mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
788b37f78f
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers. ## Motivation Please describe the motivation of this PR and the goal you want to achieve through this PR. ## Modification Please briefly describe what modification is made in this PR. 1. add `NYUDataset`class 2. add script to process NYU dataset 3. add transforms for loading depth map 4. add docs & unittest ## BC-breaking (Optional) Does the modification introduce changes that break the backward-compatibility of the downstream repos? If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR. ## Use cases (Optional) If this PR introduces a new feature, it is better to list some use cases here, and update the documentation. ## Checklist 1. Pre-commit or other linting tools are used to fix the potential lint issues. 5. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness. 6. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D. 7. The documentation has been modified accordingly, like docstring or example tutorials.
113 lines
4.1 KiB
Python
113 lines
4.1 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
import warnings
|
|
|
|
import numpy as np
|
|
from mmcv.transforms import to_tensor
|
|
from mmcv.transforms.base import BaseTransform
|
|
from mmengine.structures import PixelData
|
|
|
|
from mmseg.registry import TRANSFORMS
|
|
from mmseg.structures import SegDataSample
|
|
|
|
|
|
@TRANSFORMS.register_module()
|
|
class PackSegInputs(BaseTransform):
|
|
"""Pack the inputs data for the semantic segmentation.
|
|
|
|
The ``img_meta`` item is always populated. The contents of the
|
|
``img_meta`` dictionary depends on ``meta_keys``. By default this includes:
|
|
|
|
- ``img_path``: filename of the image
|
|
|
|
- ``ori_shape``: original shape of the image as a tuple (h, w, c)
|
|
|
|
- ``img_shape``: shape of the image input to the network as a tuple \
|
|
(h, w, c). Note that images may be zero padded on the \
|
|
bottom/right if the batch tensor is larger than this shape.
|
|
|
|
- ``pad_shape``: shape of padded images
|
|
|
|
- ``scale_factor``: a float indicating the preprocessing scale
|
|
|
|
- ``flip``: a boolean indicating if image flip transform was used
|
|
|
|
- ``flip_direction``: the flipping direction
|
|
|
|
Args:
|
|
meta_keys (Sequence[str], optional): Meta keys to be packed from
|
|
``SegDataSample`` and collected in ``data[img_metas]``.
|
|
Default: ``('img_path', 'ori_shape',
|
|
'img_shape', 'pad_shape', 'scale_factor', 'flip',
|
|
'flip_direction')``
|
|
"""
|
|
|
|
def __init__(self,
|
|
meta_keys=('img_path', 'seg_map_path', 'ori_shape',
|
|
'img_shape', 'pad_shape', 'scale_factor', 'flip',
|
|
'flip_direction', 'reduce_zero_label')):
|
|
self.meta_keys = meta_keys
|
|
|
|
def transform(self, results: dict) -> dict:
|
|
"""Method to pack the input data.
|
|
|
|
Args:
|
|
results (dict): Result dict from the data pipeline.
|
|
|
|
Returns:
|
|
dict:
|
|
|
|
- 'inputs' (obj:`torch.Tensor`): The forward data of models.
|
|
- 'data_sample' (obj:`SegDataSample`): The annotation info of the
|
|
sample.
|
|
"""
|
|
packed_results = dict()
|
|
if 'img' in results:
|
|
img = results['img']
|
|
if len(img.shape) < 3:
|
|
img = np.expand_dims(img, -1)
|
|
if not img.flags.c_contiguous:
|
|
img = to_tensor(np.ascontiguousarray(img.transpose(2, 0, 1)))
|
|
else:
|
|
img = img.transpose(2, 0, 1)
|
|
img = to_tensor(img).contiguous()
|
|
packed_results['inputs'] = img
|
|
|
|
data_sample = SegDataSample()
|
|
if 'gt_seg_map' in results:
|
|
if len(results['gt_seg_map'].shape) == 2:
|
|
data = to_tensor(results['gt_seg_map'][None,
|
|
...].astype(np.int64))
|
|
else:
|
|
warnings.warn('Please pay attention your ground truth '
|
|
'segmentation map, usually the segmentation '
|
|
'map is 2D, but got '
|
|
f'{results["gt_seg_map"].shape}')
|
|
data = to_tensor(results['gt_seg_map'].astype(np.int64))
|
|
gt_sem_seg_data = dict(data=data)
|
|
data_sample.gt_sem_seg = PixelData(**gt_sem_seg_data)
|
|
|
|
if 'gt_edge_map' in results:
|
|
gt_edge_data = dict(
|
|
data=to_tensor(results['gt_edge_map'][None,
|
|
...].astype(np.int64)))
|
|
data_sample.set_data(dict(gt_edge_map=PixelData(**gt_edge_data)))
|
|
|
|
if 'gt_depth_map' in results:
|
|
gt_depth_data = dict(
|
|
data=to_tensor(results['gt_depth_map'][None, ...]))
|
|
data_sample.set_data(dict(gt_depth_map=PixelData(**gt_depth_data)))
|
|
|
|
img_meta = {}
|
|
for key in self.meta_keys:
|
|
if key in results:
|
|
img_meta[key] = results[key]
|
|
data_sample.set_metainfo(img_meta)
|
|
packed_results['data_samples'] = data_sample
|
|
|
|
return packed_results
|
|
|
|
def __repr__(self) -> str:
|
|
repr_str = self.__class__.__name__
|
|
repr_str += f'(meta_keys={self.meta_keys})'
|
|
return repr_str
|