Wolfram.com
WolframAlpha.com
WolframCloud.com
Wolfram Language
Example Repository
Ready-to-use examples for the Wolfram Language
Primary Navigation
Categories
Astronomy
Audio Processing
Calculus
Cellular Automata
Chemistry
Complex Systems
Computer Science
Computer Vision
Control Systems
Creative Arts
Data Science
Engineering
Finance & Economics
Finite Element Method
Food & Nutrition
Geography
Geometry
Graphs & Networks
Image Processing
Life Sciences
Machine Learning
Mathematics
Optimization
Physics
Puzzles and Recreation
Quantum Computation
Signal Processing
Social Sciences
System Modeling
Text & Language Processing
Time-Related Computation
Video Processing
Visualization & Graphics
Alphabetical List
Submit a New Resource
Related Pages
Related Symbols
NetModel
NetReplacePart
Resampling
ImageResize
ColorSeparate
ColorCombine
NetChain
Related Categories
Machine Learning
Image Processing
Computer Vision
Create Super-Resolution Images Using Neural Networks
Example Notebook
Open in Cloud
Download Notebook
Get the pre-trained network from the
Wolfram Neural Net Repository
:
I
n
[
1
]
:
=
n
e
t
=
N
e
t
M
o
d
e
l
[
"
V
e
r
y
D
e
e
p
N
e
t
f
o
r
S
u
p
e
r
-
R
e
s
o
l
u
t
i
o
n
"
]
O
u
t
[
1
]
=
N
e
t
C
h
a
i
n
I
n
p
u
t
p
o
r
t
:
i
m
a
g
e
O
u
t
p
u
t
p
o
r
t
:
a
r
r
a
y
(
s
i
z
e
:
2
5
5
×
2
5
5
×
1
)
This network performs the refinement on the Y channel in the YCbCr color space. Write an evaluation function to handle net resizing and color conversion:
I
n
[
2
]
:
=
n
e
t
e
v
a
l
u
a
t
e
[
i
m
g
_
,
i
m
g
S
c
a
l
e
_
]
:
=
B
l
o
c
k
{
i
n
t
e
r
p
o
l
a
t
e
d
,
y
c
b
c
r
,
c
h
a
n
n
e
l
s
,
r
e
s
i
z
e
d
N
e
t
,
d
i
f
f
}
,
i
n
t
e
r
p
o
l
a
t
e
d
=
I
m
a
g
e
R
e
s
i
z
e
[
i
m
g
,
S
c
a
l
e
d
[
i
m
g
S
c
a
l
e
]
,
R
e
s
a
m
p
l
i
n
g
"
C
u
b
i
c
"
]
;
y
c
b
c
r
=
R
G
B
t
o
Y
C
b
C
r
@
i
n
t
e
r
p
o
l
a
t
e
d
;
r
e
s
i
z
e
d
N
e
t
=
N
e
t
R
e
p
l
a
c
e
P
a
r
t
n
e
t
,
"
I
n
p
u
t
"
N
e
t
E
n
c
o
d
e
r
[
]
;
c
h
a
n
n
e
l
s
=
C
o
l
o
r
S
e
p
a
r
a
t
e
[
y
c
b
c
r
]
;
d
i
f
f
=
I
m
a
g
e
[
r
e
s
i
z
e
d
N
e
t
[
F
i
r
s
t
[
c
h
a
n
n
e
l
s
]
]
]
;
y
c
b
c
r
=
C
o
l
o
r
C
o
m
b
i
n
e
[
c
h
a
n
n
e
l
s
+
{
d
i
f
f
,
0
,
0
}
]
;
Y
C
b
C
r
t
o
R
G
B
@
y
c
b
c
r
Start with a small image:
I
n
[
3
]
:
=
i
m
g
=
;
Evaluate the network on the image to double its size:
I
n
[
4
]
:
=
r
e
f
i
n
e
d
=
n
e
t
e
v
a
l
u
a
t
e
[
i
m
g
,
2
]
O
u
t
[
4
]
=
Compare with the unrefined resampling using the same cubic kernel used to produce the net input and a high-quality OMOMS kernel:
I
n
[
5
]
:
=
u
p
s
a
m
p
l
e
d
C
u
b
i
c
=
I
m
a
g
e
R
e
s
i
z
e
[
i
m
g
,
S
c
a
l
e
d
[
2
]
,
R
e
s
a
m
p
l
i
n
g
"
C
u
b
i
c
"
]
;
u
p
s
a
m
p
l
e
d
O
M
O
M
S
=
I
m
a
g
e
R
e
s
i
z
e
[
i
m
g
,
S
c
a
l
e
d
[
2
]
,
R
e
s
a
m
p
l
i
n
g
{
"
O
M
O
M
S
"
,
7
}
]
;
T
a
b
l
e
F
o
r
m
I
m
a
g
e
I
m
a
g
e
T
r
i
m
[
#
,
{
{
{
2
0
0
,
2
0
}
,
{
3
8
0
,
2
0
0
}
}
,
{
{
2
0
0
,
2
0
0
}
,
{
3
0
0
,
3
0
0
}
}
}
]
,
.
.
.
&
/
@
{
u
p
s
a
m
p
l
e
d
C
u
b
i
c
,
u
p
s
a
m
p
l
e
d
O
M
O
M
S
,
r
e
f
i
n
e
d
}
,
.
.
.
O
u
t
[
5
]
/
/
T
a
b
l
e
F
o
r
m
=
C
u
b
i
c
O
M
O
M
S
D
N
N
See Also
Very Deep Net for Super-Resolution
Related Symbols
NetModel
NetReplacePart
Resampling
ImageResize
ColorSeparate
ColorCombine
NetChain
Publisher Information
Contributed by:
Wolfram Staff
