mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
284 lines
11 KiB
Python
284 lines
11 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
|
|
from mmseg.core import add_prefix
|
|
from mmseg.ops import resize
|
|
from mmseg.registry import MODELS
|
|
from .base import BaseSegmentor
|
|
|
|
|
|
@MODELS.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,
|
|
preprocess_cfg=None,
|
|
pretrained=None,
|
|
init_cfg=None):
|
|
super(EncoderDecoder, self).__init__(
|
|
preprocess_cfg=preprocess_cfg, init_cfg=init_cfg)
|
|
if pretrained is not None:
|
|
assert backbone.get('pretrained') is None, \
|
|
'both backbone and segmentor set pretrained weight'
|
|
backbone.pretrained = pretrained
|
|
self.backbone = MODELS.build(backbone)
|
|
if neck is not None:
|
|
self.neck = MODELS.build(neck)
|
|
self._init_decode_head(decode_head)
|
|
self._init_auxiliary_head(auxiliary_head)
|
|
|
|
self.train_cfg = train_cfg
|
|
self.test_cfg = test_cfg
|
|
|
|
assert self.with_decode_head
|
|
|
|
def _init_decode_head(self, decode_head):
|
|
"""Initialize ``decode_head``"""
|
|
self.decode_head = MODELS.build(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(MODELS.build(head_cfg))
|
|
else:
|
|
self.auxiliary_head = MODELS.build(auxiliary_head)
|
|
|
|
def extract_feat(self, batch_inputs):
|
|
"""Extract features from images."""
|
|
x = self.backbone(batch_inputs)
|
|
if self.with_neck:
|
|
x = self.neck(x)
|
|
return x
|
|
|
|
def encode_decode(self, batch_inputs, batch_img_metas):
|
|
"""Encode images with backbone and decode into a semantic segmentation
|
|
map of the same size as input."""
|
|
x = self.extract_feat(batch_inputs)
|
|
out = self._decode_head_forward_test(x, batch_img_metas)
|
|
out = resize(
|
|
input=out,
|
|
size=batch_inputs.shape[2:],
|
|
mode='bilinear',
|
|
align_corners=self.align_corners)
|
|
return out
|
|
|
|
def _decode_head_forward_train(self, batch_inputs, batch_data_samples):
|
|
"""Run forward function and calculate loss for decode head in
|
|
training."""
|
|
losses = dict()
|
|
loss_decode = self.decode_head.forward_train(batch_inputs,
|
|
batch_data_samples,
|
|
self.train_cfg)
|
|
|
|
losses.update(add_prefix(loss_decode, 'decode'))
|
|
return losses
|
|
|
|
def _decode_head_forward_test(self, batch_inputs, batch_img_metas):
|
|
"""Run forward function and calculate loss for decode head in
|
|
inference."""
|
|
seg_logits = self.decode_head.forward_test(batch_inputs,
|
|
batch_img_metas,
|
|
self.test_cfg)
|
|
return seg_logits
|
|
|
|
def _auxiliary_head_forward_train(self, batch_inputs, batch_data_samples):
|
|
"""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(batch_inputs,
|
|
batch_data_samples,
|
|
self.train_cfg)
|
|
losses.update(add_prefix(loss_aux, f'aux_{idx}'))
|
|
else:
|
|
loss_aux = self.auxiliary_head.forward_train(
|
|
batch_inputs, batch_data_samples, self.train_cfg)
|
|
losses.update(add_prefix(loss_aux, 'aux'))
|
|
|
|
return losses
|
|
|
|
def forward_dummy(self, batch_inputs, batch_img_metas):
|
|
"""Dummy forward function."""
|
|
seg_logit = self.encode_decode(batch_inputs, batch_img_metas)
|
|
|
|
return seg_logit
|
|
|
|
def forward_train(self, batch_inputs, batch_data_samples):
|
|
"""Forward function for training.
|
|
|
|
Args:
|
|
img (Tensor): Input images.
|
|
batch_data_samples (list[:obj:`SegDataSample`]): The seg
|
|
data samples. It usually includes information such
|
|
as `img_metas` or `gt_semantic_seg`.
|
|
|
|
Returns:
|
|
dict[str, Tensor]: a dictionary of loss components
|
|
"""
|
|
|
|
x = self.extract_feat(batch_inputs)
|
|
|
|
losses = dict()
|
|
|
|
loss_decode = self._decode_head_forward_train(x, batch_data_samples)
|
|
losses.update(loss_decode)
|
|
|
|
if self.with_auxiliary_head:
|
|
loss_aux = self._auxiliary_head_forward_train(
|
|
x, batch_data_samples)
|
|
losses.update(loss_aux)
|
|
|
|
return losses
|
|
|
|
# TODO refactor
|
|
def slide_inference(self, batch_inputs, batch_img_metas, 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.
|
|
|
|
Args:
|
|
batch_inputs (tensor): the tensor should have a shape NxCxHxW,
|
|
which contains all images in the batch.
|
|
batch_img_metas (list[dict]): Meta information of each image, e.g.,
|
|
image size, scaling factor, etc.
|
|
|
|
Returns:
|
|
tensor: get seg_logit.
|
|
"""
|
|
|
|
h_stride, w_stride = self.test_cfg.stride
|
|
h_crop, w_crop = self.test_cfg.crop_size
|
|
batch_size, _, h_img, w_img = batch_inputs.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 = batch_inputs.new_zeros((batch_size, num_classes, h_img, w_img))
|
|
count_mat = batch_inputs.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 = batch_inputs[:, :, y1:y2, x1:x2]
|
|
crop_seg_logit = self.encode_decode(crop_img, batch_img_metas)
|
|
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
|
|
preds = preds / count_mat
|
|
if rescale:
|
|
preds = resize(
|
|
preds,
|
|
size=batch_img_metas[0]['ori_shape'][:2],
|
|
mode='bilinear',
|
|
align_corners=self.align_corners,
|
|
warning=False)
|
|
return preds
|
|
|
|
def whole_inference(self, batch_inputs, batch_img_metas, rescale):
|
|
"""Inference with full image."""
|
|
|
|
seg_logit = self.encode_decode(batch_inputs, batch_img_metas)
|
|
if rescale:
|
|
size = batch_img_metas[0]['ori_shape'][:2]
|
|
seg_logit = resize(
|
|
seg_logit,
|
|
size=size,
|
|
mode='bilinear',
|
|
align_corners=self.align_corners,
|
|
warning=False)
|
|
|
|
return seg_logit
|
|
|
|
def inference(self, batch_inputs, batch_img_metas, rescale):
|
|
"""Inference with slide/whole style.
|
|
|
|
Args:
|
|
batch_inputs (Tensor): The input image of shape (N, 3, H, W).
|
|
batch_img_metas (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 = batch_img_metas[0]['ori_shape']
|
|
assert all(_['ori_shape'] == ori_shape for _ in batch_img_metas)
|
|
if self.test_cfg.mode == 'slide':
|
|
seg_logit = self.slide_inference(batch_inputs, batch_img_metas,
|
|
rescale)
|
|
else:
|
|
seg_logit = self.whole_inference(batch_inputs, batch_img_metas,
|
|
rescale)
|
|
output = F.softmax(seg_logit, dim=1)
|
|
flip = batch_img_metas[0].get('flip', None)
|
|
if flip:
|
|
flip_direction = batch_img_metas[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, batch_inputs, batch_img_metas, rescale=True):
|
|
"""Simple test with single image."""
|
|
results_dict = dict()
|
|
seg_logit = self.inference(batch_inputs, batch_img_metas, rescale)
|
|
results_dict['seg_logits'] = seg_logit
|
|
seg_pred = seg_logit.argmax(dim=1)
|
|
seg_pred = seg_pred.cpu().numpy()
|
|
results_dict['pred_sem_seg'] = seg_pred
|
|
results_list = self.postprocess_result(results_dict)
|
|
return results_list
|
|
|
|
def aug_test(self, batch_inputs, batch_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(batch_inputs[0], batch_img_metas[0],
|
|
rescale)
|
|
for i in range(1, len(batch_inputs)):
|
|
cur_seg_logit = self.inference(batch_inputs[i], batch_img_metas[i],
|
|
rescale)
|
|
seg_logit += cur_seg_logit
|
|
seg_logit /= len(batch_inputs)
|
|
seg_pred = seg_logit.argmax(dim=1)
|
|
# unravel batch dim
|
|
seg_pred = list(seg_pred)
|
|
return seg_pred
|