Spaces:
Runtime error
Runtime error
File size: 9,565 Bytes
3e06e1c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 |
# Copyright (c) OpenMMLab. All rights reserved.
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 PackDetInputs(BaseTransform):
"""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')``
"""
mapping_table = {
'gt_bboxes': 'bboxes',
'gt_bboxes_labels': 'labels',
'gt_masks': 'masks'
}
def __init__(self,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction')):
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:`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)
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
def __repr__(self) -> str:
repr_str = self.__class__.__name__
repr_str += f'(meta_keys={self.meta_keys})'
return repr_str
@TRANSFORMS.register_module()
class ToTensor:
"""Convert some results to :obj:`torch.Tensor` by given keys.
Args:
keys (Sequence[str]): Keys that need to be converted to Tensor.
"""
def __init__(self, keys):
self.keys = keys
def __call__(self, results):
"""Call function to convert data in results to :obj:`torch.Tensor`.
Args:
results (dict): Result dict contains the data to convert.
Returns:
dict: The result dict contains the data converted
to :obj:`torch.Tensor`.
"""
for key in self.keys:
results[key] = to_tensor(results[key])
return results
def __repr__(self):
return self.__class__.__name__ + f'(keys={self.keys})'
@TRANSFORMS.register_module()
class ImageToTensor:
"""Convert image to :obj:`torch.Tensor` by given keys.
The dimension order of input image is (H, W, C). The pipeline will convert
it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
(1, H, W).
Args:
keys (Sequence[str]): Key of images to be converted to Tensor.
"""
def __init__(self, keys):
self.keys = keys
def __call__(self, results):
"""Call function to convert image in results to :obj:`torch.Tensor` and
transpose the channel order.
Args:
results (dict): Result dict contains the image data to convert.
Returns:
dict: The result dict contains the image converted
to :obj:`torch.Tensor` and permuted to (C, H, W) order.
"""
for key in self.keys:
img = results[key]
if len(img.shape) < 3:
img = np.expand_dims(img, -1)
results[key] = to_tensor(img).permute(2, 0, 1).contiguous()
return results
def __repr__(self):
return self.__class__.__name__ + f'(keys={self.keys})'
@TRANSFORMS.register_module()
class Transpose:
"""Transpose some results by given keys.
Args:
keys (Sequence[str]): Keys of results to be transposed.
order (Sequence[int]): Order of transpose.
"""
def __init__(self, keys, order):
self.keys = keys
self.order = order
def __call__(self, results):
"""Call function to transpose the channel order of data in results.
Args:
results (dict): Result dict contains the data to transpose.
Returns:
dict: The result dict contains the data transposed to \
``self.order``.
"""
for key in self.keys:
results[key] = results[key].transpose(self.order)
return results
def __repr__(self):
return self.__class__.__name__ + \
f'(keys={self.keys}, order={self.order})'
@TRANSFORMS.register_module()
class WrapFieldsToLists:
"""Wrap fields of the data dictionary into lists for evaluation.
This class can be used as a last step of a test or validation
pipeline for single image evaluation or inference.
Example:
>>> test_pipeline = [
>>> dict(type='LoadImageFromFile'),
>>> dict(type='Normalize',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True),
>>> dict(type='Pad', size_divisor=32),
>>> dict(type='ImageToTensor', keys=['img']),
>>> dict(type='Collect', keys=['img']),
>>> dict(type='WrapFieldsToLists')
>>> ]
"""
def __call__(self, results):
"""Call function to wrap fields into lists.
Args:
results (dict): Result dict contains the data to wrap.
Returns:
dict: The result dict where value of ``self.keys`` are wrapped \
into list.
"""
# Wrap dict fields into lists
for key, val in results.items():
results[key] = [val]
return results
def __repr__(self):
return f'{self.__class__.__name__}()'
|