File size: 4,658 Bytes
3bbb319 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
# Copyright (c) OpenMMLab. All rights reserved.
import tempfile
import torch
from mmcv import Config
from mmpose.datasets import DATASETS, build_dataloader
from mmpose.datasets.dataset_info import DatasetInfo
from mmpose.models import builder
def test_voxelpose_forward():
dataset = 'Body3DMviewDirectPanopticDataset'
dataset_class = DATASETS.get(dataset)
dataset_info = Config.fromfile(
'configs/_base_/datasets/panoptic_body3d.py').dataset_info
space_size = [8000, 8000, 2000]
space_center = [0, -500, 800]
cube_size = [20, 20, 8]
data_cfg = dict(
image_size=[960, 512],
heatmap_size=[[240, 128]],
space_size=space_size,
space_center=space_center,
cube_size=cube_size,
num_joints=15,
seq_list=['160906_band1'],
cam_list=[(0, 12), (0, 6)],
num_cameras=2,
seq_frame_interval=1,
subset='train',
need_2d_label=True,
need_camera_param=True,
root_id=2)
pipeline_heatmap = [
dict(
type='MultiItemProcess',
pipeline=[
dict(
type='BottomUpGenerateTarget', sigma=3, max_num_people=20)
]),
dict(
type='DiscardDuplicatedItems',
keys_list=[
'joints_3d', 'joints_3d_visible', 'ann_info', 'roots_3d',
'num_persons', 'sample_id'
]),
dict(
type='GenerateVoxel3DHeatmapTarget',
sigma=200.0,
joint_indices=[2]),
dict(type='RenameKeys', key_pairs=[('targets', 'input_heatmaps')]),
dict(
type='Collect',
keys=['targets_3d', 'input_heatmaps'],
meta_keys=[
'camera', 'center', 'scale', 'joints_3d', 'num_persons',
'joints_3d_visible', 'roots_3d', 'sample_id'
]),
]
model_cfg = dict(
type='DetectAndRegress',
backbone=None,
human_detector=dict(
type='VoxelCenterDetector',
image_size=[960, 512],
heatmap_size=[240, 128],
space_size=space_size,
cube_size=cube_size,
space_center=space_center,
center_net=dict(
type='V2VNet', input_channels=15, output_channels=1),
center_head=dict(
type='CuboidCenterHead',
space_size=space_size,
space_center=space_center,
cube_size=cube_size,
max_num=3,
max_pool_kernel=3),
train_cfg=dict(dist_threshold=500000000.0),
test_cfg=dict(center_threshold=0.0),
),
pose_regressor=dict(
type='VoxelSinglePose',
image_size=[960, 512],
heatmap_size=[240, 128],
sub_space_size=[2000, 2000, 2000],
sub_cube_size=[20, 20, 8],
num_joints=15,
pose_net=dict(
type='V2VNet', input_channels=15, output_channels=15),
pose_head=dict(type='CuboidPoseHead', beta=100.0),
train_cfg=None,
test_cfg=None))
model = builder.build_posenet(model_cfg)
with tempfile.TemporaryDirectory() as tmpdir:
dataset = dataset_class(
ann_file=tmpdir + '/tmp_train.pkl',
img_prefix='tests/data/panoptic_body3d/',
data_cfg=data_cfg,
pipeline=pipeline_heatmap,
dataset_info=dataset_info,
test_mode=False)
data_loader = build_dataloader(
dataset,
seed=None,
dist=False,
shuffle=False,
drop_last=False,
workers_per_gpu=1,
samples_per_gpu=1)
with torch.no_grad():
for data in data_loader:
# test forward_train
_ = model(
img=None,
img_metas=data['img_metas'].data[0],
return_loss=True,
targets_3d=data['targets_3d'],
input_heatmaps=data['input_heatmaps'])
# test forward_test
_ = model(
img=None,
img_metas=data['img_metas'].data[0],
return_loss=False,
input_heatmaps=data['input_heatmaps'])
with tempfile.TemporaryDirectory() as tmpdir:
model.show_result(
img=None,
img_metas=data['img_metas'].data[0],
input_heatmaps=data['input_heatmaps'],
dataset_info=DatasetInfo(dataset_info),
out_dir=tmpdir,
visualize_2d=True)
|