mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-15 20:33:59 +08:00
Brent YiandEthan Weber
ad8599aad0
* Add missing __init__.py files * fixing lint Co-authored-by: Ethan Weber <eweb0124@gmail.com>
54 lines
2.0 KiB
Python
54 lines
2.0 KiB
Python
# Copyright 2022 The Nerfstudio Team. All rights reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
"""
|
|
Semantic dataset.
|
|
"""
|
|
|
|
from typing import Dict
|
|
|
|
import torch
|
|
|
|
from nerfstudio.data.dataparsers.base_dataparser import DataparserOutputs, Semantics
|
|
from nerfstudio.data.datasets.base_dataset import InputDataset
|
|
from nerfstudio.data.utils.data_utils import get_semantics_and_mask_tensors_from_path
|
|
|
|
|
|
class SemanticDataset(InputDataset):
|
|
"""Dataset that returns images and semantics and masks.
|
|
|
|
Args:
|
|
dataparser_outputs: description of where and how to read input images.
|
|
"""
|
|
|
|
def __init__(self, dataparser_outputs: DataparserOutputs):
|
|
super().__init__(dataparser_outputs)
|
|
assert "semantics" in dataparser_outputs.metadata.keys() and isinstance(
|
|
dataparser_outputs.metadata["semantics"], Semantics
|
|
)
|
|
self.semantics = dataparser_outputs.metadata["semantics"]
|
|
self.mask_indices = torch.tensor(
|
|
[self.semantics.classes.index(mask_class) for mask_class in self.semantics.mask_classes]
|
|
).view(1, 1, -1)
|
|
|
|
def get_metadata(self, data: Dict) -> Dict:
|
|
# handle mask
|
|
filepath = self.semantics.filenames[data["image_idx"]]
|
|
semantic_label, mask = get_semantics_and_mask_tensors_from_path(
|
|
filepath=filepath, mask_indices=self.mask_indices
|
|
)
|
|
if "mask" in data.keys():
|
|
mask = mask & data["mask"]
|
|
return {"mask": mask, "semantics": semantic_label}
|