brainpy.math.autograd.vector_grad
brainpy.math.autograd.vector_grad#
- brainpy.math.autograd.vector_grad(func, dyn_vars=None, grad_vars=None, argnums=None, return_value=False, has_aux=None)[source]#
Take vector-valued gradients for function
func
.Same as brainpy.math.grad, brainpy.math.jacrev and brainpy.math.jacfwd, the returns in this function are different for different argument settings.
When “grad_vars” is None
“has_aux=False” + “return_value=False” =>
arg_grads
.“has_aux=True” + “return_value=False” =>
(arg_grads, aux_data)
.“has_aux=False” + “return_value=True” =>
(arg_grads, loss_value)
.“has_aux=True” + “return_value=True” =>
(arg_grads, loss_value, aux_data)
.
When “grad_vars” is not None and “argnums” is None
“has_aux=False” + “return_value=False” =>
var_grads
.“has_aux=True” + “return_value=False” =>
(var_grads, aux_data)
.“has_aux=False” + “return_value=True” =>
(var_grads, loss_value)
.“has_aux=True” + “return_value=True” =>
(var_grads, loss_value, aux_data)
.
When “grad_vars” is not None and “argnums” is not None
“has_aux=False” + “return_value=False” =>
(var_grads, arg_grads)
.“has_aux=True” + “return_value=False” =>
((var_grads, arg_grads), aux_data)
.“has_aux=False” + “return_value=True” =>
((var_grads, arg_grads), loss_value)
.“has_aux=True” + “return_value=True” =>
((var_grads, arg_grads), loss_value, aux_data)
.
- Parameters
func (Function whose Jacobian is to be computed.) –
dyn_vars (optional, JaxArray, sequence of JaxArray, dict) – The dynamically changed variables used in
func
.grad_vars (optional, JaxArray, sequence of JaxArray, dict) – The variables in
func
to take their gradients.has_aux (optional, bool) – Indicates whether
fun
returns a pair where the first element is considered the output of the mathematical function to be differentiated and the second element is auxiliary data. Default False.return_value (bool) – Whether return the loss value.
argnums (Optional, integer or sequence of integers. Specifies which) – positional argument(s) to differentiate with respect to (default
0
).
- Returns
func – The vector gradient function.
- Return type
callable