conv_arithmetic图像处理
所属分类:图形图像处理
开发工具:Python
文件大小:3686KB
下载次数:1
上传日期:2020-06-21 00:52:56
上 传 者:
魏强2310
说明: conv_arithmetic图像处理,基于python的图像处理
(conv_ Arithmetic image processing, image processing based on Python)
文件列表:
LICENSE (1067, 2019-04-13)
bibliography.bib (6792, 2019-04-13)
bin (0, 2019-04-13)
bin\generate_makefile (5368, 2019-04-13)
bin\produce_figure (11468, 2019-04-13)
conv_arithmetic.tex (59375, 2019-04-13)
gif (0, 2019-04-13)
gif\arbitrary_padding_no_strides.gif (476750, 2019-04-13)
gif\arbitrary_padding_no_strides_transposed.gif (323062, 2019-04-13)
gif\dilation.gif (124951, 2019-04-13)
gif\full_padding_no_strides.gif (435605, 2019-04-13)
gif\full_padding_no_strides_transposed.gif (287001, 2019-04-13)
gif\no_padding_no_strides.gif (37751, 2019-04-13)
gif\no_padding_no_strides_transposed.gif (164355, 2019-04-13)
gif\no_padding_strides.gif (44665, 2019-04-13)
gif\no_padding_strides_transposed.gif (197717, 2019-04-13)
gif\padding_strides.gif (118422, 2019-04-13)
gif\padding_strides_odd.gif (122211, 2019-04-13)
gif\padding_strides_odd_transposed.gif (303965, 2019-04-13)
gif\padding_strides_transposed.gif (272498, 2019-04-13)
gif\same_padding_no_strides.gif (276460, 2019-04-13)
gif\same_padding_no_strides_transposed.gif (213333, 2019-04-13)
natbib (0, 2019-04-13)
natbib\natbib.bst (24935, 2019-04-13)
pdf (0, 2019-04-13)
pdf\arbitrary_padding_no_strides_00.pdf (2828, 2019-04-13)
pdf\arbitrary_padding_no_strides_01.pdf (2866, 2019-04-13)
pdf\arbitrary_padding_no_strides_02.pdf (2838, 2019-04-13)
pdf\arbitrary_padding_no_strides_03.pdf (2836, 2019-04-13)
pdf\arbitrary_padding_no_strides_transposed_00.pdf (3174, 2019-04-13)
pdf\arbitrary_padding_no_strides_transposed_01.pdf (3160, 2019-04-13)
pdf\arbitrary_padding_no_strides_transposed_02.pdf (3151, 2019-04-13)
pdf\arbitrary_padding_no_strides_transposed_03.pdf (3145, 2019-04-13)
pdf\dilation_00.pdf (3006, 2019-04-13)
pdf\dilation_01.pdf (3016, 2019-04-13)
... ...
# Convolution arithmetic
A technical report on convolution arithmetic in the context of deep learning.
The code and the images of this tutorial are free to use as regulated by the
licence and subject to proper attribution:
* \[1\] Vincent Dumoulin, Francesco Visin - [A guide to convolution arithmetic
for deep learning](https://arxiv.org/abs/1603.07285)
([BibTeX](https://gist.github.com/fvisin/165ca9935392fa9600a6c946***a01214))
## Convolution animations
_N.B.: Blue maps are inputs, and cyan maps are outputs._
|
|
|
|
No padding, no strides |
Arbitrary padding, no strides |
Half padding, no strides |
Full padding, no strides |
|
|
|
|
No padding, strides |
Padding, strides |
Padding, strides (odd) |
|
## Transposed convolution animations
_N.B.: Blue maps are inputs, and cyan maps are outputs._
|
|
|
|
No padding, no strides, transposed |
Arbitrary padding, no strides, transposed |
Half padding, no strides, transposed |
Full padding, no strides, transposed |
|
|
|
|
No padding, strides, transposed |
Padding, strides, transposed |
Padding, strides, transposed (odd) |
|
## Dilated convolution animations
_N.B.: Blue maps are inputs, and cyan maps are outputs._
|
No padding, no stride, dilation |
## Generating the Makefile
From the repository's root directory:
``` bash
$ ./bin/generate_makefile
```
## Generating the animations
From the repository's root directory:
``` bash
$ make all_animations
```
The animations will be output to the `gif` directory. Individual animation steps
will be output in PDF format to the `pdf` directory and in PNG format to the
`png` directory.
## Compiling the document
From the repository's root directory:
``` bash
$ make
```
近期下载者:
相关文件:
收藏者: