159 lines
6.2 KiB
Python
159 lines
6.2 KiB
Python
import os
|
|
import numpy as np
|
|
|
|
from torch.utils.data import Dataset
|
|
from torch_geometric.datasets import ShapeNet
|
|
|
|
from itertools import repeat, product
|
|
from collections import defaultdict
|
|
|
|
import os
|
|
from tqdm import tqdm
|
|
import os.path as osp
|
|
import glob
|
|
|
|
import torch
|
|
from torch_geometric.data import (Data, InMemoryDataset, download_url,
|
|
extract_zip)
|
|
from torch.utils.data import Dataset
|
|
from torch_geometric.read import read_txt_array
|
|
from torch_geometric.datasets import ShapeNet
|
|
|
|
from torch_geometric.read import parse_txt_array
|
|
|
|
|
|
class CustomShapeNet(InMemoryDataset):
|
|
|
|
categories = {key: val for val, key in enumerate(['Box', 'Cone', 'Cylinder', 'Sphere'])}
|
|
|
|
def __init__(self, root, train=True, transform=None, pre_filter=None, pre_transform=None, **kwargs):
|
|
super(CustomShapeNet, self).__init__(root, transform, pre_transform, pre_filter)
|
|
path = self.processed_paths[0] if train else self.processed_paths[1]
|
|
self.data, self.slices = torch.load(path)
|
|
print("Initialized")
|
|
|
|
@property
|
|
def raw_file_names(self):
|
|
# Maybe add more data like validation sets
|
|
return ['train', 'test']
|
|
|
|
@property
|
|
def processed_file_names(self):
|
|
return [f'{x}.pt' for x in self.raw_file_names]
|
|
|
|
def download(self):
|
|
dir_count = len([name for name in os.listdir(self.raw_dir) if os.path.isdir(os.path.join(self.raw_dir, name))])
|
|
print(f'{dir_count} folders have been found....')
|
|
if dir_count:
|
|
return dir_count
|
|
raise IOError("No raw pointclouds have been found.")
|
|
|
|
@property
|
|
def num_classes(self):
|
|
return len(self.categories)
|
|
|
|
def _load_dataset(self):
|
|
data, slices = None, None
|
|
while True:
|
|
try:
|
|
filepath = os.path.join(self.root, self.processed_dir, f'{"train" if self.train else "test"}.pt')
|
|
data, slices = torch.load(filepath)
|
|
print('Dataset Loaded')
|
|
break
|
|
except FileNotFoundError:
|
|
self.process()
|
|
continue
|
|
return data, slices
|
|
|
|
def process(self, delimiter=' '):
|
|
# idx = self.categories[self.category]
|
|
# paths = [osp.join(path, idx) for path in self.raw_paths]
|
|
|
|
datasets = defaultdict(list)
|
|
for idx, setting in enumerate(self.raw_file_names):
|
|
for pointcloud in tqdm(os.scandir(os.path.join(self.raw_dir, setting))):
|
|
if not os.path.isdir(pointcloud):
|
|
continue
|
|
for element in glob.glob(os.path.join(pointcloud.path, '*.dat')):
|
|
if os.path.split(element)[-1] not in ['pc.dat']:
|
|
# Assign training data to the data container
|
|
# Following the original logic;
|
|
# y should be the label;
|
|
# pos should be the six dimensional vector describing: !its pos not points!!
|
|
# x,y,z,x_rot,y_rot,z_rot
|
|
y_raw = os.path.splitext(element)[0].split('_')[-2]
|
|
with open(element,'r') as f:
|
|
headers = f.__next__()
|
|
# Check if there are no useable nodes in this file, header says 0.
|
|
if not int(headers.rstrip().split(delimiter)[0]):
|
|
continue
|
|
# Get the y - Label
|
|
|
|
# Iterate over all rows
|
|
src = [[float(x) if x not in ['-nan(ind)', 'nan(ind)'] else 0
|
|
for x in line.rstrip().split(delimiter)[None:None]] for line in f if line != '']
|
|
points = torch.tensor(src, dtype=None).squeeze()
|
|
if not len(points.shape) > 1:
|
|
continue
|
|
# pos = points[:, :3]
|
|
# norm = points[:, 3:]
|
|
y_all = [self.categories[y_raw]] * points.shape[0]
|
|
y = torch.as_tensor(y_all, dtype=torch.int)
|
|
# points = torch.as_tensor(points, dtype=torch.float)
|
|
# norm = torch.as_tensor(norm, dtype=torch.float)
|
|
data = Data(y=y, pos=points[:, :3])
|
|
# , points=points, norm=points[:3], )
|
|
# ToDo: ANy filter to apply? Then do it here.
|
|
if self.pre_filter is not None and not self.pre_filter(data):
|
|
data = self.pre_filter(data)
|
|
raise NotImplementedError
|
|
# ToDo: ANy transformation to apply? Then do it here.
|
|
if self.pre_transform is not None:
|
|
data = self.pre_transform(data)
|
|
raise NotImplementedError
|
|
datasets[setting].append(data)
|
|
|
|
os.makedirs(self.processed_dir, exist_ok=True)
|
|
torch.save(self.collate(datasets[setting]), self.processed_paths[idx])
|
|
|
|
def __repr__(self):
|
|
return f'{self.__class__.__name__}({len(self)})'
|
|
|
|
|
|
class ShapeNetPartSegDataset(Dataset):
|
|
"""
|
|
Resample raw point cloud to fixed number of points.
|
|
Map raw label from range [1, N] to [0, N-1].
|
|
"""
|
|
def __init__(self, root_dir, train=True, transform=None, npoints=1024):
|
|
super(ShapeNetPartSegDataset, self).__init__()
|
|
self.npoints = npoints
|
|
self.dataset = CustomShapeNet(root=root_dir, train=train, transform=transform)
|
|
|
|
def __getitem__(self, index):
|
|
data = self.dataset[index]
|
|
points, labels = data.pos, data.y
|
|
|
|
# Resample to fixed number of points
|
|
try:
|
|
choice = np.random.choice(points.shape[0], self.npoints, replace=True)
|
|
except ValueError:
|
|
choice = []
|
|
|
|
points, labels = points[choice, :], labels[choice]
|
|
|
|
labels -= 1 if self.num_classes() in labels else 0 # Map label from [1, C] to [0, C-1]
|
|
|
|
sample = {
|
|
'points': points, # torch.Tensor (n, 3)
|
|
'labels': labels # torch.Tensor (n,)
|
|
}
|
|
|
|
return sample
|
|
|
|
def __len__(self):
|
|
return len(self.dataset)
|
|
|
|
def num_classes(self):
|
|
return self.dataset.num_classes
|