def __init__(self, num_layers, ndim, shape, kernel_size, stride, padding,
dilation):
super().__init__()
layers = [
spconv.SparseMaxPool3d(kernel_size, stride, padding, dilation)
]
for i in range(1, num_layers):
layers.append(
spconv.SparseMaxPool3d(kernel_size, stride, padding, dilation))
self.net = spconv.SparseSequential(*layers, )
self.shape = shape
def __init__(self,
num_layers,
ndim,
shape,
in_channels,
out_channels,
kernel_size,
stride,
padding,
dilation,
algo=spconv.ConvAlgo.Native):
super().__init__()
layers = [
spconv.SparseConv3d(in_channels,
out_channels,
kernel_size,
stride,
padding=padding,
dilation=dilation,
bias=False,
use_hash=False,
algo=algo)
]
for i in range(1, num_layers):
layers.append(
spconv.SparseConv3d(out_channels,
out_channels,
kernel_size,
stride,
padding=padding,
dilation=dilation,
bias=False,
use_hash=False,
algo=algo))
self.net = spconv.SparseSequential(*layers, )
# self.grid = torch.full([3, *shape], -1, dtype=torch.int32).cuda()
self.grid = None
self.shape = shape
def __init__(self, num_layers, ndim, shape, in_channels, out_channels,
kernel_size, stride, padding, dilation):
super().__init__()
layers = [
spconv.SparseConvTranspose3d(in_channels,
out_channels,
kernel_size,
stride,
padding=padding,
dilation=dilation,
bias=False)
]
for i in range(1, num_layers):
layers.append(
spconv.SparseConvTranspose3d(out_channels,
out_channels,
kernel_size,
stride,
padding=padding,
dilation=dilation,
bias=False))
self.net = spconv.SparseSequential(*layers, )
self.shape = shape
def __init__(self,
spatial_shape,
use_norm=True,
num_input_features=3,
name='SpMiddleFHDLite'):
"""
@param: output_shape: a dense shape, which feed to RPN
@param: use_norm: if use batchnorm
@param: num_input_features: depends on the output shape from VFE block
@param: name:
"""
super(SpMiddleFHDLite, self).__init__()
self.name = name
if use_norm:
BatchNorm1d = change_default_args(eps=1e-3, momentum=0.01)(nn.BatchNorm1d)
SpConv3d = change_default_args(bias=False)(spconv.SparseConv3d)
else:
BatchNorm1d = Empty
SpConv3d = change_default_args(bias=True)(spconv.SparseConv3d)
# ToDO: add if condition for when need padding 3D tensor
self.spatial_shape = np.array(spatial_shape) + [1, 0, 0] # padding input shape e.g. [41 1280, 1056]
# input: # [1600, 1200, 41]
self.middle_conv = spconv.SparseSequential(
SpConv3d(num_input_features, 16, 3, 2, padding=1), # [1600, 1200, 41] -> [800, 600, 21]
BatchNorm1d(16),
nn.ReLU(),
SpConv3d(16, 32, 3, 2, padding=1), # [800, 600, 21] -> [400, 300, 11]
BatchNorm1d(32),
nn.ReLU(),
SpConv3d(32, 64, 3, 2, padding=[0, 1, 1]), # [400, 300, 11] -> [200, 150, 5]
BatchNorm1d(64),
nn.ReLU(),
SpConv3d(64, 64, (3, 1, 1), (2, 1, 1)), # [200, 150, 5] -> [200, 150, 2]
BatchNorm1d(64),
nn.ReLU(),
)