masked_mae
chronax.loss.masked_mae
Mean Absolute Error with multiplicative masking.
| Parameter | Type | Default | Description |
|---|---|---|---|
y |
jnp.ndarray |
- | (undocumented) |
y_hat |
jnp.ndarray |
- | (undocumented) |
mask |
Optional[jnp.ndarray] |
None |
(undocumented) |
horizon_weight |
Optional[jnp.ndarray] |
None |
(undocumented) |
Returns: jnp.ndarray (The scalar loss value.)
masked_mse
chronax.loss.masked_mse
Mean Squared Error with multiplicative masking.
| Parameter | Type | Default | Description |
|---|---|---|---|
y |
jnp.ndarray |
- | (undocumented) |
y_hat |
jnp.ndarray |
- | (undocumented) |
mask |
Optional[jnp.ndarray] |
None |
(undocumented) |
horizon_weight |
Optional[jnp.ndarray] |
None |
(undocumented) |
Returns: jnp.ndarray (The scalar loss value.)
LOSSES
chronax.loss.LOSSES
A dictionary mapping loss names ("mae", "mse") to their respective loss functions (masked_mae, masked_mse).
resolve
chronax.loss.resolve
Return a callable loss from either a registry string or a callable.
Mirrors :func:chronax.models.gru.gru_losses.resolve. Raises ValueError for unknown strings, naming the registered options.
| Parameter | Type | Default | Description |
|---|---|---|---|
loss |
- | - | (undocumented) |
Returns: A callable loss function.
Raises: ValueError (for unknown strings, naming the registered options.)