File size: 11,156 Bytes
b13b124 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 |
import torch
import torch.nn as nn
import torch.nn.functional as F
from mmseg.core import add_prefix
from mmseg.ops import resize
from .. import builder
from ..builder import SEGMENTORS
from .base import BaseSegmentor
@SEGMENTORS.register_module()
class EncoderDecoder(BaseSegmentor):
"""Encoder Decoder segmentors.
EncoderDecoder typically consists of backbone, decode_head, auxiliary_head.
Note that auxiliary_head is only used for deep supervision during training,
which could be dumped during inference.
"""
def __init__(self,
backbone,
decode_head,
neck=None,
auxiliary_head=None,
train_cfg=None,
test_cfg=None,
pretrained=None):
super(EncoderDecoder, self).__init__()
self.backbone = builder.build_backbone(backbone)
if neck is not None:
self.neck = builder.build_neck(neck)
self._init_decode_head(decode_head)
self._init_auxiliary_head(auxiliary_head)
self.train_cfg = train_cfg
self.test_cfg = test_cfg
self.init_weights(pretrained=pretrained)
assert self.with_decode_head
def _init_decode_head(self, decode_head):
"""Initialize ``decode_head``"""
self.decode_head = builder.build_head(decode_head)
self.align_corners = self.decode_head.align_corners
self.num_classes = self.decode_head.num_classes
def _init_auxiliary_head(self, auxiliary_head):
"""Initialize ``auxiliary_head``"""
if auxiliary_head is not None:
if isinstance(auxiliary_head, list):
self.auxiliary_head = nn.ModuleList()
for head_cfg in auxiliary_head:
self.auxiliary_head.append(builder.build_head(head_cfg))
else:
self.auxiliary_head = builder.build_head(auxiliary_head)
def init_weights(self, pretrained=None):
"""Initialize the weights in backbone and heads.
Args:
pretrained (str, optional): Path to pre-trained weights.
Defaults to None.
"""
super(EncoderDecoder, self).init_weights(pretrained)
self.backbone.init_weights(pretrained=pretrained)
self.decode_head.init_weights()
if self.with_auxiliary_head:
if isinstance(self.auxiliary_head, nn.ModuleList):
for aux_head in self.auxiliary_head:
aux_head.init_weights()
else:
self.auxiliary_head.init_weights()
def extract_feat(self, img):
"""Extract features from images."""
x = self.backbone(img)
if self.with_neck:
x = self.neck(x)
return x
def encode_decode(self, img, img_metas):
"""Encode images with backbone and decode into a semantic segmentation
map of the same size as input."""
x = self.extract_feat(img)
out = self._decode_head_forward_test(x, img_metas)
out = resize(
input=out,
size=img.shape[2:],
mode='bilinear',
align_corners=self.align_corners)
return out
def _decode_head_forward_train(self, x, img_metas, gt_semantic_seg):
"""Run forward function and calculate loss for decode head in
training."""
losses = dict()
loss_decode = self.decode_head.forward_train(x, img_metas,
gt_semantic_seg,
self.train_cfg)
losses.update(add_prefix(loss_decode, 'decode'))
return losses
def _decode_head_forward_test(self, x, img_metas):
"""Run forward function and calculate loss for decode head in
inference."""
seg_logits = self.decode_head.forward_test(x, img_metas, self.test_cfg)
return seg_logits
def _auxiliary_head_forward_train(self, x, img_metas, gt_semantic_seg):
"""Run forward function and calculate loss for auxiliary head in
training."""
losses = dict()
if isinstance(self.auxiliary_head, nn.ModuleList):
for idx, aux_head in enumerate(self.auxiliary_head):
loss_aux = aux_head.forward_train(x, img_metas,
gt_semantic_seg,
self.train_cfg)
losses.update(add_prefix(loss_aux, f'aux_{idx}'))
else:
loss_aux = self.auxiliary_head.forward_train(
x, img_metas, gt_semantic_seg, self.train_cfg)
losses.update(add_prefix(loss_aux, 'aux'))
return losses
def forward_dummy(self, img):
"""Dummy forward function."""
seg_logit = self.encode_decode(img, None)
return seg_logit
def forward_train(self, img, img_metas, gt_semantic_seg):
"""Forward function for training.
Args:
img (Tensor): Input images.
img_metas (list[dict]): List of image info dict where each dict
has: 'img_shape', 'scale_factor', 'flip', and may also contain
'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
For details on the values of these keys see
`mmseg/datasets/pipelines/formatting.py:Collect`.
gt_semantic_seg (Tensor): Semantic segmentation masks
used if the architecture supports semantic segmentation task.
Returns:
dict[str, Tensor]: a dictionary of loss components
"""
x = self.extract_feat(img)
losses = dict()
loss_decode = self._decode_head_forward_train(x, img_metas,
gt_semantic_seg)
losses.update(loss_decode)
if self.with_auxiliary_head:
loss_aux = self._auxiliary_head_forward_train(
x, img_metas, gt_semantic_seg)
losses.update(loss_aux)
return losses
# TODO refactor
def slide_inference(self, img, img_meta, rescale):
"""Inference by sliding-window with overlap.
If h_crop > h_img or w_crop > w_img, the small patch will be used to
decode without padding.
"""
h_stride, w_stride = self.test_cfg.stride
h_crop, w_crop = self.test_cfg.crop_size
batch_size, _, h_img, w_img = img.size()
#print(img.size())
num_classes = self.num_classes
h_grids = max(h_img - h_crop + h_stride - 1, 0) // h_stride + 1
w_grids = max(w_img - w_crop + w_stride - 1, 0) // w_stride + 1
preds = img.new_zeros((batch_size, num_classes, h_img, w_img))
count_mat = img.new_zeros((batch_size, 1, h_img, w_img))
for h_idx in range(h_grids):
for w_idx in range(w_grids):
y1 = h_idx * h_stride
x1 = w_idx * w_stride
y2 = min(y1 + h_crop, h_img)
x2 = min(x1 + w_crop, w_img)
y1 = max(y2 - h_crop, 0)
x1 = max(x2 - w_crop, 0)
crop_img = img[:, :, y1:y2, x1:x2]
crop_seg_logit = self.encode_decode(crop_img, img_meta)
preds += F.pad(crop_seg_logit,
(int(x1), int(preds.shape[3] - x2), int(y1),
int(preds.shape[2] - y2)))
count_mat[:, :, y1:y2, x1:x2] += 1
assert (count_mat == 0).sum() == 0
if torch.onnx.is_in_onnx_export():
# cast count_mat to constant while exporting to ONNX
count_mat = torch.from_numpy(
count_mat.cpu().detach().numpy()).to(device=img.device)
preds = preds / count_mat
if rescale:
preds = resize(
preds,
size=img_meta[0]['ori_shape'][:2],
mode='bilinear',
align_corners=self.align_corners,
warning=False)
return preds
def whole_inference(self, img, img_meta, rescale):
"""Inference with full image."""
seg_logit = self.encode_decode(img, img_meta)
if rescale:
seg_logit = resize(
seg_logit,
size=img_meta[0]['ori_shape'][:2],
mode='bilinear',
align_corners=self.align_corners,
warning=False)
return seg_logit
def inference(self, img, img_meta, rescale):
"""Inference with slide/whole style.
Args:
img (Tensor): The input image of shape (N, 3, H, W).
img_meta (dict): Image info dict where each dict has: 'img_shape',
'scale_factor', 'flip', and may also contain
'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
For details on the values of these keys see
`mmseg/datasets/pipelines/formatting.py:Collect`.
rescale (bool): Whether rescale back to original shape.
Returns:
Tensor: The output segmentation map.
"""
assert self.test_cfg.mode in ['slide', 'whole']
ori_shape = img_meta[0]['ori_shape']
assert all(_['ori_shape'] == ori_shape for _ in img_meta)
if self.test_cfg.mode == 'slide':
seg_logit = self.slide_inference(img, img_meta, rescale)
else:
seg_logit = self.whole_inference(img, img_meta, rescale)
output = F.softmax(seg_logit, dim=1)
flip = img_meta[0]['flip']
if flip:
flip_direction = img_meta[0]['flip_direction']
assert flip_direction in ['horizontal', 'vertical']
if flip_direction == 'horizontal':
output = output.flip(dims=(3, ))
elif flip_direction == 'vertical':
output = output.flip(dims=(2, ))
return output
def simple_test(self, img, img_meta, rescale=True):
"""Simple test with single image."""
seg_logit = self.inference(img, img_meta, rescale)
seg_pred = seg_logit.argmax(dim=1)
if torch.onnx.is_in_onnx_export():
# our inference backend only support 4D output
seg_pred = seg_pred.unsqueeze(0)
return seg_pred
seg_pred = seg_pred.cpu().numpy()
# unravel batch dim
seg_pred = list(seg_pred)
return seg_pred
def aug_test(self, imgs, img_metas, rescale=True):
"""Test with augmentations.
Only rescale=True is supported.
"""
# aug_test rescale all imgs back to ori_shape for now
assert rescale
# to save memory, we get augmented seg logit inplace
seg_logit = self.inference(imgs[0], img_metas[0], rescale)
for i in range(1, len(imgs)):
cur_seg_logit = self.inference(imgs[i], img_metas[i], rescale)
seg_logit += cur_seg_logit
seg_logit /= len(imgs)
seg_pred = seg_logit.argmax(dim=1)
seg_pred = seg_pred.cpu().numpy()
# unravel batch dim
seg_pred = list(seg_pred)
return seg_pred
|