Latex code for making neural networks diagrams

Overview

PlotNeuralNet

DOI

Latex code for drawing neural networks for reports and presentation. Have a look into examples to see how they are made. Additionally, lets consolidate any improvements that you make and fix any bugs to help more people with this code.

Examples

Following are some network representations:

FCN-8 (view on Overleaf)

FCN-32 (view on Overleaf)

Holistically-Nested Edge Detection (view on Overleaf)

Getting Started

  1. Install the following packages on Ubuntu.

    • Ubuntu 16.04

      sudo apt-get install texlive-latex-extra
      
    • Ubuntu 18.04.2 Base on this website, please install the following packages.

      sudo apt-get install texlive-latex-base
      sudo apt-get install texlive-fonts-recommended
      sudo apt-get install texlive-fonts-extra
      sudo apt-get install texlive-latex-extra
      
    • Windows

    1. Download and install MikTeX.
    2. Download and install bash runner on Windows, recommends Git bash or Cygwin(https://www.cygwin.com/)
  2. Execute the example as followed.

    cd pyexamples/
    bash ../tikzmake.sh test_simple
    

TODO

  • Python interface
  • Add easy legend functionality
  • Add more layer shapes like TruncatedPyramid, 2DSheet etc
  • Add examples for RNN and likes.

Latex usage

See examples directory for usage.

Python usage

First, create a new directory and a new Python file:

$ mkdir my_project
$ cd my_project
vim my_arch.py

Add the following code to your new file:

import sys
sys.path.append('../')
from pycore.tikzeng import *

# defined your arch
arch = [
    to_head( '..' ),
    to_cor(),
    to_begin(),
    to_Conv("conv1", 512, 64, offset="(0,0,0)", to="(0,0,0)", height=64, depth=64, width=2 ),
    to_Pool("pool1", offset="(0,0,0)", to="(conv1-east)"),
    to_Conv("conv2", 128, 64, offset="(1,0,0)", to="(pool1-east)", height=32, depth=32, width=2 ),
    to_connection( "pool1", "conv2"),
    to_Pool("pool2", offset="(0,0,0)", to="(conv2-east)", height=28, depth=28, width=1),
    to_SoftMax("soft1", 10 ,"(3,0,0)", "(pool1-east)", caption="SOFT"  ),
    to_connection("pool2", "soft1"),
    to_end()
    ]

def main():
    namefile = str(sys.argv[0]).split('.')[0]
    to_generate(arch, namefile + '.tex' )

if __name__ == '__main__':
    main()

Now, run the program as follows:

bash ../tikzmake.sh my_arch
Comments
  • Error when running readme example: `I can't find file `tikzlibraryquotes.code.tex'`

    Error when running readme example: `I can't find file `tikzlibraryquotes.code.tex'`

    python my_arch.py works fine, producing the output included below. However, when I run pdflatex, I get error:

    ! I can't find file `tikzlibraryquotes.code.tex'.
    <argument> ...nput tikzlibrary\[email protected] .code.tex 
                                                      \catcode `\@ =\csname tikz...
    l.2 \usetikzlibrary{quotes,arrows.meta}
    

    I presume this is a simple fix requiring an install. Please may you help me diagnose what I need installed on my system for this to run? I am able to run tikz fine and create examples e.g. this one.

    LaTeX info

    $ pdflatex --version
    pdfTeX 3.1415926-2.5-1.40.14 (TeX Live 2013/Debian)
    kpathsea version 6.1.1
    Copyright 2013 Peter Breitenlohner (eTeX)/Han The Thanh (pdfTeX).
    There is NO warranty.  Redistribution of this software is
    covered by the terms of both the pdfTeX copyright and
    the Lesser GNU General Public License.
    For more information about these matters, see the file
    named COPYING and the pdfTeX source.
    Primary author of pdfTeX: Peter Breitenlohner (eTeX)/Han The Thanh (pdfTeX).
    Compiled with libpng 1.2.50; using libpng 1.2.50
    Compiled with zlib 1.2.8; using zlib 1.2.8
    Compiled with poppler version 0.24.5
    

    Python output:

    \documentclass[border=8pt, multi, tikz]{standalone} 
    \usepackage{import}
    \subimport{../layers/}{init}
    \usetikzlibrary{positioning}
    \usetikzlibrary{3d} %for including external image 
    
    
    \def\ConvColor{rgb:yellow,5;red,2.5;white,5}
    \def\ConvReluColor{rgb:yellow,5;red,5;white,5}
    \def\PoolColor{rgb:red,1;black,0.3}
    \def\UnpoolColor{rgb:blue,2;green,1;black,0.3}
    \def\FcColor{rgb:blue,5;red,2.5;white,5}
    \def\FcReluColor{rgb:blue,5;red,5;white,4}
    \def\SoftmaxColor{rgb:magenta,5;black,7}   
    
    
    \newcommand{\copymidarrow}{\tikz \draw[-Stealth,line width=0.8mm,draw={rgb:blue,4;red,1;green,1;black,3}] (-0.3,0) -- ++(0.3,0);}
    
    \begin{document}
    \begin{tikzpicture}
    \tikzstyle{connection}=[ultra thick,every node/.style={sloped,allow upside down},draw=\edgecolor,opacity=0.7]
    \tikzstyle{copyconnection}=[ultra thick,every node/.style={sloped,allow upside down},draw={rgb:blue,4;red,1;green,1;black,3},opacity=0.7]
    
    
    \pic[shift={(0,0,0)}] at (0,0,0) 
        {Box={
            name=conv1,
            caption= ,
            xlabel={{64, }},
            zlabel=512,
            fill=\ConvColor,
            height=64,
            width=2,
            depth=64
            }
        };
    
    
    \pic[shift={ (0,0,0) }] at (conv1-east) 
        {Box={
            name=pool1,
            caption= ,
            fill=\PoolColor,
            opacity=0.5,
            height=32,
            width=1,
            depth=32
            }
        };
    
    
    \pic[shift={(1,0,0)}] at (pool1-east) 
        {Box={
            name=conv2,
            caption= ,
            xlabel={{64, }},
            zlabel=128,
            fill=\ConvColor,
            height=32,
            width=2,
            depth=32
            }
        };
    
    
    \draw [connection]  (pool1-east)    -- node {\midarrow} (conv2-west);
    
    
    \pic[shift={ (0,0,0) }] at (conv2-east) 
        {Box={
            name=pool2,
            caption= ,
            fill=\PoolColor,
            opacity=0.5,
            height=28,
            width=1,
            depth=28
            }
        };
    
    
    \pic[shift={(3,0,0)}] at (pool1-east) 
        {Box={
            name=soft1,
            caption=SOFT,
            xlabel={{" ","dummy"}},
            zlabel=10,
            fill=\SoftmaxColor,
            opacity=0.8,
            height=3,
            width=1.5,
            depth=25
            }
        };
    
    
    \draw [connection]  (pool2-east)    -- node {\midarrow} (soft1-west);
    
    
    \end{tikzpicture}
    \end{document}
    
    opened by JamesOwers 8
  • Importing Standalone output to tex document

    Importing Standalone output to tex document

    Hey, Thanks for the tool, the graphics look awesome. I'm having some difficulty importing the outputted standalone tex file into a technical report of mine and was wondering if someone tried to do something similar and can help :) Thanks!

    opened by aklyussef 5
  • Fully Connected layer box

    Fully Connected layer box

    Below is the code that implements a fully connected layer box since I wasn't able to find it in the code. I used to_SoftMax function and modified it.

    The code should be put inside pycore/tikzeng.py file.

    def to_FullyConnected( name, s_filer=" ", n_filer=" ", offset="(0,0,0)", to="(0,0,0)", width=1.5, height=3, depth=25, opacity=0.8, caption=" " , zlabelposition='midway'):
        return r"""
    \pic[shift={"""+ offset +"""}] at """+ to +""" 
        {Box={
            name=""" + name +""",
            caption=""" +caption + """,
            xlabel={{ """+ '"'+str(n_filer) +'", "dummy"'+ """ }},
            zlabel="""+ str(s_filer) +""",
            zlabelposition="""+zlabelposition+""",
            fill=\FcColor,
            bandfill=\FcReluColor,
            opacity="""+ str(opacity) +""",
            height="""+ str(height) +""",
            width="""+ str(width) +""",
            depth="""+ str(depth) +"""
            }
        };
    """
    

    Cheers.

    opened by chrismaliszewski 5
  • to_input(...) doesn't have east, west... properties

    to_input(...) doesn't have east, west... properties

    I would like to connect the input image to conv blocks and other blocks, but it is not possible since to_input(...) doesn't have east, west, northeast, etc... properties. How to solve this? Maybe wrap to_input(...) in a box or something?

    opened by dougsouza 5
  • Unet to DenseNets

    Unet to DenseNets

    I am trying to modify Unet tex code to create DenseNets block. f838717a-6ad1-11e6-9391-f0906c80bc1d

    I am wondering how to modify the connection lines that then look like densenets style? Thank you for your time!

    opened by zuxfoucault 4
  • ModuleNotFoundError: No module named 'pycore.tikzeng'

    ModuleNotFoundError: No module named 'pycore.tikzeng'

    After running pip install pycore when I try to run in python: from pycore.tikzeng import * I got: ModuleNotFoundError: No module named 'pycore.tikzeng'

    Version: pycore==17.4.17

    opened by amirubin87 4
  • I want to know how to add legend

    I want to know how to add legend

    Hi, I wonder if there is a way of adding legend to the figure (identifying which color corresponds to which type of layer).

    A example default

    And how to eliminate cube number?

    opened by quinwu 4
  • Font size in the graph

    Font size in the graph

    Does anyone know how to change the font size in the graph? I tried to simply add to the documentclass

    \documentclass[border=15pt, multi, tikz]{standalone}

    but it doesn't work and returns some errors with positioning.

    opened by wufeim 3
  • unet error

    unet error

    pyexamples|master⚡ ⇒ bash ../tikzmake.sh unet

    File "unet.py", line 19 block_2ConvPool( name='b2', botton='pool_b1', top='pool_b2', s_filer=256, n_filer=128, offset="(1,0,0)", size=(32,32,3.5), opacity=0.5 ), ^ SyntaxError: invalid syntax This is pdfTeX, Version 3.14159265-2.6-1.40.19 (TeX Live 2018) (preloaded format=pdflatex) restricted \write18 enabled. entering extended mode ! I can't find file `unet.tex'. <> unet.tex

    (Press Enter to retry, or Control-D to exit) Please type another input file name: ^D ! Emergency stop. <*> unet.tex

    ! ==> Fatal error occurred, no output PDF file produced! Transcript written on texput.log. rm: *.aux: No such file or directory rm: *.vscodeLog: No such file or directory rm: *.tex: No such file or directory ../tikzmake.sh: line 10: xdg-open: command not found

    opened by wm901115nwpu 3
  • Labeling Blocks will create a solid line

    Labeling Blocks will create a solid line

    I tried to let the Box block's edges be invisible via fill=\fill, draw=\fill in Box.sty.

    Actually, It only let edges AH, AD, DE, CD, EF and HE invisible.

    Finally I found that \path (b) edge ["\bf\xlabel"', midway] (c); created a solid line in BC, so do AB and CF.

    I have no idea to fix this and I don't know why the solid lines emerged though no pic action acted in above code.

    Furthermore, I want customize the style of draw line, but nothing changes after I put thin into "box" style setting.

    opened by omegahh 3
  • What does the single quotation mark which follows double quotation marks mean?

    What does the single quotation mark which follows double quotation marks mean?

    Thanks for your amazing work! I am confused with the quotation mark like "\cubezlabel"'. What is the difference between "\cubezlabel".

    Looking forwarding your answer:)

    opened by omegahh 3
  • Made python interface installable via pip

    Made python interface installable via pip

    Hi, HarisIqbal88!

    My boss told me to use your package for my master thesis and I really like it, but it was bugging me, that it didn't have an installer. So I made it installable via pip. I had to rearrange your directories a little bit, but I hope you like it.

    I also added CITATION.cff, this will show how to cite your software directly in the repos sidebar.

    You might want to add your email or ORCID in pyproject.toml and check CITATION.cff for errors.

    I wish you a happy New Year!

    Kind regards, Jonas Eichhorn

    opened by AlreadyTakenJonas 1
  • Add a documentation

    Add a documentation

    Hello,

    Thank you for the good work.

    Please can you work toward doing a good documentation for this repo ? Some arguments are not clearly defined, and it's not clear what values we should use etc.. a proper documentation would be greatly appreciated !

    Cordially

    opened by NicolasNerr 0
  • Add arrow as legend (U-Net Model)

    Add arrow as legend (U-Net Model)

    How can I use an arrow as a legend of the plot? Please give me an example!

    Model architecture: U-Net (I want to plot "concatenate arrows" in U-Net as legend)

    image

    opened by mehrdad-dev 0
Releases(v1.0.0)
  • v1.0.0(Dec 25, 2018)

    This is the first release that is built on the idea to further extend the functionality with maximum backward compatibility. Layer names(e.g., Box,RightBandedBox) and their attributes(e.g., caption,xlabels) are generic. Moreover, the code is much better readable than the previous version. TO DO's:

    • Add easy legend functionality
    • Add more layer shapes like TruncatedPyramid, 2DSheet etc
    Source code(tar.gz)
    Source code(zip)
  • v0.1(Dec 25, 2018)

    This is the very first release in which layers were defined by specific names like Conv, ConvRelu,Deconv and a workable solution was created. This version is not suitable for extension because having a separate layer just because it is represented by a different colour is not clever. In future release, layers should be defined in generic terms like Box, RightBandedBox, Ball etc so that less code can make different layers with colour as a parameter. Additionally, attributes of each layer should also be changed to generic for example: from numFilters to xlabels

    Source code(tar.gz)
    Source code(zip)
Owner
Haris Iqbal
Computer Science Student at Saarland University
Haris Iqbal
Yoga - Yoga asana classifier for python

Yoga Asana Classifier Description Hi welcome to my new deep learning project "Yo

Programminghut 35 Dec 12, 2022
Resilience from Diversity: Population-based approach to harden models against adversarial attacks

Resilience from Diversity: Population-based approach to harden models against adversarial attacks Requirements To install requirements: pip install -r

0 Nov 23, 2021
The PyTorch implementation for paper "Neural Texture Extraction and Distribution for Controllable Person Image Synthesis" (CVPR2022 Oral)

ArXiv | Get Start Neural-Texture-Extraction-Distribution The PyTorch implementation for our paper "Neural Texture Extraction and Distribution for Cont

Ren Yurui 111 Dec 10, 2022
Official code repository for the publication "Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons"

Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons This repository contains the code to repr

Computational Neuroscience, University of Bern 3 Aug 04, 2022
To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

Kunal Wadhwa 2 Jan 05, 2022
My course projects for the 2021 Spring Machine Learning course at the National Taiwan University (NTU)

ML2021Spring There are my projects for the 2021 Spring Machine Learning course at the National Taiwan University (NTU) Course Web : https://speech.ee.

Ding-Li Chen 15 Aug 29, 2022
Multi-scale discriminator feature-wise loss function

Multi-Scale Discriminative Feature Loss This repository provides code for Multi-Scale Discriminative Feature (MDF) loss for image reconstruction algor

Graphics and Displays group - University of Cambridge 76 Dec 12, 2022
Code for Towards Streaming Perception (ECCV 2020) :car:

sAP — Code for Towards Streaming Perception ECCV Best Paper Honorable Mention Award Feb 2021: Announcing the Streaming Perception Challenge (CVPR 2021

Martin Li 85 Dec 22, 2022
Code base of object detection

rmdet code base of object detection. 环境安装: 1. 安装conda python环境 - `conda create -n xxx python=3.7/3.8` - `conda activate xxx` 2. 运行脚本,自动安装pytorch1

3 Mar 08, 2022
LTR_CrossEncoder: Legal Text Retrieval Zalo AI Challenge 2021

LTR_CrossEncoder: Legal Text Retrieval Zalo AI Challenge 2021 We propose a cross encoder model (LTR_CrossEncoder) for information retrieval, re-retrie

Hieu Duong 7 Jan 12, 2022
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification

Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [pdf] The official repository for Self-Supervised Pre-Training for Transfo

Hao Luo 116 Jan 04, 2023
Implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

SinGAN This is an unofficial implementation of SinGAN from someone who's been sitting right next to SinGAN's creator for almost five years. Please ref

35 Nov 10, 2022
Rohit Ingole 2 Mar 24, 2022
The official implementation of Theme Transformer

Theme Transformer This is the official implementation of Theme Transformer. Checkout our demo and paper : Demo | arXiv Environment: using python versi

Ian Shih 85 Dec 08, 2022
The authors' official PyTorch SigWGAN implementation

The authors' official PyTorch SigWGAN implementation This repository is the official implementation of [Sig-Wasserstein GANs for Time Series Generatio

9 Jun 16, 2022
Code accompanying our NeurIPS 2021 traffic4cast challenge

Traffic forecasting on traffic movie snippets This repo contains all code to reproduce our approach to the IARAI Traffic4cast 2021 challenge. In the c

Nina Wiedemann 2 Aug 09, 2022
The code for our NeurIPS 2021 paper "Kernelized Heterogeneous Risk Minimization".

Kernelized-HRM Jiashuo Liu, Zheyuan Hu The code for our NeurIPS 2021 paper "Kernelized Heterogeneous Risk Minimization"[1]. This repo contains the cod

Liu Jiashuo 8 Nov 20, 2022
LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image.

This project is based on ultralytics/yolov3. LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image. The related paper is avai

26 Dec 13, 2022
MVSDF - Learning Signed Distance Field for Multi-view Surface Reconstruction

MVSDF - Learning Signed Distance Field for Multi-view Surface Reconstruction This is the official implementation for the ICCV 2021 paper Learning Sign

110 Dec 20, 2022
Generate images from texts. In Russian

ruDALL-E Generate images from texts pip install rudalle==1.1.0rc0 🤗 HF Models: ruDALL-E Malevich (XL) ruDALL-E Emojich (XL) (readme here) ruDALL-E S

AI Forever 1.6k Dec 31, 2022