Conv3D

	B	C	D	E	H	I	J	M	N	O	P
1
2	conv = mx.gluon.nn.Conv3D(channels=1, kernel_size=(2,2,2))
3	Shape inference will be used to determine `in_channels=1` automatically.
4
5	Input				Kernel			Output
6
7	1	0	1	0		0	1		2	1	1
8	1	1	3	1		0	0		5	4	5
9	1	1	0	2					8	3	5
10	0	2	1	1		2	1
11						0	0		4	1	4
12	1	0	0	1					9	8	4
13	2	0	1	2					6	4	3
14	3	1	1	1
15	0	0	3	1					2	3	5
16									5	4	9
17	2	0	1	1					8	3	0
18	3	3	1	0
19	2	1	1	0
20	3	2	1	2
21
22	1	0	2	0
23	1	0	3	3
24	3	1	0	0
25	1	1	0	2
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