def eval_mesh(self, mesh, pointcloud_tgt, normals_tgt, points_iou,
occ_tgt):
''' Evaluates a mesh.
Args:
mesh (trimesh): mesh which should be evaluated
pointcloud_tgt (numpy array): target point cloud
normals_tgt (numpy array): target normals
points_iou (numpy_array): points tensor for IoU evaluation
occ_tgt (numpy_array): GT occupancy values for IoU points
'''
if len(mesh.vertices) != 0 and len(mesh.faces) != 0:
if True: #! Remove walls and floors
pointcloud, idx = mesh.sample(2 * self.n_points,
return_index=True)
eps = 0.007
x_max, x_min = pointcloud_tgt[:, 0].max(
), pointcloud_tgt[:, 0].min()
y_max, y_min = pointcloud_tgt[:, 1].max(
), pointcloud_tgt[:, 1].min()
z_max, z_min = pointcloud_tgt[:, 2].max(
), pointcloud_tgt[:, 2].min()
# add small offsets
x_max, x_min = x_max + eps, x_min - eps
y_max, y_min = y_max + eps, y_min - eps
z_max, z_min = z_max + eps, z_min - eps
mask_x = (pointcloud[:, 0] <= x_max) & (pointcloud[:, 0] >=
x_min)
mask_y = (pointcloud[:, 1] >= y_min) # floor
mask_z = (pointcloud[:, 2] <= z_max) & (pointcloud[:, 2] >=
z_min)
mask = mask_x & mask_y & mask_z
pointcloud_new = pointcloud[mask]
# Subsample
idx_new = np.random.randint(pointcloud_new.shape[0],
size=self.n_points)
pointcloud = pointcloud_new[idx_new]
idx = idx[mask][idx_new]
else:
pointcloud, idx = mesh.sample(self.n_points, return_index=True)
pointcloud = pointcloud.astype(np.float32)
normals = mesh.face_normals[idx]
else:
pointcloud = np.empty((0, 3))
normals = np.empty((0, 3))
out_dict = self.eval_pointcloud(pointcloud, pointcloud_tgt, normals,
normals_tgt)
if len(mesh.vertices) != 0 and len(mesh.faces) != 0:
occ = check_mesh_contains(mesh, points_iou)
out_dict['iou'] = compute_iou(occ, occ_tgt)
else:
out_dict['iou'] = 0.
return out_dict
def eval_step(self, data):
''' Performs an evaluation step.
Args:
data (dict): data dictionary
'''
self.model.eval()
device = self.device
threshold = self.threshold
eval_dict = {}
points = data.get('points').to(device)
occ = data.get('points.occ').to(device)
inputs = data.get('inputs', torch.empty(points.size(0), 0)).to(device)
voxels_occ = data.get('voxels')
points_iou = data.get('points_iou').to(device)
occ_iou = data.get('points_iou.occ').to(device)
batch_size = points.size(0)
kwargs = {}
# add pre-computed index
inputs = add_key(inputs,
data.get('inputs.ind'),
'points',
'index',
device=device)
# add pre-computed normalized coordinates
points = add_key(points,
data.get('points.normalized'),
'p',
'p_n',
device=device)
points_iou = add_key(points_iou,
data.get('points_iou.normalized'),
'p',
'p_n',
device=device)
# Compute iou
with torch.no_grad():
p_out = self.model(points_iou,
inputs,
sample=self.eval_sample,
**kwargs)
occ_iou_np = (occ_iou >= 0.5).cpu().numpy()
occ_iou_hat_np = (p_out.probs >= threshold).cpu().numpy()
iou = compute_iou(occ_iou_np, occ_iou_hat_np).mean()
eval_dict['iou'] = iou
# Estimate voxel iou
if voxels_occ is not None:
voxels_occ = voxels_occ.to(device)
points_voxels = make_3d_grid((-0.5 + 1 / 64, ) * 3,
(0.5 - 1 / 64, ) * 3,
voxels_occ.shape[1:])
points_voxels = points_voxels.expand(batch_size,
*points_voxels.size())
points_voxels = points_voxels.to(device)
with torch.no_grad():
p_out = self.model(points_voxels,
inputs,
sample=self.eval_sample,
**kwargs)
voxels_occ_np = (voxels_occ >= 0.5).cpu().numpy()
occ_hat_np = (p_out.probs >= threshold).cpu().numpy()
iou_voxels = compute_iou(voxels_occ_np, occ_hat_np).mean()
eval_dict['iou_voxels'] = iou_voxels
return eval_dict
def eval_step(self, data):
''' Performs an evaluation step.
Args:
data (dict): data dictionary
'''
self.model.eval()
device = self.device
threshold = self.threshold
eval_dict = {}
# Compute elbo
points = data.get('points').to(device)
occ = data.get('points.occ').to(device)
inputs = data.get('inputs', torch.empty(points.size(0), 0)).to(device)
voxels_occ = data.get('voxels')
points_iou = data.get('points_iou').to(device)
occ_iou = data.get('points_iou.occ').to(device)
kwargs = {}
semantic_map = data.get('semantic_map', None)
with torch.no_grad():
elbo, rec_error, kl = self.model.compute_elbo(
points, occ, inputs, semantic_map, **kwargs)
eval_dict['loss'] = -elbo.mean().item()
eval_dict['rec_error'] = rec_error.mean().item()
eval_dict['kl'] = kl.mean().item()
# Compute iou
batch_size = points.size(0)
with torch.no_grad():
p_out = self.model(points_iou,
inputs,
sample=self.eval_sample,
semantic_map=semantic_map,
**kwargs)
occ_iou_np = (occ_iou >= 0.5).cpu().numpy()
occ_iou_hat_np = (p_out.probs >= threshold).cpu().numpy()
iou = compute_iou(occ_iou_np, occ_iou_hat_np).mean()
eval_dict['iou'] = iou
# Estimate voxel iou
if voxels_occ is not None:
voxels_occ = voxels_occ.to(device)
points_voxels = make_3d_grid((-0.5 + 1 / 64, ) * 3,
(0.5 - 1 / 64, ) * 3,
voxels_occ.shape[1:])
points_voxels = points_voxels.expand(batch_size,
*points_voxels.size())
points_voxels = points_voxels.to(device)
with torch.no_grad():
p_out = self.model(points_voxels,
inputs,
sample=self.eval_sample,
**kwargs)
voxels_occ_np = (voxels_occ >= 0.5).cpu().numpy()
occ_hat_np = (p_out.probs >= threshold).cpu().numpy()
iou_voxels = compute_iou(voxels_occ_np, occ_hat_np).mean()
eval_dict['iou_voxels'] = iou_voxels
return eval_dict