hofee/nbv_reconstruction
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

global: upd inference

Browse Source
This commit is contained in:
hofee 2024-11-01 08:43:13 +00:00
parent b221036e8b
commit 985a08d89c
4 changed files with 74 additions and 66 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
configs/local/inference_config.yaml
View File

@ -6,71 +6,67 @@ runner:
cuda_visible_devices: "0,1,2,3,4,5,6,7"
experiment:
name: w_gf_wo_lf_full
name: overfit_ab_global_only
root_dir: "experiments"
epoch: 1 # -1 stands for last epoch
epoch: -1 # -1 stands for last epoch
test:
dataset_list:
- OmniObject3d_train
blender_script_path: "/media/hofee/data/project/python/nbv_reconstruction/blender/data_renderer.py"
output_dir: "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/test/inference_global_full_on_testset"
pipeline: nbv_reconstruction_global_pts_pipeline
blender_script_path: "/data/hofee/project/nbv_rec/blender/data_renderer.py"
output_dir: "/data/hofee/data/inference_global_full_on_testset"
pipeline: nbv_reconstruction_pipeline
voxel_size: 0.003
dataset:
OmniObject3d_train:
root_dir: "/media/hofee/repository/nbv_reconstruction_data_512"
model_dir: "/media/hofee/data/data/scaled_object_meshes"
source: seq_nbv_reconstruction_dataset
split_file: "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/test/test_set_list.txt"
root_dir: "/data/hofee/data/new_full_data"
model_dir: "/data/hofee/data/scaled_object_meshes"
source: seq_reconstruction_dataset
split_file: "/data/hofee/data/sample.txt"
type: test
filter_degree: 75
ratio: 1
batch_size: 1
num_workers: 12
pts_num: 4096
load_from_preprocess: False
pts_num: 8192
load_from_preprocess: True
OmniObject3d_test:
root_dir: "/data/hofee/data/new_full_data"
model_dir: "/data/hofee/data/scaled_object_meshes"
source: seq_reconstruction_dataset
split_file: "/data/hofee/data/sample.txt"
type: test
filter_degree: 75
eval_list:
- pose_diff
- coverage_rate_increase
ratio: 0.1
batch_size: 1
num_workers: 12
pts_num: 8192
load_from_preprocess: True
pipeline:
nbv_reconstruction_local_pts_pipeline:
nbv_reconstruction_pipeline:
modules:
pts_encoder: pointnet_encoder
seq_encoder: transformer_seq_encoder
pose_encoder: pose_encoder
view_finder: gf_view_finder
eps: 1e-5
global_scanned_feat: False
nbv_reconstruction_global_pts_pipeline:
modules:
pts_encoder: pointnet_encoder
pose_seq_encoder: transformer_pose_seq_encoder
pose_encoder: pose_encoder
view_finder: gf_view_finder
eps: 1e-5
global_scanned_feat: True
module:
pointnet_encoder:
in_dim: 3
out_dim: 1024
global_feat: True
feature_transform: False
transformer_seq_encoder:
pts_embed_dim: 1024
pose_embed_dim: 256
num_heads: 4
ffn_dim: 256
num_layers: 3
output_dim: 2048
transformer_pose_seq_encoder:
pose_embed_dim: 256
embed_dim: 256
num_heads: 4
ffn_dim: 256
num_layers: 3
@ -86,7 +82,8 @@ module:
sample_mode: ode
sampling_steps: 500
sde_mode: ve
pose_encoder:
pose_dim: 9
out_dim: 256
pts_num_encoder:
out_dim: 64

26
core/seq_dataset.py
View File

@ -103,6 +103,18 @@ class SeqReconstructionDataset(BaseDataset):
except Exception as e:
Log.error(f"Save cache failed: {e}")
def seq_combined_pts(self, scene, frame_idx_list):
all_combined_pts = []
for i in frame_idx_list:
path = DataLoadUtil.get_path(self.root_dir, scene, i)
pts = DataLoadUtil.load_from_preprocessed_pts(path,"npy")
if pts.shape[0] == 0:
continue
all_combined_pts.append(pts)
all_combined_pts = np.vstack(all_combined_pts)
downsampled_all_pts = PtsUtil.voxel_downsample_point_cloud(all_combined_pts, 0.003)
return downsampled_all_pts
def __getitem__(self, index):
data_item_info = self.datalist[index]
max_coverage_rate = data_item_info["max_coverage_rate"]
@ -130,20 +142,26 @@ class SeqReconstructionDataset(BaseDataset):
n_to_world_6d = PoseUtil.matrix_to_rotation_6d_numpy(
np.asarray(n_to_world_pose[:3, :3])
)
first_left_cam_pose = cam_info["cam_to_world"]
first_center_cam_pose = cam_info["cam_to_world_O"]
first_O_to_first_L_pose = np.dot(np.linalg.inv(first_left_cam_pose), first_center_cam_pose)
n_to_world_trans = n_to_world_pose[:3, 3]
n_to_world_9d = np.concatenate([n_to_world_6d, n_to_world_trans], axis=0)
scanned_n_to_world_pose.append(n_to_world_9d)
# combined_scanned_views_pts = np.concatenate(scanned_views_pts, axis=0)
# voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_views_pts, 0.002)
# random_downsampled_combined_scanned_pts_np = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, self.pts_num)
frame_list = []
for i in range(DataLoadUtil.get_scene_seq_length(self.root_dir, scene_name)):
frame_list.append(i)
gt_pts = self.seq_combined_pts(scene_name, frame_list)
data_item = {
"first_scanned_pts": np.asarray(scanned_views_pts, dtype=np.float32), # Ndarray(S x Nv x 3)
"first_scanned_coverage_rate": scanned_coverages_rate, # List(S): Float, range(0, 1)
"first_scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9)
"seq_max_coverage_rate": max_coverage_rate, # Float, range(0, 1)
"scene_name": scene_name, # String
"gt_pts": gt_pts, # Ndarray(N x 3)
"scene_path": os.path.join(self.root_dir, scene_name), # String
"O_to_L_pose": first_O_to_first_L_pose,
}
return data_item

39
runners/inferencer.py
View File

@ -27,6 +27,7 @@ class Inferencer(Runner):
self.script_path = ConfigManager.get(namespace.Stereotype.RUNNER, "blender_script_path")
self.output_dir = ConfigManager.get(namespace.Stereotype.RUNNER, "output_dir")
self.voxel_size = ConfigManager.get(namespace.Stereotype.RUNNER, "voxel_size")
''' Pipeline '''
self.pipeline_name = self.config[namespace.Stereotype.PIPELINE]
self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
@ -65,16 +66,11 @@ class Inferencer(Runner):
for dataset_idx, test_set in enumerate(self.test_set_list):
status_manager.set_progress("inference", "inferencer", f"dataset", dataset_idx, len(self.test_set_list))
test_set_name = test_set.get_name()
test_loader = test_set.get_loader()
if test_loader.batch_size > 1:
Log.error("Batch size should be 1 for inference, found {} in {}".format(test_loader.batch_size, test_set_name), terminate=True)
total=int(len(test_loader))
loop = tqdm(enumerate(test_loader), total=total)
for i, data in loop:
total=int(len(test_set))
for i in range(total):
data = test_set.__getitem__(i)
status_manager.set_progress("inference", "inferencer", f"Batch[{test_set_name}]", i+1, total)
test_set.process_batch(data, self.device)
output = self.predict_sequence(data)
self.save_inference_result(test_set_name, data["scene_name"][0], output)
@ -88,26 +84,23 @@ class Inferencer(Runner):
''' data for rendering '''
scene_path = data["scene_path"][0]
O_to_L_pose = data["O_to_L_pose"][0]
voxel_threshold = data["voxel_threshold"][0]
filter_degree = data["filter_degree"][0]
model_points_normals = data["model_points_normals"][0]
model_pts = model_points_normals[:,:3]
down_sampled_model_pts = PtsUtil.voxel_downsample_point_cloud(model_pts, voxel_threshold)
first_frame_to_world_9d = data["first_to_world_9d"][0]
first_frame_to_world = torch.eye(4, device=first_frame_to_world_9d.device)
first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_tensor_batch(first_frame_to_world_9d[:,:6])[0]
first_frame_to_world[:3,3] = first_frame_to_world_9d[0,6:]
first_frame_to_world = first_frame_to_world.to(self.device)
voxel_threshold = self.voxel_size
filter_degree = 75
down_sampled_model_pts = data["gt_pts"]
import ipdb; ipdb.set_trace()
first_frame_to_world_9d = data["first_scanned_n_to_world_pose_9d"][0]
first_frame_to_world = np.eye(4)
first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_numpy(first_frame_to_world_9d[:6])
first_frame_to_world[:3,3] = first_frame_to_world_9d[6:]
''' data for inference '''
input_data = {}
input_data["scanned_pts"] = [data["first_pts"][0].to(self.device)]
input_data["scanned_n_to_world_pose_9d"] = [data["first_to_world_9d"][0].to(self.device)]
input_data["combined_scanned_pts"] = torch.tensor(data["first_scanned_pts"][0], dtype=torch.float32).to(self.device)
input_data["scanned_n_to_world_pose_9d"] = [torch.tensor(data["first_scanned_n_to_world_pose_9d"], dtype=torch.float32).to(self.device)]
input_data["mode"] = namespace.Mode.TEST
input_data["combined_scanned_pts"] = data["combined_scanned_pts"]
input_pts_N = input_data["scanned_pts"][0].shape[1]
input_pts_N = input_data["combined_scanned_pts"].shape[1]
first_frame_target_pts, _ = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, model_points_normals, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
first_frame_target_pts, _ = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, down_sampled_model_pts, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
scanned_view_pts = [first_frame_target_pts]
last_pred_cr = self.compute_coverage_rate(scanned_view_pts, None, down_sampled_model_pts, threshold=voxel_threshold)

6
utils/render.py
View File

@ -10,7 +10,7 @@ from utils.pts import PtsUtil
class RenderUtil:
@staticmethod
def render_pts(cam_pose, scene_path, script_path, model_points_normals, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
def render_pts(cam_pose, scene_path, script_path, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
nO_to_world_pose = DataLoadUtil.get_real_cam_O_from_cam_L(cam_pose, nO_to_nL_pose, scene_path=scene_path)
@ -34,10 +34,10 @@ class RenderUtil:
return None
path = os.path.join(temp_dir, "tmp")
point_cloud = DataLoadUtil.get_target_point_cloud_world_from_path(path, binocular=True)
normals = DataLoadUtil.get_target_normals_world_from_path(path, binocular=True)
cam_params = DataLoadUtil.load_cam_info(path, binocular=True)
''' TODO: old code: filter_points api is changed, need to update the code '''
filtered_point_cloud = PtsUtil.filter_points(point_cloud, model_points_normals, cam_pose=cam_params["cam_to_world"], voxel_size=voxel_threshold, theta=filter_degree)
filtered_point_cloud = PtsUtil.filter_points(point_cloud, normals, cam_pose=cam_params["cam_to_world"], voxel_size=voxel_threshold, theta=filter_degree)
full_scene_point_cloud = None
if require_full_scene:
depth_L, depth_R = DataLoadUtil.load_depth(path, cam_params['near_plane'], cam_params['far_plane'], binocular=True)