encode_pytorch_tensor_to_plain_matrix

Engine.encode_pytorch_tensor_to_plain_matrix(tensor, level)

Encodes a PyTorch tensor into a plain matrix for matrix multiplication.

• Input:
  • tensor: torch.Tensor
  • The tensor should be a square matrix, with both dimensions equal to Engine.slot_count.
  • level: optional
    • Specifies the maximum multiplication level for encoding. Lower levels reduce space usage but also reduce the maximum multiplication depth.
• Output:
  • PlainMatrix

import torch

from desilofhe import Engine

engine = Engine(slot_count=64)

tensor = torch.arange(64 * 64).reshape(64, 64)
plain_matrix = engine.encode_pytorch_tensor_to_plain_matrix(tensor)
plain_matrix_level_2 = engine.encode_pytorch_tensor_to_plain_matrix(
    tensor, level=2
)