a d @sdZddlZddlmmZejejejdddZejejejdddZeje ejdd d Z dejeje d d dZ dejeje d ddZ dS)zALosses based on the divergence between probability distributions.N)pqreturncCsX|j\}}}}tj||||||||||dd}|d||}|S)Nnone) reduction)shapeFZkl_divZreshapelogsumview)rrbatchZchansheightwidthZ unsummed_klZ kl_valuesra/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/kornia/losses/divergence.py _kl_div_2ds *rcCs(d||}dt||dt||S)Ng?)r)rrmrrr _js_div_2ds r)lossesrrcCs(|dkr |S|dkrt|St|S)Nrmean)torchrr )rrrrr _reduce_losssrrinputtargetrcCstt|||S)aCalculate the Jensen-Shannon divergence loss between heatmaps. Args: input: the input tensor with shape :math:`(B, N, H, W)`. target: the target tensor with shape :math:`(B, N, H, W)`. reduction: Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied, ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. Examples: >>> input = torch.full((1, 1, 2, 4), 0.125) >>> loss = js_div_loss_2d(input, input) >>> loss.item() 0.0 )rrrrrrjs_div_loss_2d srcCstt|||S)aCalculate the Kullback-Leibler divergence loss between heatmaps. Args: input: the input tensor with shape :math:`(B, N, H, W)`. target: the target tensor with shape :math:`(B, N, H, W)`. reduction: Specifies the reduction to apply to the output: ``'none'`` | ``'mean'`` | ``'sum'``. ``'none'``: no reduction will be applied, ``'mean'``: the sum of the output will be divided by the number of elements in the output, ``'sum'``: the output will be summed. Examples: >>> input = torch.full((1, 1, 2, 4), 0.125) >>> loss = kl_div_loss_2d(input, input) >>> loss.item() 0.0 )rrrrrrkl_div_loss_2d5sr)r)r) __doc__rZtorch.nn.functionalnnZ functionalr ZTensorrrstrrrrrrrrs