mae
xlinear_losses.mae
Mean absolute error (masked mean when mask is given).
mae(pred, target, mask=None)
| Parameter | Type | Default | Description |
|---|---|---|---|
pred |
jnp.ndarray |
- | (undocumented) |
target |
jnp.ndarray |
- | (undocumented) |
mask |
jnp.ndarray | None |
None |
(undocumented) |
Returns: jnp.ndarray
mse
xlinear_losses.mse
Mean squared error (masked mean when mask is given).
mse(pred, target, mask=None)
| Parameter | Type | Default | Description |
|---|---|---|---|
pred |
jnp.ndarray |
- | (undocumented) |
target |
jnp.ndarray |
- | (undocumented) |
mask |
jnp.ndarray | None |
None |
(undocumented) |
Returns: jnp.ndarray
huber
xlinear_losses.huber
Huber loss with delta = 1.0 (masked mean when mask is given).
huber(pred, target, mask=None)
| Parameter | Type | Default | Description |
|---|---|---|---|
pred |
jnp.ndarray |
- | (undocumented) |
target |
jnp.ndarray |
- | (undocumented) |
mask |
jnp.ndarray | None |
None |
(undocumented) |
Returns: jnp.ndarray
resolve
xlinear_losses.resolve
Return a callable loss from either a registry string or a callable.
Callables receive (pred, target, mask); a custom loss should accept an optional mask (def my_loss(pred, target, mask=None): ...).
resolve(loss)
| Parameter | Type | Default | Description |
|---|---|---|---|
loss |
str | LossFn |
- | (undocumented) |
Returns: LossFn (a callable loss function).