MinkowskiEngine语义分割
MinkowskiEngine语义分割
要运行示例，请安装Open3D与PIP安装open3d-python。
cd /path/to/MinkowskiEngine
python -m examples.indoor
细分酒店房间
运行示例时，将看到一个旅馆房间和房间的语义分割。运行示例时，以交互方式旋转可视化效果。
首先，加载数据并体素化（量化）数据。调用MinkowskiEngine.utils.sparse_quantize进行体素化。
pcd = o3d.read_point_cloud(file_name)
coords = np.array(pcd.points)
feats = np.array(pcd.colors)
quantized_coords = np.floor(coords / voxel_size)
inds = ME.utils.sparse_quantize(quantized_coords)
准备体素化的坐标和特征后，应用MinkowskiEngine.SparseTensor将其包裹起来。此前，通过调用MinkowskiEngine.utils.sparse_collate来创建批处理。此函数采用一组坐标和特征并将其连接起来。还将批处理索引附加到坐标。最后，通过从颜色中减去0.5，对特征进行伪归一化。
Create a batch, this process is done in a data loader during training in parallel.
batch = [load_file(config.file_name, 0.02)]
coordinates_, featrues_, pcds = list(zip(*batch))
coordinates, features = ME.utils.sparse_collate(coordinates_, featrues_)
Normalize features and create a sparse tensor
sinput = ME.SparseTensor(features - 0.5, coords=coordinates).to(device)
最后，将稀疏张量前馈到网络中并获得预测。
soutput = model(sinput)
_, pred = soutput.F.max(1)
经过一些后处理。可以为标签着色，并排可视化输入和预测。
运行示例后，权重会自动下载，并且权重目前是Scannet 3D分段基准测试中排名最高的算法。
有关更多详细信息，请参阅完整的室内细分示例。
import os
import argparse
import numpy as np
from urllib.request import urlretrieve
try:
import open3d as o3d
except ImportError:
raise ImportError(‘Please install open3d with pip install open3d.’)
import torch
import MinkowskiEngine as ME
from examples.minkunet import MinkUNet34C
from examples.common import Timer
# Check if the weights and file exist and download
if not os.path.isfile('weights.pth'):
print('Downloading weights and a room ply file...')
urlretrieve("http://cvgl.stanford.edu/data2/minkowskiengine/weights.pth",
'weights.pth')
urlretrieve("http://cvgl.stanford.edu/data2/minkowskiengine/1.ply", '1.ply')
parser = argparse.ArgumentParser()
parser.add_argument('--file_name', type=str, default='1.ply')
parser.add_argument('--weights', type=str, default='weights.pth')
parser.add_argument('--use_cpu', action='store_true')
CLASS_LABELS = ('wall', 'floor', 'cabinet', 'bed', 'chair', 'sofa', 'table',
'door', 'window', 'bookshelf', 'picture', 'counter', 'desk',
'curtain', 'refrigerator', 'shower curtain', 'toilet', 'sink',
'bathtub', 'otherfurniture')
VALID_CLASS_IDS = [
1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 16, 24, 28, 33, 34, 36, 39
]
SCANNET_COLOR_MAP = {
0: (0., 0., 0.),
1: (174., 199., 232.),
2: (152., 223., 138.),
3: (31., 119., 180.),
4: (255., 187., 120.),
5: (188., 189., 34.),
6: (140., 86., 75.),
7: (255., 152., 150.),
8: (214., 39., 40.),
9: (197., 176., 213.),
10: (148., 103., 189.),
11: (196., 156., 148.),
12: (23., 190., 207.),
14: (247., 182., 210.),
15: (66., 188., 102.),
16: (219., 219., 141.),
17: (140., 57., 197.),
18: (202., 185., 52.),
19: (51., 176., 203.),
20: (200., 54., 131.),
21: (92., 193., 61.),
22: (78., 71., 183.),
23: (172., 114., 82.),
24: (255., 127., 14.),
25: (91., 163., 138.),
26: (153., 98., 156.),
27: (140., 153., 101.),
28: (158., 218., 229.),
29: (100., 125., 154.),
30: (178., 127., 135.),
32: (146., 111., 194.),
33: (44., 160., 44.),
34: (112., 128., 144.),
35: (96., 207., 209.),
36: (227., 119., 194.),
37: (213., 92., 176.),
38: (94., 106., 211.),
39: (82., 84., 163.),
40: (100., 85., 144.),
}
def load_file(file_name):
pcd = o3d.io.read_point_cloud(file_name)
coords = np.array(pcd.points)
colors = np.array(pcd.colors)
return coords, colors, pcd
if __name__ == '__main__':
config = parser.parse_args()
device = torch.device('cuda' if (
torch.cuda.is_available() and not config.use_cpu) else 'cpu')
print(f"Using {device}")
# Define a model and load the weights
model = MinkUNet34C(3, 20).to(device)
model_dict = torch.load(config.weights)
model.load_state_dict(model_dict)
model.eval()
coords, colors, pcd = load_file(config.file_name)
# Measure time
with torch.no_grad():
voxel_size = 0.02
# Feed-forward pass and get the prediction
in_field = ME.TensorField(
features=torch.from_numpy(colors).float(),
coordinates=ME.utils.batched_coordinates([coords / voxel_size], dtype=torch.float32),
quantization_mode=ME.SparseTensorQuantizationMode.UNWEIGHTED_AVERAGE,
minkowski_algorithm=ME.MinkowskiAlgorithm.SPEED_OPTIMIZED,
device=device,
)
# Convert to a sparse tensor
sinput = in_field.sparse()
# Output sparse tensor
soutput = model(sinput)
# get the prediction on the input tensor field
out_field = soutput.slice(in_field)
logits = out_field.F
_, pred = logits.max(1)
pred = pred.cpu().numpy()
# Create a point cloud file
pred_pcd = o3d.geometry.PointCloud()
# Map color
colors = np.array([SCANNET_COLOR_MAP[VALID_CLASS_IDS[l]] for l in pred])
pred_pcd.points = o3d.utility.Vector3dVector(coords)
pred_pcd.colors = o3d.utility.Vector3dVector(colors / 255)
pred_pcd.estimate_normals()
# Move the original point cloud
pcd.points = o3d.utility.Vector3dVector(
np.array(pcd.points) + np.array([0, 5, 0]))
# Visualize the input point cloud and the prediction
o3d.visualization.draw_geometries([pcd, pred_pcd])