Skip to content

GitLab

Unverified Commit 87b05bae authored by xiliu8006's avatar xiliu8006 Committed by GitHub
Browse files

Fix miss text (#278) 

* fixed the bug about miss text files on kitti testing

* add bbox2result_kitti unit test

* add bbox2result_kitti unit test

* add exist_submission_file unit test

* deleted debug code and convert{} to dict()

* add _get_kitti_dataset_config()

* delete print
parent 0a7fb9c7
Show whitespace changes
Inline Side-by-side
Showing with 181 additions and 285 deletions
mmdet3d/datasets/kitti_dataset.py
View file @ 87b05bae
...@@ -387,15 +387,7 @@ class KittiDataset(Custom3DDataset): ...@@ -387,15 +387,7 @@ class KittiDataset(Custom3DDataset):
info = self.data_infos[idx] info = self.data_infos[idx]
sample_idx = info['image']['image_idx'] sample_idx = info['image']['image_idx']
image_shape = info['image']['image_shape'][:2] image_shape = info['image']['image_shape'][:2]
box_dict = self.convert_valid_bboxes(pred_dicts, info) box_dict = self.convert_valid_bboxes(pred_dicts, info)
if len(box_dict['bbox']) > 0:
box_2d_preds = box_dict['bbox']
box_preds = box_dict['box3d_camera']
scores = box_dict['scores']
box_preds_lidar = box_dict['box3d_lidar']
label_preds = box_dict['label_preds']
anno = { anno = {
'name': [], 'name': [],
'truncated': [], 'truncated': [],
...@@ -407,6 +399,12 @@ class KittiDataset(Custom3DDataset): ...@@ -407,6 +399,12 @@ class KittiDataset(Custom3DDataset):
'rotation_y': [], 'rotation_y': [],
'score': [] 'score': []
} }
if len(box_dict['bbox']) > 0:
box_2d_preds = box_dict['bbox']
box_preds = box_dict['box3d_camera']
scores = box_dict['scores']
box_preds_lidar = box_dict['box3d_lidar']
label_preds = box_dict['label_preds']
for box, box_lidar, bbox, score, label in zip( for box, box_lidar, bbox, score, label in zip(
box_preds, box_preds_lidar, box_2d_preds, scores, box_preds, box_preds_lidar, box_2d_preds, scores,
...@@ -426,6 +424,19 @@ class KittiDataset(Custom3DDataset): ...@@ -426,6 +424,19 @@ class KittiDataset(Custom3DDataset):
anno = {k: np.stack(v) for k, v in anno.items()} anno = {k: np.stack(v) for k, v in anno.items()}
annos.append(anno) annos.append(anno)
else:
anno = {
'name': np.array([]),
'truncated': np.array([]),
'occluded': np.array([]),
'alpha': np.array([]),
'bbox': np.zeros([0, 4]),
'dimensions': np.zeros([0, 3]),
'location': np.zeros([0, 3]),
'rotation_y': np.array([]),
'score': np.array([]),
}
annos.append(anno)
if submission_prefix is not None: if submission_prefix is not None:
curr_file = f'{submission_prefix}/{sample_idx:06d}.txt' curr_file = f'{submission_prefix}/{sample_idx:06d}.txt'
...@@ -438,27 +449,15 @@ class KittiDataset(Custom3DDataset): ...@@ -438,27 +449,15 @@ class KittiDataset(Custom3DDataset):
print( print(
'{} -1 -1 {:.4f} {:.4f} {:.4f} {:.4f} ' '{} -1 -1 {:.4f} {:.4f} {:.4f} {:.4f} '
'{:.4f} {:.4f} {:.4f} ' '{:.4f} {:.4f} {:.4f} '
'{:.4f} {:.4f} {:.4f} {:.4f} {:.4f} {:.4f}'. '{:.4f} {:.4f} {:.4f} {:.4f} {:.4f} {:.4f}'.format(
format(anno['name'][idx], anno['alpha'][idx], anno['name'][idx], anno['alpha'][idx],
bbox[idx][0], bbox[idx][1], bbox[idx][0], bbox[idx][1], bbox[idx][2],
bbox[idx][2], bbox[idx][3], bbox[idx][3], dims[idx][1], dims[idx][2],
dims[idx][1], dims[idx][2],
dims[idx][0], loc[idx][0], loc[idx][1], dims[idx][0], loc[idx][0], loc[idx][1],
loc[idx][2], anno['rotation_y'][idx], loc[idx][2], anno['rotation_y'][idx],
anno['score'][idx]), anno['score'][idx]),
file=f) file=f)
else:
annos.append({
'name': np.array([]),
'truncated': np.array([]),
'occluded': np.array([]),
'alpha': np.array([]),
'bbox': np.zeros([0, 4]),
'dimensions': np.zeros([0, 3]),
'location': np.zeros([0, 3]),
'rotation_y': np.array([]),
'score': np.array([]),
})
annos[-1]['sample_idx'] = np.array( annos[-1]['sample_idx'] = np.array(
[sample_idx] * len(annos[-1]['score']), dtype=np.int64) [sample_idx] * len(annos[-1]['score']), dtype=np.int64)
......
tests/test_dataset/test_kitti_dataset.py
View file @ 87b05bae
import numpy as np import numpy as np
import os
import pytest import pytest
import tempfile
import torch import torch
from mmdet3d.core.bbox import LiDARInstance3DBoxes from mmdet3d.core.bbox import LiDARInstance3DBoxes
from mmdet3d.datasets import KittiDataset from mmdet3d.datasets import KittiDataset
def test_getitem(): def _generate_kitti_dataset_config():
np.random.seed(0)
data_root = 'tests/data/kitti' data_root = 'tests/data/kitti'
ann_file = 'tests/data/kitti/kitti_infos_train.pkl' ann_file = 'tests/data/kitti/kitti_infos_train.pkl'
classes = ['Pedestrian', 'Cyclist', 'Car'] classes = ['Pedestrian', 'Cyclist', 'Car']
pts_prefix = 'velodyne_reduced' pts_prefix = 'velodyne_reduced'
pipeline = [{ pipeline = [
'type': 'LoadPointsFromFile', dict(
'coord_type': 'LIDAR', type='LoadPointsFromFile',
'load_dim': 4, coord_type='LIDAR',
'use_dim': 4, load_dim=4,
'file_client_args': { use_dim=4,
'backend': 'disk' file_client_args=dict(backend='disk')),
} dict(
}, { type='MultiScaleFlipAug3D',
'type': 'LoadAnnotations3D', img_scale=(1333, 800),
'with_bbox_3d': True, pts_scale_ratio=1,
'with_label_3d': True, flip=False,
'file_client_args': { transforms=[
'backend': 'disk' dict(
} type='GlobalRotScaleTrans',
}, { rot_range=[0, 0],
'type': 'ObjectSample', scale_ratio_range=[1.0, 1.0],
'db_sampler': { translation_std=[0, 0, 0]),
'data_root': 'tests/data/kitti/', dict(type='RandomFlip3D'),
'info_path': 'tests/data/kitti/kitti_dbinfos_train.pkl', dict(
'rate': 1.0, type='PointsRangeFilter',
'prepare': { point_cloud_range=[0, -40, -3, 70.4, 40, 1]),
'filter_by_difficulty': [-1], dict(
'filter_by_min_points': { type='DefaultFormatBundle3D',
'Pedestrian': 10 class_names=['Pedestrian', 'Cyclist', 'Car'],
} with_label=False),
}, dict(type='Collect3D', keys=['points'])
'classes': ['Pedestrian', 'Cyclist', 'Car'], ])
'sample_groups': { ]
'Pedestrian': 6 modality = dict(use_lidar=True, use_camera=False)
}
}
}, {
'type': 'ObjectNoise',
'num_try': 100,
'translation_std': [1.0, 1.0, 0.5],
'global_rot_range': [0.0, 0.0],
'rot_range': [-0.78539816, 0.78539816]
}, {
'type': 'RandomFlip3D',
'flip_ratio_bev_horizontal': 0.5
}, {
'type': 'GlobalRotScaleTrans',
'rot_range': [-0.78539816, 0.78539816],
'scale_ratio_range': [0.95, 1.05]
}, {
'type': 'PointsRangeFilter',
'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
}, {
'type': 'ObjectRangeFilter',
'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
}, {
'type': 'PointShuffle'
}, {
'type': 'DefaultFormatBundle3D',
'class_names': ['Pedestrian', 'Cyclist', 'Car']
}, {
'type': 'Collect3D',
'keys': ['points', 'gt_bboxes_3d', 'gt_labels_3d']
}]
modality = {'use_lidar': True, 'use_camera': False}
split = 'training' split = 'training'
return data_root, ann_file, classes, pts_prefix, pipeline, modality, split
def test_getitem():
np.random.seed(0)
data_root, ann_file, classes, pts_prefix,\
pipeline, modality, split = _generate_kitti_dataset_config()
pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
file_client_args=dict(backend='disk')),
dict(
type='LoadAnnotations3D',
with_bbox_3d=True,
with_label_3d=True,
file_client_args=dict(backend='disk')),
dict(
type='ObjectSample',
db_sampler=dict(
data_root='tests/data/kitti/',
info_path='tests/data/kitti/kitti_dbinfos_train.pkl',
rate=1.0,
prepare=dict(
filter_by_difficulty=[-1],
filter_by_min_points=dict(Pedestrian=10)),
classes=['Pedestrian', 'Cyclist', 'Car'],
sample_groups=dict(Pedestrian=6))),
dict(
type='ObjectNoise',
num_try=100,
translation_std=[1.0, 1.0, 0.5],
global_rot_range=[0.0, 0.0],
rot_range=[-0.78539816, 0.78539816]),
dict(type='RandomFlip3D', flip_ratio_bev_horizontal=0.5),
dict(
type='GlobalRotScaleTrans',
rot_range=[-0.78539816, 0.78539816],
scale_ratio_range=[0.95, 1.05]),
dict(
type='PointsRangeFilter',
point_cloud_range=[0, -40, -3, 70.4, 40, 1]),
dict(
type='ObjectRangeFilter',
point_cloud_range=[0, -40, -3, 70.4, 40, 1]),
dict(type='PointShuffle'),
dict(
type='DefaultFormatBundle3D',
class_names=['Pedestrian', 'Cyclist', 'Car']),
dict(
type='Collect3D', keys=['points', 'gt_bboxes_3d', 'gt_labels_3d'])
]
self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline, self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
classes, modality) classes, modality)
data = self[0] data = self[0]
...@@ -92,56 +116,10 @@ def test_getitem(): ...@@ -92,56 +116,10 @@ def test_getitem():
def test_evaluate(): def test_evaluate():
if not torch.cuda.is_available(): if not torch.cuda.is_available():
pytest.skip('test requires GPU and torch+cuda') pytest.skip('test requires GPU and torch+cuda')
data_root = 'tests/data/kitti' data_root, ann_file, classes, pts_prefix,\
ann_file = 'tests/data/kitti/kitti_infos_train.pkl' pipeline, modality, split = _generate_kitti_dataset_config()
classes = ['Pedestrian', 'Cyclist', 'Car'] self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
pts_prefix = 'velodyne_reduced' classes, modality)
pipeline = [{
'type': 'LoadPointsFromFile',
'coord_type': 'LIDAR',
'load_dim': 4,
'use_dim': 4,
'file_client_args': {
'backend': 'disk'
}
}, {
'type':
'MultiScaleFlipAug3D',
'img_scale': (1333, 800),
'pts_scale_ratio':
1,
'flip':
False,
'transforms': [{
'type': 'GlobalRotScaleTrans',
'rot_range': [0, 0],
'scale_ratio_range': [1.0, 1.0],
'translation_std': [0, 0, 0]
}, {
'type': 'RandomFlip3D'
}, {
'type': 'PointsRangeFilter',
'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
}, {
'type': 'DefaultFormatBundle3D',
'class_names': ['Pedestrian', 'Cyclist', 'Car'],
'with_label': False
}, {
'type': 'Collect3D',
'keys': ['points']
}]
}]
modality = {'use_lidar': True, 'use_camera': False}
split = 'training'
self = KittiDataset(
data_root,
ann_file,
split,
pts_prefix,
pipeline,
classes,
modality,
)
boxes_3d = LiDARInstance3DBoxes( boxes_3d = LiDARInstance3DBoxes(
torch.tensor( torch.tensor(
[[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]])) [[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
...@@ -164,42 +142,8 @@ def test_show(): ...@@ -164,42 +142,8 @@ def test_show():
from mmdet3d.core.bbox import LiDARInstance3DBoxes from mmdet3d.core.bbox import LiDARInstance3DBoxes
temp_dir = tempfile.mkdtemp() temp_dir = tempfile.mkdtemp()
data_root = 'tests/data/kitti' data_root, ann_file, classes, pts_prefix,\
ann_file = 'tests/data/kitti/kitti_infos_train.pkl' pipeline, modality, split = _generate_kitti_dataset_config()
modality = {'use_lidar': True, 'use_camera': False}
split = 'training'
file_client_args = dict(backend='disk')
point_cloud_range = [0, -40, -3, 70.4, 40, 1]
class_names = ['Pedestrian', 'Cyclist', 'Car']
pipeline = [
dict(
type='LoadPointsFromFile',
coord_type='LIDAR',
load_dim=4,
use_dim=4,
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'])
])
]
kitti_dataset = KittiDataset( kitti_dataset = KittiDataset(
data_root, ann_file, split=split, modality=modality, pipeline=pipeline) data_root, ann_file, split=split, modality=modality, pipeline=pipeline)
boxes_3d = LiDARInstance3DBoxes( boxes_3d = LiDARInstance3DBoxes(
...@@ -224,56 +168,10 @@ def test_show(): ...@@ -224,56 +168,10 @@ def test_show():
def test_format_results(): def test_format_results():
from mmdet3d.core.bbox import LiDARInstance3DBoxes from mmdet3d.core.bbox import LiDARInstance3DBoxes
data_root = 'tests/data/kitti' data_root, ann_file, classes, pts_prefix,\
ann_file = 'tests/data/kitti/kitti_infos_train.pkl' pipeline, modality, split = _generate_kitti_dataset_config()
classes = ['Pedestrian', 'Cyclist', 'Car'] self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
pts_prefix = 'velodyne_reduced' classes, modality)
pipeline = [{
'type': 'LoadPointsFromFile',
'coord_type': 'LIDAR',
'load_dim': 4,
'use_dim': 4,
'file_client_args': {
'backend': 'disk'
}
}, {
'type':
'MultiScaleFlipAug3D',
'img_scale': (1333, 800),
'pts_scale_ratio':
1,
'flip':
False,
'transforms': [{
'type': 'GlobalRotScaleTrans',
'rot_range': [0, 0],
'scale_ratio_range': [1.0, 1.0],
'translation_std': [0, 0, 0]
}, {
'type': 'RandomFlip3D'
}, {
'type': 'PointsRangeFilter',
'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
}, {
'type': 'DefaultFormatBundle3D',
'class_names': ['Pedestrian', 'Cyclist', 'Car'],
'with_label': False
}, {
'type': 'Collect3D',
'keys': ['points']
}]
}]
modality = {'use_lidar': True, 'use_camera': False}
split = 'training'
self = KittiDataset(
data_root,
ann_file,
split,
pts_prefix,
pipeline,
classes,
modality,
)
boxes_3d = LiDARInstance3DBoxes( boxes_3d = LiDARInstance3DBoxes(
torch.tensor( torch.tensor(
[[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]])) [[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
...@@ -306,57 +204,56 @@ def test_format_results(): ...@@ -306,57 +204,56 @@ def test_format_results():
assert np.allclose(result_files[0]['sample_idx'], expected_sample_idx) assert np.allclose(result_files[0]['sample_idx'], expected_sample_idx)
def test_bbox2result_kitti():
data_root, ann_file, classes, pts_prefix,\
pipeline, modality, split = _generate_kitti_dataset_config()
self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
classes, modality)
boxes_3d = LiDARInstance3DBoxes(
torch.tensor(
[[8.7314, -1.8559, -1.5997, 0.4800, 1.2000, 1.8900, 0.0100]]))
labels_3d = torch.tensor([
0,
])
scores_3d = torch.tensor([0.5])
result = dict(boxes_3d=boxes_3d, labels_3d=labels_3d, scores_3d=scores_3d)
results = [result]
temp_kitti_result_dir = tempfile.mkdtemp()
det_annos = self.bbox2result_kitti(
results, classes, submission_prefix=temp_kitti_result_dir)
expected_file_path = os.path.join(temp_kitti_result_dir, '000000.txt')
expected_name = np.array(['Pedestrian'])
expected_dimensions = np.array([1.2000, 1.8900, 0.4800])
expected_rotation_y = np.array([0.0100]) - np.pi
expected_score = np.array([0.5])
assert np.all(det_annos[0]['name'] == expected_name)
assert np.allclose(det_annos[0]['rotation_y'], expected_rotation_y)
assert np.allclose(det_annos[0]['score'], expected_score)
assert np.allclose(det_annos[0]['dimensions'], expected_dimensions)
assert os.path.exists(expected_file_path)
os.remove(expected_file_path)
os.removedirs(temp_kitti_result_dir)
temp_kitti_result_dir = tempfile.mkdtemp()
boxes_3d = LiDARInstance3DBoxes(torch.tensor([]))
labels_3d = torch.tensor([])
scores_3d = torch.tensor([])
empty_result = dict(
boxes_3d=boxes_3d, labels_3d=labels_3d, scores_3d=scores_3d)
results = [empty_result]
det_annos = self.bbox2result_kitti(
results, classes, submission_prefix=temp_kitti_result_dir)
expected_file_path = os.path.join(temp_kitti_result_dir, '000000.txt')
assert os.path.exists(expected_file_path)
os.remove(expected_file_path)
os.removedirs(temp_kitti_result_dir)
def test_bbox2result_kitti2d(): def test_bbox2result_kitti2d():
data_root = 'tests/data/kitti' data_root, ann_file, classes, pts_prefix,\
ann_file = 'tests/data/kitti/kitti_infos_train.pkl' pipeline, modality, split = _generate_kitti_dataset_config()
classes = ['Pedestrian', 'Cyclist', 'Car'] self = KittiDataset(data_root, ann_file, split, pts_prefix, pipeline,
pts_prefix = 'velodyne_reduced' classes, modality)
pipeline = [{
'type': 'LoadPointsFromFile',
'coord_type': 'LIDAR',
'load_dim': 4,
'use_dim': 4,
'file_client_args': {
'backend': 'disk'
}
}, {
'type':
'MultiScaleFlipAug3D',
'img_scale': (1333, 800),
'pts_scale_ratio':
1,
'flip':
False,
'transforms': [{
'type': 'GlobalRotScaleTrans',
'rot_range': [-0.1, 0.1],
'scale_ratio_range': [0.9, 1.1],
'translation_std': [0, 0, 0]
}, {
'type': 'RandomFlip3D'
}, {
'type': 'PointsRangeFilter',
'point_cloud_range': [0, -40, -3, 70.4, 40, 1]
}, {
'type': 'DefaultFormatBundle3D',
'class_names': ['Pedestrian', 'Cyclist', 'Car'],
'with_label': False
}, {
'type': 'Collect3D',
'keys': ['points']
}]
}]
modality = {'use_lidar': True, 'use_camera': False}
split = 'training'
self = KittiDataset(
data_root,
ann_file,
split,
pts_prefix,
pipeline,
classes,
modality,
)
bboxes = np.array([[[46.1218, -4.6496, -0.9275, 0.5316, 0.5], bboxes = np.array([[[46.1218, -4.6496, -0.9275, 0.5316, 0.5],
[33.3189, 0.1981, 0.3136, 0.5656, 0.5]], [33.3189, 0.1981, 0.3136, 0.5656, 0.5]],
[[46.1366, -4.6404, -0.9510, 0.5162, 0.5], [[46.1366, -4.6404, -0.9510, 0.5162, 0.5],
......
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