, 0.0000,
-44.8000, -44.8000, -1.8000, 5.1962, 1.7320, 2.0000, 0.0000,
0.0000, 0.0000
],
[
-50.8000, -50.8000, -1.8000, 0.8000, 0.8000, 2.0000,
-44.8000, -44.8000, -1.8000, 0.8000, 0.8000, 2.0000,
1.5700, 0.0000, 0.0000
],
[
-50.0000, -50.8000, -1.8000, 0.8000, 0.8000, 2.0000,
-32.0000, -44.8000, -1.8000, 0.8000, 0.8000, 2.0000,
0.0000, 0.0000, 0.0000
],
[
-49.2000, -50.8000, -1.8000, 2.0000, 2.0000, 2.0000,
-19.2000, -44.8000, -1.8000, 2.0000, 2.0000, 2.0000,
1.5700, 0.0000, 0.0000
],
[
-48.4000, -50.8000, -1.8000, 2.0000, 2.0000, 2.0000,
-6.4000, -44.8000, -1.8000, 2.0000, 2.0000, 2.0000,
0.0000, 0.0000, 0.0000
],
[
-47.6000, -50.8000, -1.8000, 3.4642, 1.1548, 2.0000,
6.4000, -44.8000, -1.8000, 3.4642, 1.1548, 2.0000,
1.5700, 0.0000, 0.0000
],
[
-46.8000, -50.8000, -1.8000, 3.4642, 1.1548, 2.0000,
19.2000, -44.8000, -1.8000, 3.4642, 1.1548, 2.0000,
0.0000, 0.0000, 0.0000
],
[
-46.0000, -50.8000, -1.8000, 5.1962, 1.7320, 2.0000,
32.0000, -44.8000, -1.8000, 5.1962, 1.7320, 2.0000,
1.5700, 0.0000, 0.0000
]],
device=device),
torch.tensor([[
-50.4000, -50.4000, -1.8000, 10.3924, 3.4640, 4.0000, 0.0000,
-38.4000, -38.4000, -1.8000, 10.3924, 3.4640, 4.0000, 0.0000,
0.0000, 0.0000
],
[
-50.4000, -50.4000, -1.8000, 1.6000, 1.6000, 4.0000,
-38.4000, -38.4000, -1.8000, 1.6000, 1.6000, 4.0000,
1.5700, 0.0000, 0.0000
],
[
-48.8000, -50.4000, -1.8000, 1.6000, 1.6000, 4.0000,
-12.8000, -38.4000, -1.8000, 1.6000, 1.6000, 4.0000,
0.0000, 0.0000, 0.0000
],
[
-47.2000, -50.4000, -1.8000, 4.0000, 4.0000, 4.0000,
12.8000, -38.4000, -1.8000, 4.0000, 4.0000, 4.0000,
1.5700, 0.0000, 0.0000
],
[
-45.6000, -50.4000, -1.8000, 4.0000, 4.0000, 4.0000,
38.4000, -38.4000, -1.8000, 4.0000, 4.0000, 4.0000,
0.0000, 0.0000, 0.0000
],
[
-44.0000, -50.4000, -1.8000, 6.9284, 2.3096, 4.0000,
-38.4000, -12.8000, -1.8000, 6.9284, 2.3096, 4.0000,
1.5700, 0.0000, 0.0000
],
[
-42.4000, -50.4000, -1.8000, 6.9284, 2.3096, 4.0000,
-12.8000, -12.8000, -1.8000, 6.9284, 2.3096, 4.0000,
0.0000, 0.0000, 0.0000
],
[
-40.8000, -50.4000, -1.8000, 10.3924, 3.4640, 4.0000,
12.8000, -12.8000, -1.8000, 10.3924, 3.4640, 4.0000,
1.5700, 0.0000, 0.0000
]],
device=device)
......@@ -189,9 +189,9 @@ def test_aligned_anchor_generator():
multi_level_anchors = anchor_generator.grid_anchors(
featmap_sizes, device=device)
expected_multi_level_shapes = [
torch.Size([524288, 9]),
torch.Size([131072, 9]),
torch.Size([32768, 9])
torch.Size([2048, 9]),
torch.Size([512, 9]),
torch.Size([128, 9])
]
for i, single_level_anchor in enumerate(multi_level_anchors):
assert single_level_anchor.shape == expected_multi_level_shapes[i]
......
tests/test_models/test_task_modules/test_voxel/test_voxel_generator.py
View file @ d7067e44
......@@ -6,17 +6,15 @@ from mmdet3d.models.task_modules.voxel import VoxelGenerator
def test_voxel_generator():
np.random.seed(0)
voxel_size = [0.5, 0.5, 0.5]
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
max_num_points = 1000
voxel_size = [5, 5, 1]
point_cloud_range = [0, 0, 0, 20, 40, 4]
max_num_points = 5
self = VoxelGenerator(voxel_size, point_cloud_range, max_num_points)
points = np.random.rand(1000, 4)
points = np.random.uniform(0, 4, (20, 3))
voxels = self.generate(points)
voxels, coors, num_points_per_voxel = voxels
expected_coors = np.array([[7, 81, 1], [6, 81, 0], [7, 80, 1], [6, 81, 1],
[7, 81, 0], [6, 80, 1], [7, 80, 0], [6, 80, 0]])
expected_num_points_per_voxel = np.array(
[120, 121, 127, 134, 115, 127, 125, 131])
assert voxels.shape == (8, 1000, 4)
expected_coors = np.array([[2, 0, 0], [3, 0, 0], [0, 0, 0], [1, 0, 0]])
expected_num_points_per_voxel = np.array([5, 5, 5, 3])
assert voxels.shape == (4, 5, 3)
assert np.all(coors == expected_coors)
assert np.all(num_points_per_voxel == expected_num_points_per_voxel)
tools/create_data.py
View file @ d7067e44
......@@ -35,9 +35,6 @@ def kitti_data_prep(root_path,
info_train_path = osp.join(out_dir, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(out_dir, f'{info_prefix}_infos_val.pkl')
info_trainval_path = osp.join(out_dir, f'{info_prefix}_infos_trainval.pkl')
kitti.export_2d_annotation(root_path, info_train_path)
kitti.export_2d_annotation(root_path, info_val_path)
kitti.export_2d_annotation(root_path, info_trainval_path)
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_train_path)
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_val_path)
update_pkl_infos('kitti', out_dir=out_dir, pkl_path=info_trainval_path)
......@@ -76,17 +73,11 @@ def nuscenes_data_prep(root_path,
if version == 'v1.0-test':
info_test_path = osp.join(out_dir, f'{info_prefix}_infos_test.pkl')
nuscenes_converter.export_2d_annotation(
root_path, info_test_path, version=version)
update_pkl_infos('nuscenes', out_dir=out_dir, pkl_path=info_test_path)
return
info_train_path = osp.join(out_dir, f'{info_prefix}_infos_train.pkl')
info_val_path = osp.join(out_dir, f'{info_prefix}_infos_val.pkl')
nuscenes_converter.export_2d_annotation(
root_path, info_train_path, version=version)
nuscenes_converter.export_2d_annotation(
root_path, info_val_path, version=version)
update_pkl_infos('nuscenes', out_dir=out_dir, pkl_path=info_train_path)
update_pkl_infos('nuscenes', out_dir=out_dir, pkl_path=info_val_path)
create_groundtruth_database(dataset_name, root_path, info_prefix,
......@@ -265,6 +256,11 @@ args = parser.parse_args()
if __name__ == '__main__':
from mmdet3d.utils import register_all_modules
register_all_modules()
# Set to spawn mode to avoid stuck when process dataset creating
import multiprocessing
multiprocessing.set_start_method('spawn')
if args.dataset == 'kitti':
kitti_data_prep(
root_path=args.root_path,
......
tools/dataset_converters/create_gt_database.py
View file @ d7067e44
......@@ -6,13 +6,13 @@ import mmcv
import mmengine
import numpy as np
from mmcv.ops import roi_align
from mmdet.evaluation import bbox_overlaps
from mmengine import track_iter_progress
from pycocotools import mask as maskUtils
from pycocotools.coco import COCO
from mmdet3d.datasets import build_dataset
from mmdet3d.structures.ops import box_np_ops as box_np_ops
from mmdet.evaluation import bbox_overlaps
def _poly2mask(mask_ann, img_h, img_w):
......@@ -243,7 +243,7 @@ def create_groundtruth_database(dataset_class_name,
image_idx = example['sample_idx']
points = example['points'].tensor.numpy()
gt_boxes_3d = annos['gt_bboxes_3d'].tensor.numpy()
names = [dataset.metainfo['CLASSES'][i] for i in annos['gt_labels_3d']]
names = [dataset.metainfo['classes'][i] for i in annos['gt_labels_3d']]
group_dict = dict()
if 'group_ids' in annos:
group_ids = annos['group_ids']
......@@ -409,7 +409,7 @@ class GTDatabaseCreater:
points = example['points'].tensor.numpy()
gt_boxes_3d = annos['gt_bboxes_3d'].tensor.numpy()
names = [
self.dataset.metainfo['CLASSES'][i] for i in annos['gt_labels_3d']
self.dataset.metainfo['classes'][i] for i in annos['gt_labels_3d']
]
group_dict = dict()
if 'group_ids' in annos:
......
tools/dataset_converters/lyft_converter.py
View file @ d7067e44
......@@ -131,6 +131,7 @@ def _fill_trainval_infos(lyft,
info = {
'lidar_path': lidar_path,
'num_features': 5,
'token': sample['token'],
'sweeps': [],
'cams': dict(),
......
tools/dataset_converters/s3dis_data_utils.py
View file @ d7067e44
......@@ -129,7 +129,7 @@ class S3DISData(object):
- gt_num (int): Number of boxes.
"""
bboxes, labels = [], []
for i in range(1, pts_instance_mask.max()):
for i in range(1, pts_instance_mask.max() + 1):
ids = pts_instance_mask == i
# check if all instance points have same semantic label
assert pts_semantic_mask[ids].min() == pts_semantic_mask[ids].max()
......
tools/dataset_converters/update_infos_to_v2.py
View file @ d7067e44
......@@ -4,7 +4,7 @@
Example:
python tools/dataset_converters/update_infos_to_v2.py
--dataset kitti
--pkl ./data/kitti/kitti_infos_train.pkl
--pkl-path ./data/kitti/kitti_infos_train.pkl
--out-dir ./kitti_v2/
"""
......@@ -12,6 +12,7 @@ import argparse
import copy
import time
from os import path as osp
from pathlib import Path
import mmengine
import numpy as np
......@@ -80,9 +81,6 @@ def get_empty_lidar_points():
num_pts_feats=None,
# (str, optional): Path of LiDAR data file.
lidar_path=None,
# (list[list[float]]): Transformation matrix from lidar
# or depth to image with shape [4, 4].
lidar2img=None,
# (list[list[float]], optional): Transformation matrix
# from lidar to ego-vehicle
# with shape [4, 4].
......@@ -120,6 +118,9 @@ def get_empty_img_info():
# matrix from camera to image with
# shape [3, 3], [3, 4] or [4, 4].
cam2img=None,
# (list[list[float]]): Transformation matrix from lidar
# or depth to image with shape [4, 4].
lidar2img=None,
# (list[list[float]], optional) : Transformation
# matrix from camera to ego-vehicle
# with shape [4, 4].
......@@ -159,7 +160,7 @@ def get_empty_standard_data_info(
data_info = dict(
# (str): Sample id of the frame.
sample_id=None,
sample_idx=None,
# (str, optional): '000010'
token=None,
**get_single_image_sweep(camera_types),
......@@ -261,13 +262,9 @@ def update_nuscenes_infos(pkl_path, out_dir):
print(f'Reading from input file: {pkl_path}.')
data_list = mmengine.load(pkl_path)
METAINFO = {
'CLASSES':
'classes':
('car', 'truck', 'trailer', 'bus', 'construction_vehicle', 'bicycle',
'motorcycle', 'pedestrian', 'traffic_cone', 'barrier'),
'DATASET':
'Nuscenes',
'version':
data_list['metadata']['version']
}
nusc = NuScenes(
version=data_list['metadata']['version'],
......@@ -287,8 +284,8 @@ def update_nuscenes_infos(pkl_path, out_dir):
ori_info_dict['ego2global_translation'])
temp_data_info['lidar_points']['num_pts_feats'] = ori_info_dict.get(
'num_features', 5)
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'lidar_path'].split('/')[-1]
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['lidar_path']).name
temp_data_info['lidar_points'][
'lidar2ego'] = convert_quaternion_to_matrix(
ori_info_dict['lidar2ego_rotation'],
......@@ -318,8 +315,8 @@ def update_nuscenes_infos(pkl_path, out_dir):
temp_data_info['images'] = {}
for cam in ori_info_dict['cams']:
empty_img_info = get_empty_img_info()
empty_img_info['img_path'] = ori_info_dict['cams'][cam][
'data_path'].split('/')[-1]
empty_img_info['img_path'] = Path(
ori_info_dict['cams'][cam]['data_path']).name
empty_img_info['cam2img'] = ori_info_dict['cams'][cam][
'cam_intrinsic'].tolist()
empty_img_info['sample_data_token'] = ori_info_dict['cams'][cam][
......@@ -344,8 +341,8 @@ def update_nuscenes_infos(pkl_path, out_dir):
empty_instance = get_empty_instance()
empty_instance['bbox_3d'] = ori_info_dict['gt_boxes'][
i, :].tolist()
if ori_info_dict['gt_names'][i] in METAINFO['CLASSES']:
empty_instance['bbox_label'] = METAINFO['CLASSES'].index(
if ori_info_dict['gt_names'][i] in METAINFO['classes']:
empty_instance['bbox_label'] = METAINFO['classes'].index(
ori_info_dict['gt_names'][i])
else:
ignore_class_name.add(ori_info_dict['gt_names'][i])
......@@ -363,11 +360,20 @@ def update_nuscenes_infos(pkl_path, out_dir):
ori_info_dict, nusc)
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(metainfo=METAINFO, data_list=converted_list)
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 'nuscenes'
metainfo['version'] = data_list['metadata']['version']
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -381,7 +387,7 @@ def update_kitti_infos(pkl_path, out_dir):
# TODO update to full label
# TODO discuss how to process 'Van', 'DontCare'
METAINFO = {
'CLASSES': ('Pedestrian', 'Cyclist', 'Car', 'Van', 'Truck',
'classes': ('Pedestrian', 'Cyclist', 'Car', 'Van', 'Truck',
'Person_sitting', 'Tram', 'Misc'),
}
print(f'Reading from input file: {pkl_path}.')
......@@ -405,15 +411,15 @@ def update_kitti_infos(pkl_path, out_dir):
temp_data_info['images']['CAM3']['cam2img'] = ori_info_dict['calib'][
'P3'].tolist()
temp_data_info['images']['CAM2']['img_path'] = ori_info_dict['image'][
'image_path'].split('/')[-1]
temp_data_info['images']['CAM2']['img_path'] = Path(
ori_info_dict['image']['image_path']).name
h, w = ori_info_dict['image']['image_shape']
temp_data_info['images']['CAM2']['height'] = h
temp_data_info['images']['CAM2']['width'] = w
temp_data_info['lidar_points']['num_pts_feats'] = ori_info_dict[
'point_cloud']['num_features']
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'point_cloud']['velodyne_path'].split('/')[-1]
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['point_cloud']['velodyne_path']).name
rect = ori_info_dict['calib']['R0_rect'].astype(np.float32)
Trv2c = ori_info_dict['calib']['Tr_velo_to_cam'].astype(np.float32)
......@@ -446,8 +452,8 @@ def update_kitti_infos(pkl_path, out_dir):
empty_instance = get_empty_instance()
empty_instance['bbox'] = anns['bbox'][instance_id].tolist()
if anns['name'][instance_id] in METAINFO['CLASSES']:
empty_instance['bbox_label'] = METAINFO['CLASSES'].index(
if anns['name'][instance_id] in METAINFO['classes']:
empty_instance['bbox_label'] = METAINFO['classes'].index(
anns['name'][instance_id])
else:
ignore_class_name.add(anns['name'][instance_id])
......@@ -493,12 +499,20 @@ def update_kitti_infos(pkl_path, out_dir):
temp_data_info['cam_instances'] = cam_instances
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(
metainfo={'DATASET': 'KITTI'}, data_list=converted_list)
# dataset metainfo
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 'kitti'
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -509,7 +523,7 @@ def update_s3dis_infos(pkl_path, out_dir):
print(f'Warning, you may overwriting '
f'the original data {pkl_path}.')
time.sleep(5)
METAINFO = {'CLASSES': ('table', 'chair', 'sofa', 'bookcase', 'board')}
METAINFO = {'classes': ('table', 'chair', 'sofa', 'bookcase', 'board')}
print(f'Reading from input file: {pkl_path}.')
data_list = mmengine.load(pkl_path)
print('Start updating:')
......@@ -519,12 +533,12 @@ def update_s3dis_infos(pkl_path, out_dir):
temp_data_info['sample_idx'] = i
temp_data_info['lidar_points']['num_pts_feats'] = ori_info_dict[
'point_cloud']['num_features']
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'pts_path'].split('/')[-1]
temp_data_info['pts_semantic_mask_path'] = ori_info_dict[
'pts_semantic_mask_path'].split('/')[-1]
temp_data_info['pts_instance_mask_path'] = ori_info_dict[
'pts_instance_mask_path'].split('/')[-1]
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['pts_path']).name
temp_data_info['pts_semantic_mask_path'] = Path(
ori_info_dict['pts_semantic_mask_path']).name
temp_data_info['pts_instance_mask_path'] = Path(
ori_info_dict['pts_instance_mask_path']).name
# TODO support camera
# np.linalg.inv(info['axis_align_matrix'] @ extrinsic): depth2cam
......@@ -541,12 +555,12 @@ def update_s3dis_infos(pkl_path, out_dir):
empty_instance['bbox_3d'] = anns['gt_boxes_upright_depth'][
instance_id].tolist()
if anns['class'][instance_id] < len(METAINFO['CLASSES']):
if anns['class'][instance_id] < len(METAINFO['classes']):
empty_instance['bbox_label_3d'] = anns['class'][
instance_id]
else:
ignore_class_name.add(
METAINFO['CLASSES'][anns['class'][instance_id]])
METAINFO['classes'][anns['class'][instance_id]])
empty_instance['bbox_label_3d'] = -1
empty_instance = clear_instance_unused_keys(empty_instance)
......@@ -554,12 +568,21 @@ def update_s3dis_infos(pkl_path, out_dir):
temp_data_info['instances'] = instance_list
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(
metainfo={'DATASET': 'S3DIS'}, data_list=converted_list)
# dataset metainfo
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 's3dis'
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -571,7 +594,7 @@ def update_scannet_infos(pkl_path, out_dir):
f'the original data {pkl_path}.')
time.sleep(5)
METAINFO = {
'CLASSES':
'classes':
('cabinet', 'bed', 'chair', 'sofa', 'table', 'door', 'window',
'bookshelf', 'picture', 'counter', 'desk', 'curtain', 'refrigerator',
'showercurtrain', 'toilet', 'sink', 'bathtub', 'garbagebin')
......@@ -584,12 +607,12 @@ def update_scannet_infos(pkl_path, out_dir):
temp_data_info = get_empty_standard_data_info()
temp_data_info['lidar_points']['num_pts_feats'] = ori_info_dict[
'point_cloud']['num_features']
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'pts_path'].split('/')[-1]
temp_data_info['pts_semantic_mask_path'] = ori_info_dict[
'pts_semantic_mask_path'].split('/')[-1]
temp_data_info['pts_instance_mask_path'] = ori_info_dict[
'pts_instance_mask_path'].split('/')[-1]
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['pts_path']).name
temp_data_info['pts_semantic_mask_path'] = Path(
ori_info_dict['pts_semantic_mask_path']).name
temp_data_info['pts_instance_mask_path'] = Path(
ori_info_dict['pts_instance_mask_path']).name
# TODO support camera
# np.linalg.inv(info['axis_align_matrix'] @ extrinsic): depth2cam
......@@ -607,9 +630,9 @@ def update_scannet_infos(pkl_path, out_dir):
empty_instance['bbox_3d'] = anns['gt_boxes_upright_depth'][
instance_id].tolist()
if anns['name'][instance_id] in METAINFO['CLASSES']:
if anns['name'][instance_id] in METAINFO['classes']:
empty_instance['bbox_label_3d'] = METAINFO[
'CLASSES'].index(anns['name'][instance_id])
'classes'].index(anns['name'][instance_id])
else:
ignore_class_name.add(anns['name'][instance_id])
empty_instance['bbox_label_3d'] = -1
......@@ -619,12 +642,21 @@ def update_scannet_infos(pkl_path, out_dir):
temp_data_info['instances'] = instance_list
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(
metainfo={'DATASET': 'SCANNET'}, data_list=converted_list)
# dataset metainfo
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 'scannet'
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -636,7 +668,7 @@ def update_sunrgbd_infos(pkl_path, out_dir):
f'the original data {pkl_path}.')
time.sleep(5)
METAINFO = {
'CLASSES': ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk',
'classes': ('bed', 'table', 'sofa', 'chair', 'toilet', 'desk',
'dresser', 'night_stand', 'bookshelf', 'bathtub')
}
print(f'Reading from input file: {pkl_path}.')
......@@ -647,8 +679,8 @@ def update_sunrgbd_infos(pkl_path, out_dir):
temp_data_info = get_empty_standard_data_info()
temp_data_info['lidar_points']['num_pts_feats'] = ori_info_dict[
'point_cloud']['num_features']
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'pts_path'].split('/')[-1]
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['pts_path']).name
calib = ori_info_dict['calib']
rt_mat = calib['Rt']
# follow Coord3DMode.convert_point
......@@ -656,8 +688,8 @@ def update_sunrgbd_infos(pkl_path, out_dir):
]) @ rt_mat.transpose(1, 0)
depth2img = calib['K'] @ rt_mat
temp_data_info['images']['CAM0']['depth2img'] = depth2img.tolist()
temp_data_info['images']['CAM0']['img_path'] = ori_info_dict['image'][
'image_path'].split('/')[-1]
temp_data_info['images']['CAM0']['img_path'] = Path(
ori_info_dict['image']['image_path']).name
h, w = ori_info_dict['image']['image_shape']
temp_data_info['images']['CAM0']['height'] = h
temp_data_info['images']['CAM0']['width'] = w
......@@ -674,9 +706,9 @@ def update_sunrgbd_infos(pkl_path, out_dir):
empty_instance['bbox_3d'] = anns['gt_boxes_upright_depth'][
instance_id].tolist()
empty_instance['bbox'] = anns['bbox'][instance_id].tolist()
if anns['name'][instance_id] in METAINFO['CLASSES']:
if anns['name'][instance_id] in METAINFO['classes']:
empty_instance['bbox_label_3d'] = METAINFO[
'CLASSES'].index(anns['name'][instance_id])
'classes'].index(anns['name'][instance_id])
empty_instance['bbox_label'] = empty_instance[
'bbox_label_3d']
else:
......@@ -688,12 +720,21 @@ def update_sunrgbd_infos(pkl_path, out_dir):
temp_data_info['instances'] = instance_list
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(
metainfo={'DATASET': 'SUNRGBD'}, data_list=converted_list)
# dataset metainfo
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 'sunrgbd'
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -706,13 +747,9 @@ def update_lyft_infos(pkl_path, out_dir):
print(f'Reading from input file: {pkl_path}.')
data_list = mmengine.load(pkl_path)
METAINFO = {
'CLASSES':
'classes':
('car', 'truck', 'bus', 'emergency_vehicle', 'other_vehicle',
'motorcycle', 'bicycle', 'pedestrian', 'animal'),
'DATASET':
'Nuscenes',
'version':
data_list['metadata']['version']
}
print('Start updating:')
converted_list = []
......@@ -724,8 +761,10 @@ def update_lyft_infos(pkl_path, out_dir):
temp_data_info['ego2global'] = convert_quaternion_to_matrix(
ori_info_dict['ego2global_rotation'],
ori_info_dict['ego2global_translation'])
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'lidar_path'].split('/')[-1]
temp_data_info['lidar_points']['num_pts_feats'] = ori_info_dict.get(
'num_features', 5)
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['lidar_path']).name
temp_data_info['lidar_points'][
'lidar2ego'] = convert_quaternion_to_matrix(
ori_info_dict['lidar2ego_rotation'],
......@@ -756,8 +795,8 @@ def update_lyft_infos(pkl_path, out_dir):
temp_data_info['images'] = {}
for cam in ori_info_dict['cams']:
empty_img_info = get_empty_img_info()
empty_img_info['img_path'] = ori_info_dict['cams'][cam][
'data_path'].split('/')[-1]
empty_img_info['img_path'] = Path(
ori_info_dict['cams'][cam]['data_path']).name
empty_img_info['cam2img'] = ori_info_dict['cams'][cam][
'cam_intrinsic'].tolist()
empty_img_info['sample_data_token'] = ori_info_dict['cams'][cam][
......@@ -781,8 +820,8 @@ def update_lyft_infos(pkl_path, out_dir):
empty_instance = get_empty_instance()
empty_instance['bbox_3d'] = ori_info_dict['gt_boxes'][
i, :].tolist()
if ori_info_dict['gt_names'][i] in METAINFO['CLASSES']:
empty_instance['bbox_label'] = METAINFO['CLASSES'].index(
if ori_info_dict['gt_names'][i] in METAINFO['classes']:
empty_instance['bbox_label'] = METAINFO['classes'].index(
ori_info_dict['gt_names'][i])
else:
ignore_class_name.add(ori_info_dict['gt_names'][i])
......@@ -793,11 +832,20 @@ def update_lyft_infos(pkl_path, out_dir):
temp_data_info['instances'].append(empty_instance)
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(metainfo=METAINFO, data_list=converted_list)
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 'lyft'
metainfo['version'] = data_list['metadata']['version']
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -820,7 +868,7 @@ def update_waymo_infos(pkl_path, out_dir):
# TODO update to full label
# TODO discuss how to process 'Van', 'DontCare'
METAINFO = {
'CLASSES': ('Car', 'Pedestrian', 'Cyclist', 'Sign'),
'classes': ('Car', 'Pedestrian', 'Cyclist', 'Sign'),
}
print(f'Reading from input file: {pkl_path}.')
data_list = mmengine.load(pkl_path)
......@@ -851,7 +899,7 @@ def update_waymo_infos(pkl_path, out_dir):
ori_info_dict['calib'][f'P{cam_idx}'] @ lidar2cam).tolist()
# image path
base_img_path = ori_info_dict['image']['image_path'].split('/')[-1]
base_img_path = Path(ori_info_dict['image']['image_path']).name
for cam_idx, cam_key in enumerate(camera_types):
temp_data_info['images'][cam_key]['timestamp'] = ori_info_dict[
......@@ -867,8 +915,8 @@ def update_waymo_infos(pkl_path, out_dir):
'point_cloud']['num_features']
temp_data_info['lidar_points']['timestamp'] = ori_info_dict[
'timestamp']
temp_data_info['lidar_points']['lidar_path'] = ori_info_dict[
'point_cloud']['velodyne_path'].split('/')[-1]
temp_data_info['lidar_points']['lidar_path'] = Path(
ori_info_dict['point_cloud']['velodyne_path']).name
# TODO discuss the usage of Tr_velo_to_cam in lidar
Trv2c = ori_info_dict['calib']['Tr_velo_to_cam'].astype(np.float32)
......@@ -888,13 +936,13 @@ def update_waymo_infos(pkl_path, out_dir):
lidar_sweep = get_single_lidar_sweep()
lidar_sweep['ego2global'] = ori_sweep['pose']
lidar_sweep['timestamp'] = ori_sweep['timestamp']
lidar_sweep['lidar_points']['lidar_path'] = ori_sweep[
'velodyne_path'].split('/')[-1]
lidar_sweep['lidar_points']['lidar_path'] = Path(
ori_sweep['velodyne_path']).name
# image sweeps
image_sweep = get_single_image_sweep(camera_types)
image_sweep['ego2global'] = ori_sweep['pose']
image_sweep['timestamp'] = ori_sweep['timestamp']
img_path = ori_sweep['image_path'].split('/')[-1]
img_path = Path(ori_sweep['image_path']).name
for cam_idx, cam_key in enumerate(camera_types):
image_sweep['images'][cam_key]['img_path'] = img_path
......@@ -910,8 +958,8 @@ def update_waymo_infos(pkl_path, out_dir):
empty_instance = get_empty_instance()
empty_instance['bbox'] = anns['bbox'][instance_id].tolist()
if anns['name'][instance_id] in METAINFO['CLASSES']:
empty_instance['bbox_label'] = METAINFO['CLASSES'].index(
if anns['name'][instance_id] in METAINFO['classes']:
empty_instance['bbox_label'] = METAINFO['classes'].index(
anns['name'][instance_id])
else:
ignore_class_name.add(anns['name'][instance_id])
......@@ -954,8 +1002,8 @@ def update_waymo_infos(pkl_path, out_dir):
empty_instance = get_empty_instance()
empty_instance['bbox'] = anns['bbox'][instance_id].tolist()
if anns['name'][instance_id] in METAINFO['CLASSES']:
empty_instance['bbox_label'] = METAINFO['CLASSES'].index(
if anns['name'][instance_id] in METAINFO['classes']:
empty_instance['bbox_label'] = METAINFO['classes'].index(
anns['name'][instance_id])
else:
ignore_class_name.add(anns['name'][instance_id])
......@@ -991,12 +1039,22 @@ def update_waymo_infos(pkl_path, out_dir):
temp_data_info, _ = clear_data_info_unused_keys(temp_data_info)
converted_list.append(temp_data_info)
pkl_name = pkl_path.split('/')[-1]
pkl_name = Path(pkl_path).name
out_path = osp.join(out_dir, pkl_name)
print(f'Writing to output file: {out_path}.')
print(f'ignore classes: {ignore_class_name}')
converted_data_info = dict(
metainfo={'DATASET': 'Waymo'}, data_list=converted_list)
# dataset metainfo
metainfo = dict()
metainfo['categories'] = {k: i for i, k in enumerate(METAINFO['classes'])}
if ignore_class_name:
for ignore_class in ignore_class_name:
metainfo['categories'][ignore_class] = -1
metainfo['dataset'] = 'waymo'
metainfo['version'] = '1.2'
metainfo['info_version'] = '1.1'
converted_data_info = dict(metainfo=metainfo, data_list=converted_list)
mmengine.dump(converted_data_info, out_path, 'pkl')
......@@ -1073,4 +1131,4 @@ if __name__ == '__main__':
if args.out_dir is None:
args.out_dir = args.root_dir
update_pkl_infos(
dataset=args.dataset, out_dir=args.out_dir, pkl_path=args.pkl)
dataset=args.dataset, out_dir=args.out_dir, pkl_path=args.pkl_path)
tools/dataset_converters/waymo_converter.py
View file @ d7067e44
......@@ -12,7 +12,6 @@ except ImportError:
from glob import glob
from os.path import join
import mmcv
import mmengine
import numpy as np
import tensorflow as tf
......@@ -70,10 +69,7 @@ class Waymo2KITTI(object):
'_SIDE_LEFT',
'_SIDE_RIGHT',
]
self.lidar_list = [
'_FRONT', '_FRONT_RIGHT', '_FRONT_LEFT', '_SIDE_RIGHT',
'_SIDE_LEFT'
]
self.lidar_list = ['TOP', 'FRONT', 'SIDE_LEFT', 'SIDE_RIGHT', 'REAR']
self.type_list = [
'UNKNOWN', 'VEHICLE', 'PEDESTRIAN', 'SIGN', 'CYCLIST'
]
......@@ -136,6 +132,8 @@ class Waymo2KITTI(object):
self.save_image(frame, file_idx, frame_idx)
self.save_calib(frame, file_idx, frame_idx)
if 'testing_3d_camera_only_detection' not in self.load_dir:
# the camera only split doesn't contain lidar points.
self.save_lidar(frame, file_idx, frame_idx)
self.save_pose(frame, file_idx, frame_idx)
self.save_timestamp(frame, file_idx, frame_idx)
......@@ -162,8 +160,8 @@ class Waymo2KITTI(object):
img_path = f'{self.image_save_dir}{str(img.name - 1)}/' + \
f'{self.prefix}{str(file_idx).zfill(3)}' + \
f'{str(frame_idx).zfill(3)}.jpg'
img = mmcv.imfrombytes(img.image)
mmcv.imwrite(img, img_path)
with open(img_path, 'wb') as fp:
fp.write(img.image)
def save_calib(self, frame, file_idx, frame_idx):
"""Parse and save the calibration data.
......@@ -442,7 +440,6 @@ class Waymo2KITTI(object):
dir_list1 = [
self.label_all_save_dir,
self.calib_save_dir,
self.point_cloud_save_dir,
self.pose_save_dir,
self.timestamp_save_dir,
]
......@@ -452,10 +449,12 @@ class Waymo2KITTI(object):
dir_list2.append(self.cam_sync_label_save_dir)
else:
dir_list1 = [
self.calib_save_dir, self.point_cloud_save_dir,
self.pose_save_dir, self.timestamp_save_dir
self.calib_save_dir, self.pose_save_dir,
self.timestamp_save_dir
]
dir_list2 = [self.image_save_dir]
if 'testing_3d_camera_only_detection' not in self.load_dir:
dir_list1.append(self.point_cloud_save_dir)
for d in dir_list1:
mmengine.mkdir_or_exist(d)
for d in dir_list2:
......
tools/misc/browse_dataset.py
View file @ d7067e44
......@@ -71,7 +71,7 @@ def build_data_cfg(config_path, aug, cfg_options):
if aug:
show_pipeline = cfg.train_pipeline
else:
show_pipeline = cfg.eval_pipeline
show_pipeline = cfg.test_pipeline
for i in range(len(cfg.train_pipeline)):
if cfg.train_pipeline[i]['type'] == 'LoadAnnotations3D':
show_pipeline.insert(i, cfg.train_pipeline[i])
......@@ -117,13 +117,20 @@ def main():
progress_bar = ProgressBar(len(dataset))
for item in dataset:
for i, item in enumerate(dataset):
# the 3D Boxes in input could be in any of three coordinates
data_input = item['inputs']
data_sample = item['data_samples'].numpy()
out_file = osp.join(
args.output_dir) if args.output_dir is not None else None
args.output_dir,
f'{i}.jpg') if args.output_dir is not None else None
# o3d_save_path is valid when args.not_show is False
o3d_save_path = osp.join(args.output_dir, f'pc_{i}.png') if (
args.output_dir is not None
and vis_task in ['lidar_det', 'lidar_seg', 'multi-modality_det']
and not args.not_show) else None
visualizer.add_datasample(
'3d visualzier',
......@@ -132,6 +139,7 @@ def main():
show=not args.not_show,
wait_time=args.show_interval,
out_file=out_file,
o3d_save_path=o3d_save_path,
vis_task=vis_task)
progress_bar.update()
......
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