Encode Boards

Setup

import importlib.util

DEV = True

if importlib.util.find_spec("google.colab") is not None:
    MODE = "colab-dev" if DEV else "colab"
else:
    MODE = "local"

if MODE == "colab":
    %pip install -q lczerolens
elif MODE == "colab-dev":
    !rm -r lczerolens
    !git clone https://github.com/Xmaster6y/lczerolens -b main
    %pip install -q ./lczerolens

Create a Board

Create a board from a FEN string.

from lczerolens import LczeroBoard

board = LczeroBoard("r1qr3k/pp3pB1/1np1pb2/8/3P3P/2N2PR1/PP1Q2P1/2KR4 b - - 0 22")
display(board)

Encode a Board

We can now encode the board into a tensor, and we’ll visualize the planes.

import IPython.display

input_tensor = board.to_input_tensor()

plane_idx = 3  # our rooks

svg_board, svg_colorbar = board.render_heatmap(input_tensor[plane_idx])
display(IPython.display.HTML(f"{svg_board}{svg_colorbar}"))

See the to_input_tensor method for more details.