[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-70913":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":28,"readmeContent":29,"aiSummary":30,"trendingCount":15,"starSnapshotCount":15,"syncStatus":31,"lastSyncTime":32,"discoverSource":33},70913,"PlotNeuralNet","HarisIqbal88\u002FPlotNeuralNet","HarisIqbal88","Latex code for making neural networks diagrams",null,"TeX",24808,3064,226,70,0,12,28,81,36,45,"MIT License",false,"master",true,[26,27],"deep-neural-networks","latex","2026-06-12 02:02:45","# PlotNeuralNet\n[![DOI](https:\u002F\u002Fzenodo.org\u002Fbadge\u002FDOI\u002F10.5281\u002Fzenodo.2526396.svg)](https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.2526396)\n\nLatex 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.\n\n## Examples\n\nFollowing are some network representations:\n\n\u003Cp align=\"center\">\u003Cimg  src=\"https:\u002F\u002Fuser-images.githubusercontent.com\u002F17570785\u002F50308846-c2231880-049c-11e9-8763-3daa1024de78.png\" width=\"85%\" height=\"85%\">\u003C\u002Fp>\n\u003Ch6 align=\"center\">FCN-8 (\u003Ca href=\"https:\u002F\u002Fwww.overleaf.com\u002Fread\u002Fkkqntfxnvbsk\">view on Overleaf\u003C\u002Fa>)\u003C\u002Fh6>\n\n\n\u003Cp align=\"center\">\u003Cimg  src=\"https:\u002F\u002Fuser-images.githubusercontent.com\u002F17570785\u002F50308873-e2eb6e00-049c-11e9-9587-9da6bdec011b.png\" width=\"85%\" height=\"85%\">\u003C\u002Fp>\n\u003Ch6 align=\"center\">FCN-32 (\u003Ca href=\"https:\u002F\u002Fwww.overleaf.com\u002Fread\u002Fwsxpmkqvjnbs\">view on Overleaf\u003C\u002Fa>)\u003C\u002Fh6>\n\n\n\u003Cp align=\"center\">\u003Cimg  src=\"https:\u002F\u002Fuser-images.githubusercontent.com\u002F17570785\u002F50308911-03b3c380-049d-11e9-92d9-ce15669017ad.png\" width=\"85%\" height=\"85%\">\u003C\u002Fp>\n\u003Ch6 align=\"center\">Holistically-Nested Edge Detection (\u003Ca href=\"https:\u002F\u002Fwww.overleaf.com\u002Fread\u002Fjxhnkcnwhfxp\">view on Overleaf\u003C\u002Fa>)\u003C\u002Fh6>\n\n## Getting Started\n1. Install the following packages on Ubuntu.\n    * Ubuntu 16.04\n        ```\n        sudo apt-get install texlive-latex-extra\n        ```\n\n    * Ubuntu 18.04.2\nBase on this [website](https:\u002F\u002Fgist.github.com\u002Frain1024\u002F98dd5e2c6c8c28f9ea9d), please install the following packages.\n        ```\n        sudo apt-get install texlive-latex-base\n        sudo apt-get install texlive-fonts-recommended\n        sudo apt-get install texlive-fonts-extra\n        sudo apt-get install texlive-latex-extra\n        ```\n\n    * Windows\n    1. Download and install [MikTeX](https:\u002F\u002Fmiktex.org\u002Fdownload).\n    2. Download and install bash runner on Windows, recommends [Git bash](https:\u002F\u002Fgit-scm.com\u002Fdownload\u002Fwin) or Cygwin(https:\u002F\u002Fwww.cygwin.com\u002F)\n\n2. Execute the example as followed.\n    ```\n    cd pyexamples\u002F\n    bash ..\u002Ftikzmake.sh test_simple\n    ```\n\n## TODO\n\n- [X] Python interface\n- [ ] Add easy legend functionality\n- [ ] Add more layer shapes like TruncatedPyramid, 2DSheet etc\n- [ ] Add examples for RNN and likes.\n\n## Latex usage\n\nSee [`examples`](examples) directory for usage.\n\n## Python usage\n\nFirst, create a new directory and a new Python file:\n\n    $ mkdir my_project\n    $ cd my_project\n    vim my_arch.py\n\nAdd the following code to your new file:\n\n```python\nimport sys\nsys.path.append('..\u002F')\nfrom pycore.tikzeng import *\n\n# defined your arch\narch = [\n    to_head( '..' ),\n    to_cor(),\n    to_begin(),\n    to_Conv(\"conv1\", 512, 64, offset=\"(0,0,0)\", to=\"(0,0,0)\", height=64, depth=64, width=2 ),\n    to_Pool(\"pool1\", offset=\"(0,0,0)\", to=\"(conv1-east)\"),\n    to_Conv(\"conv2\", 128, 64, offset=\"(1,0,0)\", to=\"(pool1-east)\", height=32, depth=32, width=2 ),\n    to_connection( \"pool1\", \"conv2\"),\n    to_Pool(\"pool2\", offset=\"(0,0,0)\", to=\"(conv2-east)\", height=28, depth=28, width=1),\n    to_SoftMax(\"soft1\", 10 ,\"(3,0,0)\", \"(pool1-east)\", caption=\"SOFT\"  ),\n    to_connection(\"pool2\", \"soft1\"),\n    to_end()\n    ]\n\ndef main():\n    namefile = str(sys.argv[0]).split('.')[0]\n    to_generate(arch, namefile + '.tex' )\n\nif __name__ == '__main__':\n    main()\n```\n\nNow, run the program as follows:\n\n    bash ..\u002Ftikzmake.sh my_arch\n\n\n\n","PlotNeuralNet 是一个用于绘制神经网络图的 LaTeX 代码库。该项目提供了一系列 TeX 代码模板，帮助用户轻松创建复杂的神经网络架构图，适用于学术报告和演示文稿。其核心功能包括丰富的预定义层类型（如卷积层、池化层等）以及灵活的自定义选项，支持多种常见深度学习模型的可视化。此外，项目还提供了 Python 接口，方便编程方式生成图表。适用于需要在论文或演讲中展示神经网络结构的研究人员和学生。",2,"2026-06-11 03:34:54","high_star"]