das.loss#

class das.loss.TMSE(batch_size, trunc=None)[source]#

Initializes Loss class.

Parameters
  • reduction

    Type of tf.keras.losses.Reduction to apply to loss. Default value is AUTO. AUTO indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to SUM_OVER_BATCH_SIZE. When used with tf.distribute.Strategy, outside of built-in training loops such as tf.keras compile and fit, using AUTO or SUM_OVER_BATCH_SIZE will raise an error. Please see this custom training [tutorial](

  • name – Optional name for the instance.

call(y_true, y_pred)[source]#

Temporal MSE Loss

Temporal MSE Loss Function Proposed in Y. A. Farha et al. MS-TCN: Multi-Stage Temporal Convolutional Network for ActionSegmentation in CVPR2019 arXiv: https://arxiv.org/pdf/1903.01945.pdf

Parameters
  • y_true (_type_) – _description_

  • y_pred (_type_) – _description_

  • trunc (_type_, optional) – _description_. Defaults to None.

Returns

_description_

Return type

_type_

class das.loss.WeightedLoss(losses, loss_weights)[source]#

Initializes Loss class.

Parameters
  • reduction

    Type of tf.keras.losses.Reduction to apply to loss. Default value is AUTO. AUTO indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to SUM_OVER_BATCH_SIZE. When used with tf.distribute.Strategy, outside of built-in training loops such as tf.keras compile and fit, using AUTO or SUM_OVER_BATCH_SIZE will raise an error. Please see this custom training [tutorial](

  • name – Optional name for the instance.

call(y_true, y_pred)[source]#

Invokes the Loss instance.

Parameters
  • y_true – Ground truth values. shape = [batch_size, d0, .. dN], except sparse loss functions such as sparse categorical crossentropy where shape = [batch_size, d0, .. dN-1]

  • y_pred – The predicted values. shape = [batch_size, d0, .. dN]

Returns

Loss values with the shape [batch_size, d0, .. dN-1].