File size: 5,522 Bytes
e8f2571 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
from ..formatting import ImageToTensor, PackDetInputs, ToTensor, Transpose
import numpy as np
from mmcv.transforms import to_tensor
from mmcv.transforms.base import BaseTransform
from mmengine.structures import InstanceData, PixelData
from mmdet.registry import TRANSFORMS
from mmdet.structures import DetDataSample
from mmdet.structures.bbox import BaseBoxes
@TRANSFORMS.register_module()
class PackDetInputsPiexlTarget(PackDetInputs):
"""Pack the inputs data for the detection / semantic segmentation /
panoptic segmentation.
The ``img_meta`` item is always populated. The contents of the
``img_meta`` dictionary depends on ``meta_keys``. By default this includes:
- ``img_id``: id of the image
- ``img_path``: path to the image file
- ``ori_shape``: original shape of the image as a tuple (h, w)
- ``img_shape``: shape of the image input to the network as a tuple \
(h, w). Note that images may be zero padded on the \
bottom/right if the batch tensor is larger than this shape.
- ``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 converted to
``mmcv.DataContainer`` and collected in ``data[img_metas]``.
Default: ``('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction')``
"""
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:`DetDataSample`): 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)
# To improve the computational speed by by 3-5 times, apply:
# If image is not contiguous, use
# `numpy.transpose()` followed by `numpy.ascontiguousarray()`
# If image is already contiguous, use
# `torch.permute()` followed by `torch.contiguous()`
# Refer to https://github.com/open-mmlab/mmdetection/pull/9533
# for more details
if not img.flags.c_contiguous:
img = np.ascontiguousarray(img.transpose(2, 0, 1))
img = to_tensor(img)
else:
img = to_tensor(img).permute(2, 0, 1).contiguous()
packed_results['inputs'] = img
if 'gt_ignore_flags' in results:
valid_idx = np.where(results['gt_ignore_flags'] == 0)[0]
ignore_idx = np.where(results['gt_ignore_flags'] == 1)[0]
data_sample = DetDataSample()
instance_data = InstanceData()
ignore_instance_data = InstanceData()
for key in self.mapping_table.keys():
if key not in results:
continue
if key == 'gt_masks' or isinstance(results[key], BaseBoxes):
if 'gt_ignore_flags' in results:
instance_data[
self.mapping_table[key]] = results[key][valid_idx]
ignore_instance_data[
self.mapping_table[key]] = results[key][ignore_idx]
else:
instance_data[self.mapping_table[key]] = results[key]
else:
if 'gt_ignore_flags' in results:
instance_data[self.mapping_table[key]] = to_tensor(
results[key][valid_idx])
ignore_instance_data[self.mapping_table[key]] = to_tensor(
results[key][ignore_idx])
else:
instance_data[self.mapping_table[key]] = to_tensor(
results[key])
data_sample.gt_instances = instance_data
data_sample.ignored_instances = ignore_instance_data
if 'proposals' in results:
proposals = InstanceData(
bboxes=to_tensor(results['proposals']),
scores=to_tensor(results['proposals_scores']))
data_sample.proposals = proposals
if 'gt_seg_map' in results:
gt_sem_seg_data = dict(
sem_seg=to_tensor(results['gt_seg_map'][None, ...].copy()))
data_sample.gt_sem_seg = PixelData(**gt_sem_seg_data)
if 'gt_seg' in results:
if 'gt_abu' in results:
gt_pixel_data = dict(
seg=to_tensor(results['gt_seg'][None, ...].copy()),
abu=to_tensor(results['gt_abu'][None, ...].copy()),
)
else:
gt_pixel_data = dict(
seg=to_tensor(results['gt_seg'][None, ...].copy()),
)
data_sample.gt_pixel = PixelData(**gt_pixel_data)
img_meta = {}
for key in self.meta_keys:
assert key in results, f'`{key}` is not found in `results`, ' \
f'the valid keys are {list(results)}.'
img_meta[key] = results[key]
data_sample.set_metainfo(img_meta)
packed_results['data_samples'] = data_sample
return packed_results |