PlotNeuralNet

You can programmatically define neural network architectures using Python. This involves importing functions from pycore.tikzeng and building an arch list containing layer definitions.

Workflow

1. Create a new directory and a Python file.
2. Import tikzeng (ensure the project root is in sys.path).
3. Define an arch list using functions like to_Conv, to_Pool, to_SoftMax, and to_connection.
4. Use to_generate(arch, filename) to produce the .tex file.
5. Run the script using the tikzmake.sh helper script to compile the LaTeX into an image.

Example Architecture Definition

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()

Compiling the output

After writing your script (e.g., my_arch.py), run it via the shell script:

bash ../tikzmake.sh my_arch