new_nbv_rec/core/seq_dataset.py
2025-05-13 09:03:38 +08:00

210 lines
8.0 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
@stereotype.dataset("seq_reconstruction_dataset")
class SeqReconstructionDataset(BaseDataset):
def __init__(self, config):
super(SeqReconstructionDataset, 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:
scale_ratio = 1
self.datalist = self.datalist*scale_ratio
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()
if not os.path.exists(os.path.join(self.root_dir, scene_name)):
continue
scene_name_list.append(scene_name)
return scene_name_list
def get_scene_name_list(self):
return self.scene_name_list
def get_datalist(self):
datalist = []
total = len(self.scene_name_list)
for idx, scene_name in enumerate(self.scene_name_list):
print(f"processing {scene_name} ({idx}/{total})")
scene_max_cr_idx = 0
frame_len = DataLoadUtil.get_scene_seq_length(self.root_dir, scene_name)
for i in range(10,frame_len):
path = DataLoadUtil.get_path(self.root_dir, scene_name, i)
pts = DataLoadUtil.load_from_preprocessed_pts(path, "npy")
print(pts.shape)
if pts.shape[0] == 0:
continue
else:
break
print(i)
datalist.append({
"scene_name": scene_name,
"first_frame": i,
"best_seq_len": -1,
"max_coverage_rate": 1.0,
"label_idx": scene_max_cr_idx,
})
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}")
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"]
best_seq_len = data_item_info["best_seq_len"]
scene_name = data_item_info["scene_name"]
(
scanned_views_pts,
scanned_coverages_rate,
scanned_n_to_world_pose,
) = ([], [], [])
view = data_item_info["first_frame"]
frame_idx = view
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"]
target_point_cloud = (
DataLoadUtil.load_from_preprocessed_pts(view_path)
)
downsampled_target_point_cloud = PtsUtil.random_downsample_point_cloud(
target_point_cloud, self.pts_num
)
scanned_views_pts.append(downsampled_target_point_cloud)
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)
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_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)
"best_seq_len": best_seq_len, # Int
"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
def __len__(self):
return len(self.datalist)
# -------------- Debug ---------------- #
if __name__ == "__main__":
import torch
from tqdm import tqdm
import pickle
import os
seed = 0
torch.manual_seed(seed)
np.random.seed(seed)
config = {
"root_dir": "/media/hofee/data/data/test_bottle/view",
"source": "seq_reconstruction_dataset",
"split_file": "/media/hofee/data/data/test_bottle/test_bottle.txt",
"load_from_preprocess": True,
"filter_degree": 75,
"num_workers": 0,
"pts_num": 8192,
"type": namespace.Mode.TEST,
}
output_dir = "/media/hofee/data/data/test_bottle/preprocessed_dataset"
os.makedirs(output_dir, exist_ok=True)
ds = SeqReconstructionDataset(config)
for i in tqdm(range(len(ds)), desc="processing dataset"):
output_path = os.path.join(output_dir, f"item_{i}.pkl")
item = ds.__getitem__(i)
for key, value in item.items():
if isinstance(value, np.ndarray):
item[key] = value.tolist()
#import ipdb; ipdb.set_trace()
with open(output_path, "wb") as f:
pickle.dump(item, f)