File size: 4,879 Bytes
a6dd040
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright (c) 2021 NVIDIA CORPORATION.
#
# Permission is hereby granted, free of charge, to any person obtaining a copy of
# this software and associated documentation files (the "Software"), to deal in
# the Software without restriction, including without limitation the rights to
# use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
# of the Software, and to permit persons to whom the Software is furnished to do
# so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
# Please cite "4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural
# Networks", CVPR'19 (https://arxiv.org/abs/1904.08755) if you use any part
# of the code.

import unittest
import numpy as np

import torch
import torch.nn as nn

import MinkowskiEngine as ME
from MinkowskiEngine import MinkowskiStackCat, MinkowskiStackSum
from MinkowskiEngine.utils import batched_coordinates

from utils.gradcheck import gradcheck
from tests.python.common import data_loader, load_file


class TestStack(unittest.TestCase):
    def test_sum(self):
        coords, colors, pcd = load_file("1.ply")
        device = "cuda"

        D = 3
        batch_size = 16
        voxel_size = 0.02
        channels = [3, 64, 128]
        dcoords = torch.from_numpy(np.floor(coords / voxel_size)).int()
        bcoords = batched_coordinates([dcoords for i in range(batch_size)])
        in_feats = torch.rand(len(bcoords), 3).to(0)

        layer = MinkowskiStackSum(
            ME.MinkowskiConvolution(
                channels[0],
                channels[1],
                kernel_size=3,
                stride=1,
                dimension=3,
            ),
            nn.Sequential(
                ME.MinkowskiConvolution(
                    channels[0],
                    channels[1],
                    kernel_size=3,
                    stride=2,
                    dimension=3,
                ),
                ME.MinkowskiStackSum(
                    nn.Identity(),
                    nn.Sequential(
                        ME.MinkowskiConvolution(
                            channels[1],
                            channels[2],
                            kernel_size=3,
                            stride=2,
                            dimension=3,
                        ),
                        ME.MinkowskiConvolutionTranspose(
                            channels[2],
                            channels[1],
                            kernel_size=3,
                            stride=1,
                            dimension=3,
                        ),
                        ME.MinkowskiPoolingTranspose(
                            kernel_size=2, stride=2, dimension=D
                        ),
                    ),
                ),
                ME.MinkowskiPoolingTranspose(kernel_size=2, stride=2, dimension=D),
            ),
        ).cuda()

        for i in range(1000):
            torch.cuda.empty_cache()
            sinput = ME.SparseTensor(in_feats, coordinates=bcoords, device=device)
            layer(sinput)

    def test_baseline(self):
        coords, colors, pcd = load_file("1.ply")
        device = "cuda"

        D = 3
        batch_size = 16
        voxel_size = 0.02
        channels = [3, 64, 128]
        dcoords = torch.from_numpy(np.floor(coords / voxel_size)).int()
        bcoords = batched_coordinates([dcoords for i in range(batch_size)])
        in_feats = torch.rand(len(bcoords), 3).to(0)

        layer = nn.Sequential(
            ME.MinkowskiConvolution(
                channels[0],
                channels[1],
                kernel_size=3,
                stride=1,
                dimension=3,
            ),
            ME.MinkowskiConvolution(
                channels[1],
                channels[2],
                kernel_size=3,
                stride=2,
                dimension=3,
            ),
            ME.MinkowskiConvolutionTranspose(
                channels[2],
                channels[1],
                kernel_size=3,
                stride=1,
                dimension=3,
            ),
        ).cuda()

        for i in range(1000):
            torch.cuda.empty_cache()
            sinput = ME.SparseTensor(in_feats, coordinates=bcoords, device=device)
            layer(sinput)