diff options
author | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2021-07-29 23:59:52 +0200 |
---|---|---|
committer | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2021-07-29 23:59:52 +0200 |
commit | 34098ccbbbf6379c0bd29a987440b8479c743746 (patch) | |
tree | a8c68e3036503049fc7034c677ec855465f7a8e0 /text_recognizer/criterions/label_smoothing_loss.py | |
parent | c032ffb05a7ed86f8fe5d596f94e8997c558cae8 (diff) |
Configs, refactor with attrs, fix attr bug in iam
Diffstat (limited to 'text_recognizer/criterions/label_smoothing_loss.py')
-rw-r--r-- | text_recognizer/criterions/label_smoothing_loss.py | 42 |
1 files changed, 0 insertions, 42 deletions
diff --git a/text_recognizer/criterions/label_smoothing_loss.py b/text_recognizer/criterions/label_smoothing_loss.py deleted file mode 100644 index 40a7609..0000000 --- a/text_recognizer/criterions/label_smoothing_loss.py +++ /dev/null @@ -1,42 +0,0 @@ -"""Implementations of custom loss functions.""" -import torch -from torch import nn -from torch import Tensor -import torch.nn.functional as F - - -class LabelSmoothingLoss(nn.Module): - """Label smoothing cross entropy loss.""" - - def __init__( - self, label_smoothing: float, vocab_size: int, ignore_index: int = -100 - ) -> None: - assert 0.0 < label_smoothing <= 1.0 - self.ignore_index = ignore_index - super().__init__() - - smoothing_value = label_smoothing / (vocab_size - 2) - one_hot = torch.full((vocab_size,), smoothing_value) - one_hot[self.ignore_index] = 0 - self.register_buffer("one_hot", one_hot.unsqueeze(0)) - - self.confidence = 1.0 - label_smoothing - - def forward(self, output: Tensor, targets: Tensor) -> Tensor: - """Computes the loss. - - Args: - output (Tensor): Predictions from the network. - targets (Tensor): Ground truth. - - Shapes: - outpus: Batch size x num classes - targets: Batch size - - Returns: - Tensor: Label smoothing loss. - """ - model_prob = self.one_hot.repeat(targets.size(0), 1) - model_prob.scatter_(1, targets.unsqueeze(1), self.confidence) - model_prob.masked_fill_((targets == self.ignore_index).unsqueeze(1), 0) - return F.kl_div(output, model_prob, reduction="sum") |