nbv_reconstruction/core/nbv_dataset.py
2024-09-23 14:30:51 +08:00

262 lines
12 KiB
Python

import numpy as np
from PytorchBoot.dataset import BaseDataset
import PytorchBoot.namespace as namespace
import PytorchBoot.stereotype as stereotype
from PytorchBoot.config import ConfigManager
from PytorchBoot.utils.log_util import Log
import torch
import os
import sys
sys.path.append(r"/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction")
from utils.data_load import DataLoadUtil
from utils.pose import PoseUtil
from utils.pts import PtsUtil
from utils.reconstruction import ReconstructionUtil
@stereotype.dataset("nbv_reconstruction_dataset")
class NBVReconstructionDataset(BaseDataset):
def __init__(self, config):
super(NBVReconstructionDataset, self).__init__(config)
self.config = config
self.root_dir = config["root_dir"]
self.split_file_path = config["split_file"]
self.scene_name_list = self.load_scene_name_list()
self.datalist = self.get_datalist()
self.pts_num = config["pts_num"]
self.type = config["type"]
self.cache = config.get("cache")
self.load_from_preprocess = config.get("load_from_preprocess", False)
if self.type == namespace.Mode.TEST:
self.model_dir = config["model_dir"]
self.filter_degree = config["filter_degree"]
if self.type == namespace.Mode.TRAIN:
self.datalist = self.datalist*100
if self.cache:
expr_root = ConfigManager.get("runner", "experiment", "root_dir")
expr_name = ConfigManager.get("runner", "experiment", "name")
self.cache_dir = os.path.join(expr_root, expr_name, "cache")
#self.preprocess_cache()
def load_scene_name_list(self):
scene_name_list = []
with open(self.split_file_path, "r") as f:
for line in f:
scene_name = line.strip()
scene_name_list.append(scene_name)
return scene_name_list
def get_datalist(self):
datalist = []
for scene_name in self.scene_name_list:
label_path = DataLoadUtil.get_label_path(self.root_dir, scene_name)
label_data = DataLoadUtil.load_label(label_path)
for data_pair in label_data["data_pairs"]:
scanned_views = data_pair[0]
next_best_view = data_pair[1]
max_coverage_rate = label_data["max_coverage_rate"]
datalist.append(
{
"scanned_views": scanned_views,
"next_best_view": next_best_view,
"max_coverage_rate": max_coverage_rate,
"scene_name": scene_name,
}
)
return datalist
def preprocess_cache(self):
Log.info("preprocessing cache...")
for item_idx in range(len(self.datalist)):
self.__getitem__(item_idx)
Log.success("finish preprocessing cache.")
def load_from_cache(self, scene_name, curr_frame_idx):
cache_name = f"{scene_name}_{curr_frame_idx}.txt"
cache_path = os.path.join(self.cache_dir, cache_name)
if os.path.exists(cache_path):
data = np.loadtxt(cache_path)
return data
else:
return None
def save_to_cache(self, scene_name, curr_frame_idx, data):
cache_name = f"{scene_name}_{curr_frame_idx}.txt"
cache_path = os.path.join(self.cache_dir, cache_name)
try:
np.savetxt(cache_path, data)
except Exception as e:
Log.error(f"Save cache failed: {e}")
# ----- Debug Trace ----- #
import ipdb; ipdb.set_trace()
# ------------------------ #
def __getitem__(self, index):
data_item_info = self.datalist[index]
scanned_views = data_item_info["scanned_views"]
nbv = data_item_info["next_best_view"]
max_coverage_rate = data_item_info["max_coverage_rate"]
scene_name = data_item_info["scene_name"]
scanned_views_pts, scanned_coverages_rate, scanned_n_to_world_pose = [], [], []
for view in scanned_views:
frame_idx = view[0]
coverage_rate = view[1]
view_path = DataLoadUtil.get_path(self.root_dir, scene_name, frame_idx)
cam_info = DataLoadUtil.load_cam_info(view_path, binocular=True)
n_to_world_pose = cam_info["cam_to_world"]
nR_to_world_pose = cam_info["cam_to_world_R"]
if self.load_from_preprocess:
downsampled_target_point_cloud = DataLoadUtil.load_from_preprocessed_pts(view_path)
else:
cached_data = None
if self.cache:
cached_data = self.load_from_cache(scene_name, frame_idx)
if cached_data is None:
print("load depth")
depth_L, depth_R = DataLoadUtil.load_depth(view_path, cam_info['near_plane'], cam_info['far_plane'], binocular=True)
point_cloud_L = DataLoadUtil.get_point_cloud(depth_L, cam_info['cam_intrinsic'], n_to_world_pose)['points_world']
point_cloud_R = DataLoadUtil.get_point_cloud(depth_R, cam_info['cam_intrinsic'], nR_to_world_pose)['points_world']
point_cloud_L = PtsUtil.random_downsample_point_cloud(point_cloud_L, 65536)
point_cloud_R = PtsUtil.random_downsample_point_cloud(point_cloud_R, 65536)
overlap_points = DataLoadUtil.get_overlapping_points(point_cloud_L, point_cloud_R)
downsampled_target_point_cloud = PtsUtil.random_downsample_point_cloud(overlap_points, self.pts_num)
if self.cache:
self.save_to_cache(scene_name, frame_idx, downsampled_target_point_cloud)
else:
downsampled_target_point_cloud = cached_data
scanned_views_pts.append(downsampled_target_point_cloud)
scanned_coverages_rate.append(coverage_rate)
n_to_world_6d = PoseUtil.matrix_to_rotation_6d_numpy(np.asarray(n_to_world_pose[:3,:3]))
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)
nbv_idx, nbv_coverage_rate = nbv[0], nbv[1]
nbv_path = DataLoadUtil.get_path(self.root_dir, scene_name, nbv_idx)
cam_info = DataLoadUtil.load_cam_info(nbv_path)
best_frame_to_world = cam_info["cam_to_world"]
best_to_world_6d = PoseUtil.matrix_to_rotation_6d_numpy(np.asarray(best_frame_to_world[:3,:3]))
best_to_world_trans = best_frame_to_world[:3,3]
best_to_world_9d = np.concatenate([best_to_world_6d, best_to_world_trans], axis=0)
data_item = {
"scanned_pts": np.asarray(scanned_views_pts,dtype=np.float32),
"scanned_coverage_rate": scanned_coverages_rate,
"scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose,dtype=np.float32),
"best_coverage_rate": nbv_coverage_rate,
"best_to_world_pose_9d": np.asarray(best_to_world_9d,dtype=np.float32),
"max_coverage_rate": max_coverage_rate,
"scene_name": scene_name
}
# if self.type == namespace.Mode.TEST:
# diag = DataLoadUtil.get_bbox_diag(self.model_dir, scene_name)
# voxel_threshold = diag*0.02
# model_points_normals = DataLoadUtil.load_points_normals(self.root_dir, scene_name)
# pts_list = []
# for view in scanned_views:
# frame_idx = view[0]
# view_path = DataLoadUtil.get_path(self.root_dir, scene_name, frame_idx)
# point_cloud = DataLoadUtil.get_target_point_cloud_world_from_path(view_path, binocular=True)
# cam_params = DataLoadUtil.load_cam_info(view_path, binocular=True)
# sampled_point_cloud = ReconstructionUtil.filter_points(point_cloud, model_points_normals, cam_pose=cam_params["cam_to_world"], voxel_size=voxel_threshold, theta=self.filter_degree)
# pts_list.append(sampled_point_cloud)
# nL_to_world_pose = cam_params["cam_to_world"]
# nO_to_world_pose = cam_params["cam_to_world_O"]
# nO_to_nL_pose = np.dot(np.linalg.inv(nL_to_world_pose), nO_to_world_pose)
# data_item["scanned_target_pts_list"] = pts_list
# data_item["model_points_normals"] = model_points_normals
# data_item["voxel_threshold"] = voxel_threshold
# data_item["filter_degree"] = self.filter_degree
# data_item["scene_path"] = os.path.join(self.root_dir, scene_name)
# data_item["first_frame_to_world"] = np.asarray(first_frame_to_world, dtype=np.float32)
# data_item["nO_to_nL_pose"] = np.asarray(nO_to_nL_pose, dtype=np.float32)
return data_item
def __len__(self):
return len(self.datalist)
def get_collate_fn(self):
def collate_fn(batch):
collate_data = {}
collate_data["scanned_pts"] = [torch.tensor(item['scanned_pts']) for item in batch]
collate_data["scanned_n_to_world_pose_9d"] = [torch.tensor(item['scanned_n_to_world_pose_9d']) for item in batch]
collate_data["best_to_world_pose_9d"] = torch.stack([torch.tensor(item['best_to_world_pose_9d']) for item in batch])
if "first_frame_to_world" in batch[0]:
collate_data["first_frame_to_world"] = torch.stack([torch.tensor(item["first_frame_to_world"]) for item in batch])
for key in batch[0].keys():
if key not in ["scanned_pts", "scanned_n_to_world_pose_9d", "best_to_world_pose_9d", "first_frame_to_world"]:
collate_data[key] = [item[key] for item in batch]
return collate_data
return collate_fn
# -------------- Debug ---------------- #
if __name__ == "__main__":
import torch
seed = 0
torch.manual_seed(seed)
np.random.seed(seed)
config = {
"root_dir": "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/preprocessed_scenes/",
"model_dir": "/media/hofee/data/data/scaled_object_meshes",
"source": "nbv_reconstruction_dataset",
"split_file": "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/OmniObject3d_train.txt",
"load_from_preprocess": True,
"ratio": 0.5,
"batch_size": 2,
"filter_degree": 75,
"num_workers": 0,
"pts_num": 4096,
"type": namespace.Mode.TRAIN,
}
ds = NBVReconstructionDataset(config)
print(len(ds))
#ds.__getitem__(10)
dl = ds.get_loader(shuffle=True)
for idx, data in enumerate(dl):
data = ds.process_batch(data, "cuda:0")
print(data)
# ------ Debug Start ------
import ipdb;ipdb.set_trace()
# ------ Debug End ------
#
# for idx, data in enumerate(dl):
# cnt=0
# print(data["scene_name"])
# print(data["scanned_coverage_rate"])
# print(data["best_coverage_rate"])
# for pts in data["scanned_pts"][0]:
# #np.savetxt(f"pts_{cnt}.txt", pts)
# cnt+=1
# #np.savetxt("best_pts.txt", best_pts)
# for key, value in data.items():
# if isinstance(value, torch.Tensor):
# print(key, ":" ,value.shape)
# else:
# print(key, ":" ,len(value))
# if key == "scanned_n_to_world_pose_9d":
# for val in value:
# print(val.shape)
# if key == "scanned_pts":
# print("scanned_pts")
# for val in value:
# print(val.shape)
# cnt = 0
# for v in val:
# import ipdb;ipdb.set_trace()
# np.savetxt(f"pts_{cnt}.txt", v)
# cnt+=1
# print()