# MIT License
#
# Copyright (c) 2021 Soohwan Kim and Sangchun Ha and Soyoung Cho
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
import torch.nn as nn
from torch import Tensor
from omegaconf import DictConfig
from .. import register_criterion
from ..cross_entropy.configuration import CrossEntropyLossConfigs
from ...tokenizers.tokenizer import Tokenizer
[docs]@register_criterion("cross_entropy", dataclass=CrossEntropyLossConfigs)
class CrossEntropyLoss(nn.Module):
r"""
The negative log likelihood loss. It is useful to train a classification
problem with `C` classes.
If provided, the optional argument :attr:`weight` should be a 1D Tensor assigning
weight to each of the classes. This is particularly useful when you have an
unbalanced training set.
The `input` given through a forward call is expected to contain
log-probabilities of each class. `input` has to be a Tensor of size either
:math:`(minibatch, C)` or :math:`(minibatch, C, d_1, d_2, ..., d_K)`
with :math:`K \geq 1` for the `K`-dimensional case (described later).
Obtaining log-probabilities in a neural network is easily achieved by
adding a `LogSoftmax` layer in the last layer of your network.
You may use `CrossEntropyLoss` instead, if you prefer not to add an extra
layer.
The `target` that this loss expects should be a class index in the range :math:`[0, C-1]`
where `C = number of classes`; if `ignore_index` is specified, this loss also accepts
this class index (this index may not necessarily be in the class range).
The unreduced (i.e. with :attr:`reduction` set to ``'none'``) loss can be described as:
.. math::
\ell(x, y) = L = \{l_1,\dots,l_N\}^\top, \quad
l_n = - w_{y_n} x_{n,y_n}, \quad
w_{c} = \text{weight}[c] \cdot \mathbb{1}\{c \not= \text{ignore\_index}\},
where :math:`x` is the input, :math:`y` is the target, :math:`w` is the weight, and
:math:`N` is the batch size. If :attr:`reduction` is not ``'none'``
(default ``'mean'``), then
.. math::
\ell(x, y) = \begin{cases}
\sum_{n=1}^N \frac{1}{\sum_{n=1}^N w_{y_n}} l_n, &
\text{if reduction} = \text{`mean';}\\
\sum_{n=1}^N l_n, &
\text{if reduction} = \text{`sum'.}
\end{cases}
Can also be used for higher dimension inputs, such as 2D images, by providing
an input of size :math:`(minibatch, C, d_1, d_2, ..., d_K)` with :math:`K \geq 1`,
where :math:`K` is the number of dimensions, and a target of appropriate shape
(see below). In the case of images, it computes NLL loss per-pixel.
Args:
configs (DictConfig): hydra configuration set
tokenizer (Tokenizer): tokenizer is in charge of preparing the inputs for a model.
Inputs: logits, targets
- logits (torch.FloatTensor): probability distribution value from model and it has a logarithm shape.
The `FloatTensor` of size ``(batch, seq_length, num_classes)``
- targets (torch.LongTensor): ground-truth encoded to integers which directly point a word in label.
The `LongTensor` of size ``(batch, target_length)``
Returns: loss
* loss (float): loss for training
Examples::
>>> B, T1, C, T2 = 3, 128, 4, 10
>>> loss = CrossEntropyLoss()
>>> inputs = torch.randn(B, T1, C, requires_grad=True)
>>> targets = torch.empty(B, T2, dtype=torch.long).random_(T2)
>>> outputs = loss(inputs, targets)
>>> outputs.backward()
"""
def __init__(
self,
configs: DictConfig,
tokenizer: Tokenizer,
) -> None:
super(CrossEntropyLoss, self).__init__()
self.cross_entropy_loss = nn.CrossEntropyLoss(
reduction=configs.criterion.reduction,
ignore_index=tokenizer.pad_id,
)
def forward(self, logits: Tensor, targets: Tensor) -> Tensor:
max_target_length = targets.size(1)
max_logits_length = logits.size(1)
if max_logits_length > max_target_length:
logits = logits[:, :max_target_length, :]
elif max_target_length > max_logits_length:
targets = targets[:, :max_logits_length]
logits = logits.contiguous().view(-1, logits.size(-1))
return self.cross_entropy_loss(
logits.contiguous().view(-1, logits.size(-1)),
targets.contiguous().view(-1),
)