Source code for aimet_torch.gptvq.defs

# -*- mode: python -*-
# =============================================================================
#  @@-COPYRIGHT-START-@@
#
#  Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved.
#
#  Redistribution and use in source and binary forms, with or without
#  modification, are permitted provided that the following conditions are met:
#
#  1. Redistributions of source code must retain the above copyright notice,
#     this list of conditions and the following disclaimer.
#
#  2. Redistributions in binary form must reproduce the above copyright notice,
#     this list of conditions and the following disclaimer in the documentation
#     and/or other materials provided with the distribution.
#
#  3. Neither the name of the copyright holder nor the names of its contributors
#     may be used to endorse or promote products derived from this software
#     without specific prior written permission.
#
#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
#  AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
#  IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
#  ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
#  LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
#  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
#  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
#  INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
#  CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
#  ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
#  POSSIBILITY OF SUCH DAMAGE.
#
#  SPDX-License-Identifier: BSD-3-Clause
#
#  @@-COPYRIGHT-END-@@
# =============================================================================
"""Type definitions that are used across GPTVQ"""

from dataclasses import dataclass
from typing import Callable, Any, Optional

from torch import nn
from torch.utils.data import DataLoader

GPTVQSupportedModules = (nn.Linear, nn.Conv2d)
DAMPENING_PERCENTAGE = 0.01
BLOCK_STRIDE = 128


[docs]@dataclass class GPTVQParameters: """ Data carrier containing GPTVQ parameters """ # pylint: disable=too-many-instance-attributes data_loader: DataLoader forward_fn: Callable[[nn.Module, Any], Any] row_axis: int = 0 col_axis: int = 1 rows_per_block: int = 32 cols_per_block: int = 256 vector_dim: int = 2 vector_bw: int = 8 vector_stride: int = 1 index_bw: int = 6 num_of_kmeans_iterations: int = 100 assignment_chunk_size: Optional[int] = None