Loss

Loss functions. Each takes (input, target) and returns a scalar loss tensor.

binaryCrossEntropyWithLogit

binaryCrossEntropyWithLogit inp target

$\text{BCE} = \max(x,0) - x \cdot y + \ln(1 + e^{-\lvert x \rvert})$

Parameters

• inp : Tensor
• target : Tensor

Returns Tensor

cosineEmbedding

cosineEmbedding margin x1 x2 target

Cosine embedding loss for similarity learning.

Parameters

• margin : float
• x1 : Tensor
• x2 : Tensor
• target : Tensor

Returns Tensor

crossEntropy

crossEntropy inp target

$H(p,q) = -(1/n)\sum \log\text{softmax}(x)_{y_i}$

Parameters

• inp : Tensor
• target : Tensor

Returns Tensor

ctc

ctc logProbs targets inputLengths targetLengths

CTC loss for sequence-to-sequence alignment.

Parameters

• logProbs : Tensor
• targets : Tensor
• inputLengths : Tensor
• targetLengths : Tensor

Returns Tensor

huber

huber delta inp target

Huber loss: smooth combination of L1 and L2.

Parameters

• delta : float
• inp : Tensor
• target : Tensor

Returns Tensor

klDiv

klDiv inp target

$\text{KL}(p \| q) = (1/n)\sum p_i (\log p_i - q_i)$. Expects log-probabilities as input and probabilities as target.

Parameters

• inp : Tensor
• target : Tensor

Returns Tensor

l1

l1 inp target

$\text{L1} = (1/n)\sum|x_i - y_i|$

Parameters

• inp : Tensor
• target : Tensor

Returns Tensor

mse

mse inp target

$\text{MSE} = (1/n)\sum(x_i - y_i)^2$

Parameters

• inp : Tensor
• target : Tensor

Returns Tensor

nll

nll inp target

$\text{NLL} = -(1/n)\sum x_{i,y_i}$

Parameters

• inp : Tensor
• target : Tensor

Returns Tensor

smoothL1

smoothL1 beta inp target

$\text{SmoothL1} = (1/n)\sum z_i$ where $z_i = 0.5 x_i^2/\beta$ if $|x_i| < \beta$, else $|x_i| - 0.5\beta$

Parameters

• beta : float
• inp : Tensor
• target : Tensor

Returns Tensor

tripletMargin

tripletMargin margin anchor positive negative

Triplet margin loss for metric learning.

Parameters

• margin : float
• anchor : Tensor
• positive : Tensor
• negative : Tensor

Returns Tensor