File size: 6,504 Bytes
985cc7f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import numpy as np
import torch
from mmcv import ConfigDict
from torch import nn

from mmseg.models import BACKBONES, HEADS, build_segmentor
from mmseg.models.decode_heads.cascade_decode_head import BaseCascadeDecodeHead
from mmseg.models.decode_heads.decode_head import BaseDecodeHead


def _demo_mm_inputs(input_shape=(1, 3, 8, 16), num_classes=10):
    """Create a superset of inputs needed to run test or train batches.

    Args:
        input_shape (tuple):
            input batch dimensions

        num_classes (int):
            number of semantic classes
    """
    (N, C, H, W) = input_shape

    rng = np.random.RandomState(0)

    imgs = rng.rand(*input_shape)
    segs = rng.randint(
        low=0, high=num_classes - 1, size=(N, 1, H, W)).astype(np.uint8)

    img_metas = [{
        'img_shape': (H, W, C),
        'ori_shape': (H, W, C),
        'pad_shape': (H, W, C),
        'filename': '<demo>.png',
        'scale_factor': 1.0,
        'flip': False,
        'flip_direction': 'horizontal'
    } for _ in range(N)]

    mm_inputs = {
        'imgs': torch.FloatTensor(imgs),
        'img_metas': img_metas,
        'gt_semantic_seg': torch.LongTensor(segs)
    }
    return mm_inputs


@BACKBONES.register_module()
class ExampleBackbone(nn.Module):

    def __init__(self):
        super(ExampleBackbone, self).__init__()
        self.conv = nn.Conv2d(3, 3, 3)

    def init_weights(self, pretrained=None):
        pass

    def forward(self, x):
        return [self.conv(x)]


@HEADS.register_module()
class ExampleDecodeHead(BaseDecodeHead):

    def __init__(self):
        super(ExampleDecodeHead, self).__init__(3, 3, num_classes=19)

    def forward(self, inputs):
        return self.cls_seg(inputs[0])


@HEADS.register_module()
class ExampleCascadeDecodeHead(BaseCascadeDecodeHead):

    def __init__(self):
        super(ExampleCascadeDecodeHead, self).__init__(3, 3, num_classes=19)

    def forward(self, inputs, prev_out):
        return self.cls_seg(inputs[0])


def _segmentor_forward_train_test(segmentor):
    if isinstance(segmentor.decode_head, nn.ModuleList):
        num_classes = segmentor.decode_head[-1].num_classes
    else:
        num_classes = segmentor.decode_head.num_classes
    # batch_size=2 for BatchNorm
    mm_inputs = _demo_mm_inputs(num_classes=num_classes)

    imgs = mm_inputs.pop('imgs')
    img_metas = mm_inputs.pop('img_metas')
    gt_semantic_seg = mm_inputs['gt_semantic_seg']

    # convert to cuda Tensor if applicable
    if torch.cuda.is_available():
        segmentor = segmentor.cuda()
        imgs = imgs.cuda()
        gt_semantic_seg = gt_semantic_seg.cuda()

    # Test forward train
    losses = segmentor.forward(
        imgs, img_metas, gt_semantic_seg=gt_semantic_seg, return_loss=True)
    assert isinstance(losses, dict)

    # Test forward simple test
    with torch.no_grad():
        segmentor.eval()
        # pack into lists
        img_list = [img[None, :] for img in imgs]
        img_meta_list = [[img_meta] for img_meta in img_metas]
        segmentor.forward(img_list, img_meta_list, return_loss=False)

    # Test forward aug test
    with torch.no_grad():
        segmentor.eval()
        # pack into lists
        img_list = [img[None, :] for img in imgs]
        img_list = img_list + img_list
        img_meta_list = [[img_meta] for img_meta in img_metas]
        img_meta_list = img_meta_list + img_meta_list
        segmentor.forward(img_list, img_meta_list, return_loss=False)


def test_encoder_decoder():

    # test 1 decode head, w.o. aux head

    cfg = ConfigDict(
        type='EncoderDecoder',
        backbone=dict(type='ExampleBackbone'),
        decode_head=dict(type='ExampleDecodeHead'),
        train_cfg=None,
        test_cfg=dict(mode='whole'))
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)

    # test slide mode
    cfg.test_cfg = ConfigDict(mode='slide', crop_size=(3, 3), stride=(2, 2))
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)

    # test 1 decode head, 1 aux head
    cfg = ConfigDict(
        type='EncoderDecoder',
        backbone=dict(type='ExampleBackbone'),
        decode_head=dict(type='ExampleDecodeHead'),
        auxiliary_head=dict(type='ExampleDecodeHead'))
    cfg.test_cfg = ConfigDict(mode='whole')
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)

    # test 1 decode head, 2 aux head
    cfg = ConfigDict(
        type='EncoderDecoder',
        backbone=dict(type='ExampleBackbone'),
        decode_head=dict(type='ExampleDecodeHead'),
        auxiliary_head=[
            dict(type='ExampleDecodeHead'),
            dict(type='ExampleDecodeHead')
        ])
    cfg.test_cfg = ConfigDict(mode='whole')
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)


def test_cascade_encoder_decoder():

    # test 1 decode head, w.o. aux head
    cfg = ConfigDict(
        type='CascadeEncoderDecoder',
        num_stages=2,
        backbone=dict(type='ExampleBackbone'),
        decode_head=[
            dict(type='ExampleDecodeHead'),
            dict(type='ExampleCascadeDecodeHead')
        ])
    cfg.test_cfg = ConfigDict(mode='whole')
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)

    # test slide mode
    cfg.test_cfg = ConfigDict(mode='slide', crop_size=(3, 3), stride=(2, 2))
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)

    # test 1 decode head, 1 aux head
    cfg = ConfigDict(
        type='CascadeEncoderDecoder',
        num_stages=2,
        backbone=dict(type='ExampleBackbone'),
        decode_head=[
            dict(type='ExampleDecodeHead'),
            dict(type='ExampleCascadeDecodeHead')
        ],
        auxiliary_head=dict(type='ExampleDecodeHead'))
    cfg.test_cfg = ConfigDict(mode='whole')
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)

    # test 1 decode head, 2 aux head
    cfg = ConfigDict(
        type='CascadeEncoderDecoder',
        num_stages=2,
        backbone=dict(type='ExampleBackbone'),
        decode_head=[
            dict(type='ExampleDecodeHead'),
            dict(type='ExampleCascadeDecodeHead')
        ],
        auxiliary_head=[
            dict(type='ExampleDecodeHead'),
            dict(type='ExampleDecodeHead')
        ])
    cfg.test_cfg = ConfigDict(mode='whole')
    segmentor = build_segmentor(cfg)
    _segmentor_forward_train_test(segmentor)