Skip to content

GitLab

Commit fe4a2e61 authored by yan.yan's avatar yan.yan
Browse files

v2.1.12: add pc_voxel_id in voxel gen, fix bug

parent 3bda1b64
Hide whitespace changes
Inline Side-by-side
Showing with 254 additions and 157 deletions
CHANGELOG.md
View file @ fe4a2e61
# Changelog
## [2.1.12] - 2021-11-23
### Added
- Add a method for voxel generator to get pc_voxel_id, which is usually used in semantic segmentation
### Fixed
- Fix a bug in cuda voxel generater when max_voxels is smaller than real number of voxels
## [2.1.11] - 2021-11-22
### Fixed
- Fixed a bug Volta kernels (TITAN V, Tesla V100), backward weight kernels use f16 as accumulator. we should use f32.
......
docs/USAGE.md
View file @ fe4a2e61
......@@ -82,6 +82,8 @@ class ExampleNet(nn.Module):
Inverse sparse convolution means "inv" of sparse convolution. the output of inverse convolution contains same indices as input of sparse convolution.
**WARNING** ```SparseInverseConv``` isn't equivalent to ```SparseConvTranspose```. SparseConvTranspose is equivalent to ```ConvTranspose``` in pytorch, but SparseInverseConv isn't.
Inverse convolution usually used in semantic segmentation.
```Python
......@@ -112,8 +114,10 @@ voxel generator in spconv generate indices in **ZYX** order, the params format a
generated indices don't include batch axis, you need to add it by yourself.
see examples/voxel_gen.py for examples.
```Python
from spconv.pytorch.utils import PointToVoxel
from spconv.pytorch.utils import PointToVoxel, gather_features_by_pc_voxel_id
# this generator generate ZYX indices.
gen = PointToVoxel(
vsize_xyz=[0.1, 0.1, 0.1],
......@@ -123,5 +127,14 @@ gen = PointToVoxel(
max_num_points_per_voxel=5)
pc = np.random.uniform(-10, 10, size=[1000, 3])
pc_th = torch.from_numpy(pc)
voxels, coords, num_points_per_voxel = gen(pc_th)
voxels, coords, num_points_per_voxel = gen(pc_th, empty_mean=True)
```
If you want to get label for every point of your pc, you need to use another function to get pc_voxel_id and gather features from sematic segmentation result:
```Python
voxels, coords, num_points_per_voxel, pc_voxel_id = gen.generate_voxel_with_id(pc_th, empty_mean=True)
seg_features = YourSegNet(...)
# if voxel id is invalid (point out of range, or no space left in a voxel)
# features will be zero.
point_features = gather_features_by_pc_voxel_id(seg_features, pc_voxel_id)
```
\ No newline at end of file
example/voxel_gen.py
View file @ fe4a2e61
......@@ -16,9 +16,94 @@ import numpy as np
from cumm import tensorview as tv
from spconv.utils import Point2VoxelCPU3d
from spconv.pytorch.utils import PointToVoxel
from spconv.pytorch.utils import PointToVoxel, gather_features_by_pc_voxel_id
import torch
def main_pytorch_voxel_gen():
np.random.seed(50051)
# voxel gen source code: spconv/csrc/sparse/pointops.py
gen = PointToVoxel(vsize_xyz=[0.1, 0.1, 0.1],
coors_range_xyz=[-80, -80, -6, 80, 80, 6],
num_point_features=3,
max_num_voxels=5000,
max_num_points_per_voxel=5)
pc = np.random.uniform(-4, 4, size=[1000, 3])
pc_th = torch.from_numpy(pc)
voxels_th, indices_th, num_p_in_vx_th = gen(pc_th)
voxels_np = voxels_th.numpy()
indices_np = indices_th.numpy()
num_p_in_vx_np = num_p_in_vx_th.numpy()
print(f"------Raw Voxels {voxels_np.shape[0]}-------")
print(voxels_np[0])
# run voxel gen and FILL MEAN VALUE to voxel remain
voxels_th, indices_th, num_p_in_vx_th = gen(pc_th, empty_mean=True)
voxels_np = voxels_th.numpy()
indices_np = indices_th.numpy()
num_p_in_vx_np = num_p_in_vx_th.numpy()
print("------Voxels with mean filled-------")
print(voxels_np[0])
voxels_th, indices_th, num_p_in_vx_th, pc_voxel_id = gen.generate_voxel_with_id(pc_th, empty_mean=True)
print("------Voxel ids for every point-------")
print(pc_voxel_id[:10])
def main_pytorch_voxel_gen_cuda():
np.random.seed(50051)
# voxel gen source code: spconv/csrc/sparse/pointops.py
pc = np.random.uniform(-2, 8, size=[1000, 3]).astype(np.float32)
for device in [torch.device("cuda:0"), torch.device("cpu:0")]:
gen = PointToVoxel(vsize_xyz=[0.25, 0.25, 0.25],
coors_range_xyz=[0, 0, 0, 10, 10, 10],
num_point_features=3,
max_num_voxels=5000,
max_num_points_per_voxel=5,
device=device)
pc_th = torch.from_numpy(pc).to(device)
voxels_th, indices_th, num_p_in_vx_th = gen(pc_th)
voxels_np = voxels_th.cpu().numpy()
indices_np = indices_th.cpu().numpy()
num_p_in_vx_np = num_p_in_vx_th.cpu().numpy()
print(f"------{device} Raw Voxels {voxels_np.shape[0]}-------")
print(voxels_np[0])
# run voxel gen and FILL MEAN VALUE to voxel remain
voxels_tv, indices_tv, num_p_in_vx_tv = gen(pc_th, empty_mean=True)
voxels_np = voxels_tv.cpu().numpy()
indices_np = indices_tv.cpu().numpy()
num_p_in_vx_np = num_p_in_vx_tv.cpu().numpy()
print(f"------{device} Voxels with mean filled-------")
print(voxels_np[0])
voxels_th, indices_th, num_p_in_vx_th, pc_voxel_id = gen.generate_voxel_with_id(pc_th, empty_mean=True)
print(f"------{device} Reconstruct Indices From Voxel ids for every point-------")
indices_th_float = indices_th.float()
# we gather indices by voxel_id to see correctness of voxel id.
indices_th_voxel_id = gather_features_by_pc_voxel_id(indices_th_float, pc_voxel_id)
indices_th_voxel_id_np = indices_th_voxel_id[:10].cpu().numpy()
print(pc[:10])
print(indices_th_voxel_id_np[:, ::-1] / 4)
def main_gather_features_by_pc_voxel_id():
np.random.seed(50051)
# voxel gen source code: spconv/csrc/sparse/pointops.py
device = torch.device("cuda:0")
gen = PointToVoxel(vsize_xyz=[0.25, 0.25, 0.25],
coors_range_xyz=[-10, -10, -10, 10, 10, 10],
num_point_features=3,
max_num_voxels=2000,
max_num_points_per_voxel=5,
device=device)
pc = np.random.uniform(-8, 8, size=[5000, 3]).astype(np.float32)
pc_th = torch.from_numpy(pc).to(device)
voxels_th, indices_th, num_p_in_vx_th, pc_voxel_id = gen.generate_voxel_with_id(pc_th, empty_mean=True)
res_features_from_seg = torch.zeros((voxels_th.shape[0], 128), dtype=torch.float32, device=device)
pc_features = gather_features_by_pc_voxel_id(res_features_from_seg, pc_voxel_id)
print(pc.shape, pc_features.shape)
def main():
np.random.seed(50051)
......@@ -81,58 +166,26 @@ def main_point_with_features():
print("------Voxels with mean filled-------")
print(voxels_np[0])
def main_pytorch_voxel_gen():
def main_cuda():
np.random.seed(50051)
# voxel gen source code: spconv/csrc/sparse/pointops.py
gen = PointToVoxel(vsize_xyz=[0.1, 0.1, 0.1],
coors_range_xyz=[-80, -80, -2, 80, 80, 6],
num_point_features=3,
max_num_voxels=5000,
max_num_points_per_voxel=5)
from spconv.utils import Point2VoxelGPU3d
pc = np.random.uniform(-10, 10, size=[1000, 3])
pc_th = torch.from_numpy(pc)
voxels_th, indices_th, num_p_in_vx_th = gen(pc_th)
voxels_np = voxels_th.numpy()
indices_np = indices_th.numpy()
num_p_in_vx_np = num_p_in_vx_th.numpy()
print(f"------Raw Voxels {voxels_np.shape[0]}-------")
print(voxels_np[0])
# run voxel gen and FILL MEAN VALUE to voxel remain
voxels_tv, indices_tv, num_p_in_vx_tv = gen(pc_th, empty_mean=True)
voxels_np = voxels_tv.numpy()
indices_np = indices_tv.numpy()
num_p_in_vx_np = num_p_in_vx_tv.numpy()
print("------Voxels with mean filled-------")
print(voxels_np[0])
def main_pytorch_voxel_gen_cuda():
np.random.seed(50051)
# voxel gen source code: spconv/csrc/sparse/pointops.py
device = torch.device("cuda:0")
gen = PointToVoxel(vsize_xyz=[0.1, 0.1, 0.1],
coors_range_xyz=[-80, -80, -2, 80, 80, 6],
num_point_features=3,
max_num_voxels=5000,
max_num_points_per_voxel=5,
device=device)
gen = Point2VoxelGPU3d(vsize_xyz=[0.1, 0.1, 0.1],
coors_range_xyz=[-80, -80, -2, 80, 80, 6],
num_point_features=3,
max_num_voxels=5000,
max_num_points_per_voxel=5)
pc = np.random.uniform(-10, 10, size=[1000, 3]).astype(np.float32)
pc_th = torch.from_numpy(pc).to(device)
voxels_th, indices_th, num_p_in_vx_th = gen(pc_th)
voxels_np = voxels_th.cpu().numpy()
indices_np = indices_th.cpu().numpy()
num_p_in_vx_np = num_p_in_vx_th.cpu().numpy()
print(f"------Raw Voxels {voxels_np.shape[0]}-------")
print(voxels_np[0])
# run voxel gen and FILL MEAN VALUE to voxel remain
voxels_tv, indices_tv, num_p_in_vx_tv = gen(pc_th, empty_mean=True)
pc = np.random.uniform(-10, 10, size=[100000, 3]).astype(np.float32)
pc_tv = tv.from_numpy(pc).cuda()
# generate voxels, note that voxels_tv reference to a persistent buffer in generator,
# so we can't run it in multi-thread.
voxels_tv, indices_tv, num_p_in_vx_tv = gen.point_to_voxel_hash(pc_tv)
voxels_np = voxels_tv.cpu().numpy()
indices_np = indices_tv.cpu().numpy()
num_p_in_vx_np = num_p_in_vx_tv.cpu().numpy()
print("------Voxels with mean filled-------")
print(f"------CUDA Raw Voxels {voxels_np.shape[0]}-------")
print(voxels_np[0])
......@@ -141,4 +194,6 @@ if __name__ == "__main__":
main_point_with_features()
main_pytorch_voxel_gen()
if torch.cuda.is_available():
main_cuda()
main_pytorch_voxel_gen_cuda()
main_gather_features_by_pc_voxel_id()
spconv/core_cc/csrc/sparse/all/__init__.pyi
View file @ fe4a2e61
......@@ -291,7 +291,7 @@ class SpconvOps:
"""
...
@staticmethod
def point2voxel_cpu(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], empty_mean: bool = False, clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point2voxel_cpu(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, pc_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], empty_mean: bool = False, clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -299,6 +299,7 @@ class SpconvOps:
indices:
num_per_voxel:
densehashdata:
pc_voxel_id:
vsize:
grid_size:
grid_stride:
......@@ -308,7 +309,7 @@ class SpconvOps:
"""
...
@staticmethod
def point2voxel_cuda(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], empty_mean: bool = False, clear_voxels: bool = True, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
def point2voxel_cuda(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, pc_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], empty_mean: bool = False, clear_voxels: bool = True, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -317,6 +318,7 @@ class SpconvOps:
num_per_voxel:
hashdata:
point_indice_data:
pc_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops1d.pyi
View file @ fe4a2e61
......@@ -29,7 +29,7 @@ class Point2Voxel:
"""
...
@staticmethod
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -38,6 +38,7 @@ class Point2Voxel:
num_per_voxel:
hashdata:
point_indice_data:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops2d.pyi
View file @ fe4a2e61
......@@ -29,7 +29,7 @@ class Point2Voxel:
"""
...
@staticmethod
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -38,6 +38,7 @@ class Point2Voxel:
num_per_voxel:
hashdata:
point_indice_data:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops3d.pyi
View file @ fe4a2e61
......@@ -29,7 +29,7 @@ class Point2Voxel:
"""
...
@staticmethod
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -38,6 +38,7 @@ class Point2Voxel:
num_per_voxel:
hashdata:
point_indice_data:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops4d.pyi
View file @ fe4a2e61
......@@ -29,7 +29,7 @@ class Point2Voxel:
"""
...
@staticmethod
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_hash_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, hashdata: Tensor, point_indice_data: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True, empty_mean: bool = False, stream_int: int = 0) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -38,6 +38,7 @@ class Point2Voxel:
num_per_voxel:
hashdata:
point_indice_data:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops_cpu1d.pyi
View file @ fe4a2e61
......@@ -27,7 +27,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -35,6 +35,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......@@ -43,7 +44,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -51,6 +52,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops_cpu2d.pyi
View file @ fe4a2e61
......@@ -27,7 +27,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -35,6 +35,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......@@ -43,7 +44,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -51,6 +52,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops_cpu3d.pyi
View file @ fe4a2e61
......@@ -27,7 +27,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -35,6 +35,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......@@ -43,7 +44,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -51,6 +52,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/core_cc/csrc/sparse/all/ops_cpu4d.pyi
View file @ fe4a2e61
......@@ -27,7 +27,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -35,6 +35,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......@@ -43,7 +44,7 @@ class Point2VoxelCPU:
"""
...
@staticmethod
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
def point_to_voxel_empty_mean_static(points: Tensor, voxels: Tensor, indices: Tensor, num_per_voxel: Tensor, densehashdata: Tensor, points_voxel_id: Tensor, vsize: List[float], grid_size: List[int], grid_stride: List[int], coors_range: List[float], clear_voxels: bool = True) -> Tuple[Tensor, Tensor, Tensor]:
"""
Args:
points:
......@@ -51,6 +52,7 @@ class Point2VoxelCPU:
indices:
num_per_voxel:
densehashdata:
points_voxel_id:
vsize:
grid_size:
grid_stride:
......
spconv/csrc/sparse/all.py
View file @ fe4a2e61
......@@ -860,7 +860,7 @@ class SpconvOps(pccm.Class):
def point2voxel_cpu(self):
code = pccm.FunctionCode()
code.arg("points", "tv::Tensor")
code.arg("voxels, indices, num_per_voxel, densehashdata", "tv::Tensor")
code.arg("voxels, indices, num_per_voxel, densehashdata, pc_voxel_id", "tv::Tensor")
code.arg("vsize", f"std::vector<float>")
code.arg("grid_size, grid_stride", f"std::vector<int>")
code.arg("coors_range", f"std::vector<float>")
......@@ -890,11 +890,11 @@ class SpconvOps(pccm.Class):
}}
if (empty_mean){{
return Point2Voxel{ndim}DCPU::point_to_voxel_empty_mean_static(points, voxels, indices,
num_per_voxel, densehashdata,
num_per_voxel, densehashdata, pc_voxel_id,
vsize_, grid_size_, grid_stride_, coors_range_, clear_voxels);
}} else{{
return Point2Voxel{ndim}DCPU::point_to_voxel_static(points, voxels, indices,
num_per_voxel, densehashdata,
num_per_voxel, densehashdata, pc_voxel_id,
vsize_, grid_size_, grid_stride_, coors_range_, clear_voxels);
}}
}}
......@@ -907,7 +907,7 @@ class SpconvOps(pccm.Class):
def point2voxel_cuda(self):
code = pccm.FunctionCode()
code.arg("points", "tv::Tensor")
code.arg("voxels, indices, num_per_voxel, hashdata, point_indice_data",
code.arg("voxels, indices, num_per_voxel, hashdata, point_indice_data, pc_voxel_id",
"tv::Tensor")
code.arg("vsize", f"std::vector<float>")
code.arg("grid_size, grid_stride", f"std::vector<int>")
......@@ -940,7 +940,7 @@ class SpconvOps(pccm.Class):
coors_range_[i + {ndim}] = coors_range[i + {ndim}];
}}
return Point2Voxel{ndim}D::point_to_voxel_hash_static(points, voxels, indices,
num_per_voxel, hashdata, point_indice_data,
num_per_voxel, hashdata, point_indice_data, pc_voxel_id,
vsize_, grid_size_, grid_stride_, coors_range_, clear_voxels,
empty_mean, stream_int);
}}
......
spconv/csrc/sparse/pointops.py
View file @ fe4a2e61
......@@ -208,6 +208,7 @@ class Point2VoxelKernel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
code.arg("points_indice_data", f"const int64_t*")
code.arg("voxels", f"{self.dtype} *")
code.arg("num_per_voxel", f"int *")
code.arg("points_voxel_id", f"int64_t*")
code.arg("point_stride", f"int")
code.arg("max_points_per_voxel", f"int")
......@@ -219,14 +220,17 @@ class Point2VoxelKernel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
code.arg("grid_stride", f"tv::array<int, {self.ndim}>")
code.arg("num_points", f"int")
# TODO add backward?
code.raw(f"""
int voxel_stride0 = point_stride * max_points_per_voxel;
for (int i : tv::KernelLoopX<int>(num_points)){{
int64_t prod = points_indice_data[i];
int voxel_id = -1;
if (prod != -1){{
auto voxel_index_pair = table.lookup(prod);
if (!voxel_index_pair.empty() &&
voxel_index_pair.second < max_voxels) {{
voxel_id = voxel_index_pair.second;
int old = atomicAdd(num_per_voxel + voxel_index_pair.second, 1);
if (old < max_points_per_voxel) {{
for (int j = 0; j < point_stride; ++j) {{
......@@ -235,6 +239,7 @@ class Point2VoxelKernel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
}}
}}
}}
points_voxel_id[i] = voxel_id;
}}
""")
return code
......@@ -385,6 +390,7 @@ class Point2Voxel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
code.arg("stream_int", f"std::uintptr_t", "0")
code.raw(f"""
tv::Tensor points_voxel_id = tv::empty({{points.dim(0)}}, tv::int64, 0);
int64_t expected_hash_data_num = points.dim(0) * 2;
if (hashdata.dim(0) < expected_hash_data_num){{
hashdata = tv::zeros({{expected_hash_data_num}}, tv::custom128, 0);
......@@ -393,74 +399,18 @@ class Point2Voxel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
point_indice_data = tv::zeros({{points.dim(0)}}, tv::int64, 0);
}}
return point_to_voxel_hash_static(points, voxels, indices, num_per_voxel,
hashdata, point_indice_data, Point2VoxelCommon::tvarray2array(vsize),
hashdata, point_indice_data, points_voxel_id, Point2VoxelCommon::tvarray2array(vsize),
Point2VoxelCommon::tvarray2array(grid_size), Point2VoxelCommon::tvarray2array(grid_stride),
Point2VoxelCommon::tvarray2array(coors_range), clear_voxels, empty_mean, stream_int);
""")
return code.ret("std::tuple<tv::Tensor, tv::Tensor, tv::Tensor>")
code.raw(f"""
TV_ASSERT_INVALID_ARG(points.ndim() == 2 && points.dim(1) >= {self.ndim}, "error");
using V = int64_t;
using KeyType = int64_t;
constexpr KeyType kEmptyKey = std::numeric_limits<KeyType>::max();
if (clear_voxels){{
voxels.zero_();
}}
using table_t =
tv::hash::LinearHashTable<KeyType, V, tv::hash::Murmur3Hash<KeyType>,
kEmptyKey, false>;
using pair_t = typename table_t::value_type;
// int64_t expected_hash_data_num = int64_t(tv::hash::align_to_power2(points.dim(0) * 2));
int64_t expected_hash_data_num = points.dim(0) * 2;
if (hashdata.dim(0) < expected_hash_data_num){{
hashdata = tv::zeros({{expected_hash_data_num}}, tv::custom128, 0);
}}
if (point_indice_data.dim(0) < points.dim(0)){{
point_indice_data = tv::zeros({{points.dim(0)}}, tv::int64, 0);
}}
// auto timer = tv::CudaContextTimer<>();
num_per_voxel.zero_();
table_t hash = table_t(hashdata.data_ptr<pair_t>(), expected_hash_data_num);
hash.clear();
// tv::ssprint("clear time", timer.report());
auto launcher = tv::cuda::Launch(points.dim(0));
launcher(kernel::build_hash_table<table_t>, hash, points.data_ptr<const {self.dtype}>(),
point_indice_data.data_ptr<int64_t>(),
points.dim(1), vsize, coors_range, grid_size, grid_stride, points.dim(0));
// tv::ssprint("build_hash_table", timer.report());
auto table_launcher = tv::cuda::Launch(hash.size());
tv::Tensor count = tv::zeros({{1}}, tv::int32, 0);
Layout layout = Layout::from_shape(grid_size);
table_launcher(kernel::assign_table<table_t>, hash, indices.data_ptr<int>(),
count.data_ptr<int>(),
layout, voxels.dim(0));
auto count_cpu = count.cpu();
int count_val = count_cpu.item<int32_t>();
// tv::ssprint("assign_table", timer.report());
launcher(kernel::generate_voxel<table_t>, hash, points.data_ptr<const {self.dtype}>(),
point_indice_data.data_ptr<const int64_t>(), voxels.data_ptr<{self.dtype}>(),
num_per_voxel.data_ptr<int>(), points.dim(1), voxels.dim(1),
voxels.dim(0), vsize, coors_range,
grid_size, grid_stride, points.dim(0));
// tv::ssprint("generate_voxel", timer.report());
return std::make_tuple(voxels.slice_first_axis(0, count_val),
indices.slice_first_axis(0, count_val),
num_per_voxel.slice_first_axis(0, count_val));
""")
return code.ret("std::tuple<tv::Tensor, tv::Tensor, tv::Tensor>")
@pccm.pybind.mark
@pccm.cuda.static_function
def point_to_voxel_hash_static(self):
code = pccm.FunctionCode()
code.arg("points", "tv::Tensor")
code.arg("voxels, indices, num_per_voxel, hashdata, point_indice_data",
code.arg("voxels, indices, num_per_voxel, hashdata, point_indice_data, points_voxel_id",
"tv::Tensor")
code.arg("vsize", f"std::array<float, {self.ndim}>")
code.arg("grid_size, grid_stride", f"std::array<int, {self.ndim}>")
......@@ -495,7 +445,6 @@ class Point2Voxel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
int64_t expected_hash_data_num = points.dim(0) * 2;
TV_ASSERT_RT_ERR(hashdata.dim(0) >= expected_hash_data_num, "hash table too small")
TV_ASSERT_RT_ERR(point_indice_data.dim(0) >= points.dim(0), "point_indice_data too small")
// auto timer = tv::CudaContextTimer<>();
num_per_voxel.zero_(ctx);
table_t hash = table_t(hashdata.data_ptr<pair_t>(), expected_hash_data_num);
hash.clear(custream);
......@@ -512,14 +461,12 @@ class Point2Voxel(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
layout, voxels.dim(0));
auto count_cpu = count.cpu();
int count_val = count_cpu.item<int32_t>();
// tv::ssprint("assign_table", timer.report());
count_val = count_val > voxels.dim(0) ? voxels.dim(0) : count_val;
launcher(kernel::generate_voxel<table_t>, hash, points.data_ptr<const {self.dtype}>(),
point_indice_data.data_ptr<const int64_t>(), voxels.data_ptr<{self.dtype}>(),
num_per_voxel.data_ptr<int>(), points.dim(1), voxels.dim(1),
num_per_voxel.data_ptr<int>(), points_voxel_id.data_ptr<int64_t>(), points.dim(1), voxels.dim(1),
voxels.dim(0), vsize_tv, coors_range_tv,
grid_size_tv, grid_stride_tv, points.dim(0));
// tv::ssprint("generate_voxel", timer.report());
auto voxel_launcher = tv::cuda::Launch(count_val, custream);
if (empty_mean){{
launcher(kernel::voxel_empty_fill_mean, voxels.data_ptr<{self.dtype}>(),
......@@ -636,7 +583,7 @@ class Point2VoxelCPU(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
def point_to_voxel_static_template(self, mean: bool = False):
code = pccm.FunctionCode()
code.arg("points", "tv::Tensor")
code.arg("voxels, indices, num_per_voxel, densehashdata", "tv::Tensor")
code.arg("voxels, indices, num_per_voxel, densehashdata, points_voxel_id", "tv::Tensor")
code.arg("vsize", f"std::array<float, {self.ndim}>")
code.arg("grid_size, grid_stride", f"std::array<int, {self.ndim}>")
code.arg("coors_range", f"std::array<float, {self.ndim * 2}>")
......@@ -653,6 +600,7 @@ class Point2VoxelCPU(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
if (clear_voxels){{
voxels.zero_();
}}
auto points_voxel_id_ptr = points_voxel_id.data_ptr<int64_t>();
int res_voxel_num = 0;
int num_features = points.dim(1);
auto N = points.dim(0);
......@@ -680,20 +628,25 @@ class Point2VoxelCPU(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
}}
coor[j] = c;
}}
if (failed)
if (failed){{
points_voxel_id_ptr[i] = -1;
continue;
}}
voxelidx = coor_to_voxelidx_rw({codeops.unpack("coor", range(self.ndim))});
if (voxelidx == -1) {{
voxelidx = voxel_num;
if (voxel_num >= max_num_voxels)
if (voxel_num >= max_num_voxels){{
points_voxel_id_ptr[i] = -1;
continue;
}}
voxel_num += 1;
coor_to_voxelidx_rw({codeops.unpack("coor", range(self.ndim))}) = voxelidx;
for (int k = 0; k < {self.ndim}; ++k) {{
coors_rw(voxelidx, k) = coor[k];
}}
}}
points_voxel_id_ptr[i] = voxelidx;
num = num_points_per_voxel_rw(voxelidx);
if (num < max_num_points_per_voxel) {{
// voxel_point_mask_rw(voxelidx, num) = {self.dtype}(1);
......@@ -781,8 +734,10 @@ class Point2VoxelCPU(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
code.arg("points", "tv::Tensor")
code.arg("clear_voxels", "bool", "true")
code.raw(f"""
tv::Tensor points_voxel_id = tv::empty({{points.dim(0)}}, tv::int64, -1);
return point_to_voxel_static(points, voxels, indices, num_per_voxel, densehashdata,
tvarray2array(vsize),
points_voxel_id, tvarray2array(vsize),
tvarray2array(grid_size), tvarray2array(grid_stride),
tvarray2array(coors_range), clear_voxels);
""")
......@@ -795,8 +750,10 @@ class Point2VoxelCPU(pccm.ParameterizedClass, pccm.pybind.PybindClassMixin):
code.arg("points", "tv::Tensor")
code.arg("clear_voxels", "bool", "true")
code.raw(f"""
tv::Tensor points_voxel_id = tv::empty({{points.dim(0)}}, tv::int64, -1);
return point_to_voxel_empty_mean_static(points, voxels, indices, num_per_voxel,
densehashdata, tvarray2array(vsize),
densehashdata, points_voxel_id, tvarray2array(vsize),
tvarray2array(grid_size), tvarray2array(grid_stride),
tvarray2array(coors_range), clear_voxels);
""")
......
spconv/pytorch/utils.py
View file @ fe4a2e61
......@@ -71,45 +71,83 @@ class PointToVoxel(object):
pc: torch.Tensor,
clear_voxels: bool = True,
empty_mean: bool = False):
"""generate voxels/indices/num_point_per_voxel/pc_voxel_ids from
point cloud.
This function don't return pc_voxel_id for backward compatility.
pc_voxel_id will be added in spconv 2.2.
Args:
pc: [N, 3+] point cloud.
clear_voxels: if True, call zero on voxels
empty_mean: if True, full empty location of voxels with mean.
Returns:
voxels: voxels
indices: quantized coords
num_per_voxel: number of points in a voxel
"""
res = self.generate_voxel_with_id(pc, clear_voxels, empty_mean)
return res[0], res[1], res[2]
def generate_voxel_with_id(self,
pc: torch.Tensor,
clear_voxels: bool = True,
empty_mean: bool = False):
"""generate voxels/indices/num_point_per_voxel/pc_voxel_ids from
point cloud.
Args:
pc: [N, 3+] point cloud.
clear_voxels: if True, call zero on voxels
empty_mean: if True, full empty location of voxels with mean.
Returns:
voxels: voxels
indices: quantized coords
num_per_voxel: number of points in a voxel
pc_voxel_id: voxel id for every point. if not exists, -1.
"""
assert pc.device.type == self.device.type, "your pc device is wrong"
expected_hash_data_num = pc.shape[0] * 2
with torch.no_grad():
pc_voxel_id = torch.empty([pc.shape[0]],
dtype=torch.int64,
device=self.device)
pc_voxel_id_tv = torch_tensor_to_tv(pc_voxel_id)
if self.device.type != "cpu":
if self.hashdata.shape[0] < expected_hash_data_num:
self.hashdata = torch.empty([expected_hash_data_num, 2],
dtype=torch.int64,
device=self.device)
if self.point_indice_data.shape[0] < pc.shape[0]:
self.point_indice_data = torch.empty([pc.shape[0]],
dtype=torch.int64,
device=self.device)
hashdata = torch.empty([expected_hash_data_num, 2],
dtype=torch.int64,
device=pc.device)
point_indice_data = torch.empty([pc.shape[0]],
dtype=torch.int64,
device=pc.device)
pc_tv = torch_tensor_to_tv(pc)
stream = get_current_stream()
voxels_tv = torch_tensor_to_tv(self.voxels)
indices_tv = torch_tensor_to_tv(self.indices)
num_per_voxel_tv = torch_tensor_to_tv(self.num_per_voxel)
hashdata_tv = torch_tensor_to_tv(
self.hashdata,
hashdata,
dtype=tv.custom128,
shape=[self.hashdata.shape[0]])
point_indice_data_tv = torch_tensor_to_tv(
self.point_indice_data)
res = SpconvOps.point2voxel_cuda(
pc_tv, voxels_tv, indices_tv, num_per_voxel_tv,
hashdata_tv, point_indice_data_tv, self.vsize,
self.grid_size, self.grid_stride, self.coors_range,
empty_mean, clear_voxels, stream)
shape=[hashdata.shape[0]])
point_indice_data_tv = torch_tensor_to_tv(point_indice_data)
with torch.cuda.device(pc.device):
res = SpconvOps.point2voxel_cuda(
pc_tv, voxels_tv, indices_tv, num_per_voxel_tv,
hashdata_tv, point_indice_data_tv, pc_voxel_id_tv, self.vsize,
self.grid_size, self.grid_stride, self.coors_range,
empty_mean, clear_voxels, stream)
num_voxels = res[0].shape[0]
else:
pc_tv = torch_tensor_to_tv(pc)
stream = get_current_stream()
voxels_tv = torch_tensor_to_tv(self.voxels)
indices_tv = torch_tensor_to_tv(self.indices)
num_per_voxel_tv = torch_tensor_to_tv(self.num_per_voxel)
hashdata_tv = torch_tensor_to_tv(self.hashdata, dtype=tv.int32)
res = SpconvOps.point2voxel_cpu(pc_tv, voxels_tv, indices_tv,
num_per_voxel_tv, hashdata_tv,
pc_voxel_id_tv,
self.vsize, self.grid_size,
self.grid_stride,
self.coors_range, empty_mean,
......@@ -117,4 +155,18 @@ class PointToVoxel(object):
num_voxels = res[0].shape[0]
return (self.voxels[:num_voxels], self.indices[:num_voxels],
self.num_per_voxel[:num_voxels])
self.num_per_voxel[:num_voxels], pc_voxel_id)
def gather_features_by_pc_voxel_id(seg_res_features: torch.Tensor, pc_voxel_id: torch.Tensor):
"""This function is used to gather segmentation result to match origin pc.
"""
if seg_res_features.device != pc_voxel_id.device:
pc_voxel_id = pc_voxel_id.to(seg_res_features.device)
res = torch.zeros((pc_voxel_id.shape[0], seg_res_features.shape[1]), dtype=seg_res_features.dtype, device=seg_res_features.device)
pc_voxel_id_valid = pc_voxel_id != -1
pc_voxel_id_valid_ids = torch.nonzero(pc_voxel_id_valid).view(-1)
seg_res_features_valid = seg_res_features[pc_voxel_id[pc_voxel_id_valid_ids]]
res[pc_voxel_id_valid_ids] = seg_res_features_valid
return res
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