|
__init__(self,
input_dim=None,
output_dim=None,
dtype=None)
If the input dimension and the output dimension are
unspecified, they will be set when the `train` or `execute`
method is called for the first time. |
|
|
|
|
|
_stop_training(self,
*args,
**kwargs)
Transform the data and labels lists to array objects and reshape them. |
|
|
|
_train(self,
x,
labels)
Cumulate all input data in a one dimensional list. |
|
|
|
stop_training(self,
*args,
**kwargs)
Transform the data and labels lists to array objects and reshape them. |
|
|
|
train(self,
x,
labels)
Cumulate all input data in a one dimensional list. |
|
|
Inherited from unreachable.newobject :
__long__ ,
__native__ ,
__nonzero__ ,
__unicode__ ,
next
|
|
|
|
_label(self,
x,
*args,
**kargs) |
|
|
|
_prob(self,
x,
*args,
**kargs) |
|
|
|
execute(self,
x)
Process the data contained in `x`. |
|
|
|
label(self,
x,
*args,
**kwargs)
Returns an array with best class labels. |
|
|
|
prob(self,
x,
*args,
**kwargs)
Probability estimates. |
|
|
|
rank(self,
x,
threshold=None)
Returns ordered list with all labels ordered according to prob(x)
(e.g., [[3 1 2], [2 1 3], ...]). |
|
|
|
|
|
|
|
|
|
__call__(self,
x,
*args,
**kwargs)
Calling an instance of `Node` is equivalent to calling
its `execute` method. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_refcast(self,
x)
Helper function to cast arrays to the internal dtype. |
|
|
|
|
|
copy(self,
protocol=None)
Return a deep copy of the node. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
inverse(self,
y,
*args,
**kwargs)
Invert `y`. |
|
|
|
is_training(self)
Return True if the node is in the training phase,
False otherwise. |
|
|
|
save(self,
filename,
protocol=-1)
Save a pickled serialization of the node to `filename`. |
|
|
|
set_dtype(self,
t)
Set internal structures' dtype. |
|
|
|
|
|
|