ba256835a4f33d9139a70b6440c3223123132bc8,torchnet/meter/confusionmeter.py,ConfusionMeter,add,#ConfusionMeter#,42

Before Change

                    "multi-label setting is not supported"
 
        pred = output.argmax(1)
        for i,n in enumerate(pred):
            pos = onehot and target[i].argmax(0) or int(target[i])
            self.conf[pos][n] += 1

    def value(self):
        if self.normalized:
            conf = self.conf.astype(np.float32)
            return conf / conf.sum(1).clip(min=1e-12)[:,None]

After Change

        assert predicted.shape[0] == target.shape[0], \
            "number of targets and predicted outputs do not match"

        if np.ndim(predicted) != 1:
            assert predicted.shape[1] == self.k, \
                "number of predictions does not match size of confusion matrix"
            predicted = np.argmax(predicted, 1)
        else:
            assert (predicted.max() < self.k) and (predicted.min() >= 0), \
                "predicted values are not between 1 and k"

        onehot_target = np.ndim(target) != 1
        if onehot_target:
            assert target.shape[1] == self.k, \
                "Onehot target does not match size of confusion matrix"
            assert (target >= 0).all() and (target <= 1).all(), \
                "in one-hot encoding, target values should be 0 or 1"
            assert (target.sum(1) == 1).all(), \
                "multi-label setting is not supported"
            target = np.argmax(target, 1)
        else:
            assert (predicted.max() < self.k) and (predicted.min() >= 0), \
                "predicted values are not between 1 and k"

        // hack for bincounting 2 arrays together
        x = predicted + self.k * target
        bincount_2d = np.bincount(x.astype(np.int32),
                                  minlength=self.k ** 2)
        assert bincount_2d.size == self.k ** 2
        conf = bincount_2d.reshape((self.k, self.k))

        self.conf += conf

    def value(self):

Instances