# Copyright (c) 2021 Graphcore Ltd. All rights reserved.
# Copyright 2019 Shigeki Karita
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# This file has been modified by Graphcore Ltd.
# Main change is modifying the forward function.

import torch


class LayerNorm(torch.nn.LayerNorm):
    """Layer normalization module.

    Args:
        nout (int): Output dim size.
        dim (int): Dimension to be normalized.

    """

    def __init__(self, nout, dim=-1, eps_=1e-5):
        """Construct an LayerNorm object."""
        super(LayerNorm, self).__init__(nout, eps=eps_)
        self.dim = dim

    def forward(self, x):
        """Apply layer normalization.

        Args:
            x (torch.Tensor): Input tensor.

        Returns:
            torch.Tensor: Normalized tensor.

        """
        if self.dim == -1:
            return super(LayerNorm, self).forward(x)
        return super(LayerNorm, self).forward(x.transpose(self.dim, -1)).transpose(self.dim, -1)