6e5cf676b113af8d70e34224f23bc8eace618856,mloop/nnlearner.py,SingleNeuralNet,fit,#SingleNeuralNet#Any#Any#,120

Before Change


                + str(self.tf_session.run(
                        self.loss_func,
                        feed_dict={self.input_placeholder: params,
                                   self.output_placeholder: [[c] for c in costs],
                                   self.regularisation_coefficient_placeholder: 0,
                                   })))

After Change


                                                   self.regularisation_coefficient_placeholder: self.regularisation_coefficient,
                                                   self.keep_prob_placeholder: self.keep_prob,
                                                   })
            (l, ul) = self._loss(params, costs)
            self.log.debug("Fit neural network with total training cost " + str(l)
                    + ", with unregularized cost " + str(ul))
            if l > threshold:
                break
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 3

Instances


Project Name: michaelhush/M-LOOP
Commit Name: 6e5cf676b113af8d70e34224f23bc8eace618856
Time: 2017-05-02
Author: harry.slatyer@gmail.com
File Name: mloop/nnlearner.py
Class Name: SingleNeuralNet
Method Name: fit


Project Name: IBM/adversarial-robustness-toolbox
Commit Name: 64764718080b11c8fb91df34c12e0ce8ac54aa4e
Time: 2018-05-15
Author: M.N.Tran@ibm.com
File Name: art/classifiers/pytorch.py
Class Name: PyTorchClassifier
Method Name: fit


Project Name: IBM/adversarial-robustness-toolbox
Commit Name: 9b9a42de05056b418f98e3635f2cffd747123548
Time: 2018-05-16
Author: M.N.Tran@ibm.com
File Name: art/classifiers/pytorch.py
Class Name: PyTorchClassifier
Method Name: loss_gradient