BEAT - tpereira/llr_score

This algorithm is a legacy one. The API has changed since its implementation. New versions and forks will need to be updated.

Endpoint Groups 1

Algorithms have at least one input and one output. All algorithm endpoints are organized in groups. Groups are used by the platform to indicate which inputs and outputs are synchronized together. The first group is automatically synchronized with the channel defined by the block in which the algorithm is deployed.

Group: main

Endpoint Name	Data Format	Nature
scores_dev1	tutorial/probe_scores/1	Input
scores_dev2	tutorial/probe_scores/1	Input
machine	tutorial/linear_machine/1	Output

class Algorithm:

def __init__(self):
        self.positives_dev1 = []
        self.negatives_dev1 = []
        
        self.positives_dev2 = []
        self.negatives_dev2 = []
        
        self.machine = None

def accumulate_scores(self, inputs, input_name):

positives_test = []
        negatives_test = []

# accumulate the test scores
        data_test = inputs[input_name].data
        positives_test.extend([k.score for k in data_test.scores if k.template_identity == data_test.client_identity])
        negatives_test.extend([k.score for k in data_test.scores if k.template_identity != data_test.client_identity])
        
        return positives_test,negatives_test
    
    
    #def compute_fused_scores(self, machine, inputs, input_name1, input_name2):        
        #while inputs[input_name].hasMoreData():
            
    
    def compute_znorm(self, positives, negatives):
        import numpy
        
        data = numpy.concatenate((positives, negatives),axis=0)
        
        mean = numpy.mean(data, axis=0)
        std  = numpy.std(data, axis=0)
        
        return mean, std    
    
    def process(self, inputs, outputs):
        
        import numpy
        import bob
        
        #Loading the inputs
        self.positives_dev1, self.negatives_dev1 = self.accumulate_scores(inputs, "scores_dev1")
        self.positives_dev2, self.negatives_dev2 = self.accumulate_scores(inputs, "scores_dev2")
        
        
        # once all values are received, compute the fusion        
        if not(inputs.hasMoreData()):
        
            #Preparing data for fusion
            positives_dev = numpy.zeros(shape=(len(self.positives_dev1),2))
            negatives_dev = numpy.zeros(shape=(len(self.negatives_dev1),2))
        
            positives_dev[:,0] = self.positives_dev1
            positives_dev[:,1] = self.positives_dev2
            negatives_dev[:,0] = self.negatives_dev1
            negatives_dev[:,1] = self.negatives_dev2
        
        
            #normalizing data
            subtract, divide = self.compute_znorm(positives_dev,negatives_dev)
            positives_dev = numpy.divide(positives_dev-subtract, divide)
            negatives_dev = numpy.divide(negatives_dev-subtract, divide)

#Training the logistic regression machine
            trainer = bob.trainer.CGLogRegTrainer()
            machine = trainer.train(negatives_dev, positives_dev)
        
            outputs["machine"].write({
                'input_subtract': subtract,
                'input_divide':   divide,
                'weights':        machine.weights,
                'biases':         machine.biases,
            })        
        
        
        return True

The code for this algorithm in Python
The ruler at 80 columns indicate suggested POSIX line breaks (for readability).
The editor will automatically enlarge to accomodate the entirety of your input
Use keyboard shortcuts for search/replace and faster editing. For example, use Ctrl-F (PC) or Cmd-F (Mac) to search through this box

Could not find any documentation for this object.

Experiments

Attestation:

Privacy:

Status:

Name	Databases/Protocols	Analyzers
smarcel/tpereira/full_isv_multi/2/btas2015_face-periocular_mobio-female_det	mobio/1@female	tutorial/eerhter_postperf_iso/1
tpereira/tpereira/full_isv_multi/2/btas2015_face-periocular_cpqd-smartphone-male_det	cpqd/1@smartphone_male	tutorial/eerhter_postperf_iso/1
tpereira/tpereira/full_isv_multi/2/btas2015_face-periocular_mobio-male_det	mobio/1@male	tutorial/eerhter_postperf_iso/1
tpereira/tpereira/full_isv_multi/2/btas2015_face-periocular_cpqd-smartphone-female_det	cpqd/1@smartphone_female	tutorial/eerhter_postperf_iso/1
tpereira/tpereira/full_isv_multi/2/btas2015_face-periocular_mobio-female_det	mobio/1@female	tutorial/eerhter_postperf_iso/1

This table shows the number of times this algorithm has been successfully run using the given environment. Note this does not provide sufficient information to evaluate if the algorithm will run when submitted to different conditions.

algorithms tpereira llr_score_fusion 1

Endpoint Groups 1

Group: main

Experiments

algorithms

tpereira

llr_score_fusion

1