Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/vdumoulin/conv_arithmetic

A technical report on convolution arithmetic in the context of deep learning
https://github.com/vdumoulin/conv_arithmetic

Last synced: 3 months ago
JSON representation

A technical report on convolution arithmetic in the context of deep learning

Awesome Lists containing this project

README

        

# 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/165ca9935392fa9600a6c94664a01214))

## 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
```