PerfectLCA Class Reference

Inheritance diagram for PerfectLCA:

Collaboration diagram for PerfectLCA:

Public Member Functions
def	__init__ (self, ignore_index, output_transform, device='cpu')
def	reset (self)
def	update (self, output)
def	compute (self)

Public Attributes
	ignore_index
	Ignore index.
	device
	CPU or GPU.

Protected Attributes
	_per_corrects
	Good samples.
	_num_examples
	Total samples.

Detailed Description

Computes the rate of perfectly predicted LCAS matrices over a batch.

``output_transform`` should return the following items: ``(edge_pred, edge_y, edge_index, u_y, batch, num_graphs)``.

* ``edge_pred`` must contain edge prediction logits and have shape (num_edges_in_batch, edge_classes);
* ``edge_y`` must contain edge ground-truth class indices and have shape (num_edges_in_batch, 1);
* ``edge index`` maps edges to its nodes;
* ``u_y`` is the signal/background class (always 1 in the current setting);
* ``batch`` maps nodes to their graph;
* ``num_graphs`` is the number of graph in a batch (could be derived from ``batch`` also).

.. seealso::
    `Ignite metrics <https://pytorch.org/ignite/metrics.html>`_

:param ignore_index: Class or list of classes to ignore during the computation (e.g. padding).
:type ignore_index: list[int]
:param output_transform: Function to transform engine's output to desired output.
:type output_transform: `function <https://docs.python.org/3/glossary.html#term-function>`_
:param device: ``cpu`` or ``gpu``.
:type device: str

Definition at line 17 of file metrics.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			ignore_index,
			output_transform,
			device = 'cpu'
	)

Initialization.

Definition at line 41 of file metrics.py.

    def __init__(self, ignore_index, output_transform, device='cpu'):
        """
        Initialization.
        """
        
        self.ignore_index = ignore_index if isinstance(ignore_index, list) else [ignore_index]
        
        self.device = device
        
        self._per_corrects = None
        
        self._num_examples = None
 
        super(PerfectLCA, self).__init__(output_transform=output_transform, device=device)
 

Member Function Documentation

compute()

def compute

(

self

)

Final result.

Definition at line 101 of file metrics.py.

    def compute(self):
        """
        Final result.
        """
        if self._num_examples == 0:
            raise NotComputableError(
                "CustomAccuracy must have at least one example before it can be computed."
            )
        return self._per_corrects / self._num_examples
 
 

reset()

def reset

(

self

)

Resets counters.

Definition at line 57 of file metrics.py.

    def reset(self):
        """
        Resets counters.
        """
        self._per_corrects = 0
        self._num_examples = 0
 
        super(PerfectLCA, self).reset()
 

update()

def update	(		self,
			output
	)

Updates counts.

Definition at line 67 of file metrics.py.

    def update(self, output):
        """
        Updates counts.
        """
        edge_pred, edge_y, edge_index, u_y, batch, num_graphs = output
 
        num_graphs = num_graphs.item()
 
        probs = torch.softmax(edge_pred, dim=1)
        winners = probs.argmax(dim=1)
 
        assert winners.shape == edge_y.shape, 'Edge predictions shape does not match target shape'
 
        # Create a mask for the zeroth elements (padded entries)
        mask = torch.ones(edge_y.size(), dtype=torch.long, device=self.device)
        for ig_class in self.ignore_index:
            mask &= (edge_y != ig_class)
 
        # Zero the respective entries in the predictions
        y_pred_mask = winners * mask
        y_mask = edge_y * mask
 
        # (N) compare the masked predictions with the target. The padded will be equal due to masking
        truth = y_pred_mask.eq(y_mask) + 0  # +0 so it's not bool but 0 and 1
        truth = scatter(truth, edge_index[0], reduce="min")
        truth = scatter(truth, batch, reduce="min")
 
        # Count the number of zero wrong predictions across the batch
        batch_perfect = truth.sum().item()
 
        self._per_corrects += batch_perfect
        self._num_examples += num_graphs
 

Member Data Documentation

_num_examples

_num_examples

protected

Total samples.

Definition at line 52 of file metrics.py.

_per_corrects

_per_corrects

protected

Good samples.

Definition at line 50 of file metrics.py.

device

device

CPU or GPU.

Definition at line 48 of file metrics.py.

ignore_index

ignore_index

Ignore index.

Definition at line 46 of file metrics.py.

---

The documentation for this class was generated from the following file:

• analysis/scripts/grafei/model/metrics.py