mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
ff95416c3b
## Motivation 1. It is used to save the segmentation predictions as files and upload these files to a test server ## Modification 1. Add output_file and format only in `IoUMetric` ## BC-breaking (Optional) No ## 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. 3. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness. 4. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D. 5. The documentation has been modified accordingly, like docstring or example tutorials.
108 lines
3.9 KiB
Python
108 lines
3.9 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)))
|
|
|
|
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
|