def test(self):
print(f"{self.__class__.__name__}: test_dense")
in_channels, out_channels, D = 2, 3, 2
coords1 = torch.IntTensor([[0, 0], [0, 1], [1, 1]])
feats1 = torch.DoubleTensor([[1, 2], [3, 4], [5, 6]])
coords2 = torch.IntTensor([[1, 1], [1, 2], [2, 1]])
feats2 = torch.DoubleTensor([[7, 8], [9, 10], [11, 12]])
coords, feats = ME.utils.sparse_collate([coords1, coords2],
[feats1, feats2])
input = SparseTensor(feats, coords)
input.requires_grad_()
dinput, min_coord, tensor_stride = input.dense()
self.assertTrue(dinput[0, 0, 0, 1] == 3)
self.assertTrue(dinput[0, 1, 0, 1] == 4)
self.assertTrue(dinput[0, 0, 1, 1] == 5)
self.assertTrue(dinput[0, 1, 1, 1] == 6)
self.assertTrue(dinput[1, 0, 1, 1] == 7)
self.assertTrue(dinput[1, 1, 1, 1] == 8)
self.assertTrue(dinput[1, 0, 2, 1] == 11)
self.assertTrue(dinput[1, 1, 2, 1] == 12)
# Initialize context
conv = MinkowskiConvolution(
in_channels,
out_channels,
kernel_size=3,
stride=2,
bias=True,
dimension=D,
)
conv = conv.double()
output = conv(input)
print(input.C, output.C)
# Convert to a dense tensor
dense_output, min_coord, tensor_stride = output.dense()
print(dense_output.shape)
print(dense_output)
print(min_coord)
print(tensor_stride)
dense_output, min_coord, tensor_stride = output.dense(
min_coordinate=torch.IntTensor([-2, -2]))
print(dense_output)
print(min_coord)
print(tensor_stride)
print(feats.grad)
loss = dense_output.sum()
loss.backward()
print(feats.grad)
def forward(self, x: ME.SparseTensor):
return x.dense(self.min_coords, self.max_coords)[0]
def prepare_sparse_input(img, img_meta=None, gt_bboxes=None, gt_labels=None, rescale=None):
coords_batch, feats_batch = img
## For some networks, making the network invariant to even, odd coords is important
#coord_base = (torch.rand(3) * 100).type_as(coords_batch)
#coords_batch[:, 1:4] += coord_base
sinput = SparseTensor(feats_batch, coords_batch)
if DEBUG_CFG.SPARSE_BEV:
sinput = get_pcl_topview(sinput, gt_bboxes)
assert gt_labels[0].min() > 0
debug = 0
if DEBUG_CFG.VISUAL_SPARSE_3D_INPUT:
obj_rep = img_meta[0]['obj_rep']
n = coords_batch.shape[0]
print(f'batch voxe num: {n/1000}k')
batch_size = coords_batch[:,0].max()+1
for i in range(batch_size):
print(f'example {i}/{batch_size}')
batch_mask = coords_batch[:,0] == i
points = coords_batch[batch_mask][:, 1:].cpu().data.numpy()
colors = feats_batch[batch_mask][:, :3].cpu().data.numpy()
colors = colors+0.5
normals = feats_batch[batch_mask][:, 3:6].cpu().data.numpy()
num_p = points.shape[0]
img_meta_i = img_meta[i]
voxel_size = img_meta_i['voxel_size']
raw_dynamic_vox_size = img_meta_i['raw_dynamic_vox_size']
mask_i = sinput.C[:,0] == i
ci = sinput.C[mask_i]
bboxes3d = gt_bboxes[i].cpu().data.numpy()
min_points = points.min(axis=0)
max_points = points.max(axis=0)
gt_labels_i = gt_labels[i].cpu().data.numpy()
data_aug = img_meta_i['data_aug']
dynamic_vox_size_aug = img_meta_i['dynamic_vox_size_aug']
print('\n\nfinal sparse input')
footprint = dynamic_vox_size_aug[0] * dynamic_vox_size_aug[1] * (voxel_size*voxel_size)
print(f'dynamic_vox_size_aug: {dynamic_vox_size_aug}, footprint: {footprint}')
print(f'num voxel: {num_p/1000}K')
print(img_meta[i]['filename'])
print(f'points scope: {min_points} - {max_points}')
print(f'data aug:\n {data_aug}\n')
print(f'labels: {gt_labels}')
scale = 1
#_show_lines_ls_points_ls((512,512), [lines2d*scale], [points*scale])
#_show_lines_ls_points_ls((512,512), [lines2d*scale])
#_show_objs_ls_points_ls((512,512), [lines2d*scale], 'RoLine2D_UpRight_xyxy_sin2a')
#_show_objs_ls_points_ls((512,512), [lines2d*scale], 'RoLine2D_UpRight_xyxy_sin2a', [points*scale])
#_show_3d_points_objs_ls([points], None, [bboxes3d], obj_rep='RoBox3D_UpRight_xyxy_sin2a_thick_Z0Z1' , obj_colors=[gt_labels_i] )
_show_3d_points_objs_ls([points], [colors], [bboxes3d], obj_rep=obj_rep, obj_colors=[gt_labels_i])
import pdb; pdb.set_trace() # XXX BREAKPOINT
pass
if 0 and DEBUG_CFG.SPARSE_BEV:
coords_batch = sinput.C
feats_batch = sinput.F
dense, _, _ = sinput.dense()
dense = dense.permute(0,1,3,2,4)
batch_size = coords_batch[:,0].max()+1
for i in range(batch_size):
batch_mask = coords_batch[:,0] == i
points = coords_batch[batch_mask][:, 1:].cpu().data.numpy()
normals = feats_batch[batch_mask][:, 1:].cpu().data.numpy()
num_p = points.shape[0]
lines2d = gt_bboxes[i].cpu().data.numpy()
density = dense[i,-1,:,:,0].cpu().data.numpy()
min_points = points.min(axis=0)
max_points = points.max(axis=0)
min_lines = lines2d[:,:4].reshape(-1,2).min(axis=0)
max_lines = lines2d[:,:4].reshape(-1,2).max(axis=0)
img_meta_i = img_meta[i]
data_aug = img_meta_i['data_aug']
dynamic_vox_size_aug = img_meta_i['dynamic_vox_size_aug']
print('\n\nfinal sparse input')
footprint = dynamic_vox_size_aug[0] * dynamic_vox_size_aug[1] * (voxel_size*voxel_size)
print(f'dynamic_vox_size_aug: {dynamic_vox_size_aug}, footprint: {footprint}')
print(f'num voxel: {num_p/1000}K')
print(img_meta[i]['filename'])
print(f'points scope: {min_points} - {max_points}')
print(f'lines scope: {min_lines} - {max_lines}')
print(f'data aug:\n {data_aug}\n')
#_show_lines_ls_points_ls(density, [lines2d])
from beike_data_utils.line_utils import lines2d_to_bboxes3d
bboxes3d_pixel = lines2d_to_bboxes3d(lines2d, OBJ_REP, height=30, thickness=1)
_show_3d_points_bboxes_ls([points], None, [ bboxes3d_pixel ],
b_colors = 'red', box_oriented=True, point_normals=[normals])
import pdb; pdb.set_trace() # XXX BREAKPOINT
pass
if 0 and not DEBUG_CFG.SPARSE_BEV:
n = coords_batch.shape[0]
print(f'batch voxe num: {n/1000}k')
batch_size = coords_batch[:,0].max()+1
for i in range(batch_size):
print(f'example {i}/{batch_size}')
batch_mask = coords_batch[:,0] == i
points = coords_batch[batch_mask][:, 1:].cpu().data.numpy()
colors = feats_batch[batch_mask][:, :3].cpu().data.numpy()
colors = colors+0.5
normals = feats_batch[batch_mask][:, 3:6].cpu().data.numpy()
num_p = points.shape[0]
img_meta_i = img_meta[i]
voxel_size = img_meta_i['voxel_size']
raw_dynamic_vox_size = img_meta_i['raw_dynamic_vox_size']
mask_i = sinput.c[:,0] == i
ci = sinput.c[mask_i]
lines2d = gt_bboxes[i].cpu().data.numpy()
from beike_data_utils.line_utils import lines2d_to_bboxes3d
bboxes3d_pixel = lines2d_to_bboxes3d(lines2d, OBJ_REP, height=50, thickness=1)
min_points = points.min(axis=0)
max_points = points.max(axis=0)
min_lines = lines2d[:,:4].reshape(-1,2).min(axis=0)
max_lines = lines2d[:,:4].reshape(-1,2).max(axis=0)
data_aug = img_meta_i['data_aug']
dynamic_vox_size_aug = img_meta_i['dynamic_vox_size_aug']
print('\n\nfinal sparse input')
footprint = dynamic_vox_size_aug[0] * dynamic_vox_size_aug[1] * (voxel_size*voxel_size)
print(f'dynamic_vox_size_aug: {dynamic_vox_size_aug}, footprint: {footprint}')
print(f'num voxel: {num_p/1000}K')
print(img_meta[i]['filename'])
print(f'points scope: {min_points} - {max_points}')
print(f'lines scope: {min_lines} - {max_lines}')
print(f'data aug:\n {data_aug}\n')
scale = 1
#_show_lines_ls_points_ls((512,512), [lines2d*scale], [points*scale])
_show_3d_points_bboxes_ls([points], [colors], [ bboxes3d_pixel ],
b_colors = 'red', box_oriented=True, point_normals=[normals])
import pdb; pdb.set_trace() # XXX BREAKPOINT
pass
return sinput
