softmax_cross_entropy.py 文件源码

def backward_cpu(self, inputs, grad_outputs):
        x, t = inputs
        gloss = grad_outputs[0]
        if hasattr(self, 'y'):
            y = self.y.copy()
        else:
            y = log_softmax._log_softmax(x, self.use_cudnn)
            numpy.exp(y, out=y)
        if y.ndim == 2:
            gx = y
            gx[numpy.arange(len(t)), numpy.maximum(t, 0)] -= 1
            if self.class_weight is not None:
                c = self.class_weight[
                    numpy.arange(len(t)), numpy.maximum(t, 0)]
                gx *= numpy.broadcast_to(numpy.expand_dims(c, 1), gx.shape)
            gx *= (t != self.ignore_label).reshape((len(t), 1))
        else:
            # in the case where y.ndim is higher than 2,
            # we think that a current implementation is inefficient
            # because it yields two provisional arrays for indexing.
            n_unit = t.size // len(t)
            gx = y.reshape(y.shape[0], y.shape[1], -1)
            fst_index = numpy.arange(t.size) // n_unit
            trd_index = numpy.arange(t.size) % n_unit
            gx[fst_index, numpy.maximum(t.ravel(), 0), trd_index] -= 1
            if self.class_weight is not None:
                c = self.class_weight.reshape(gx.shape)
                c = c[fst_index, numpy.maximum(t.ravel(), 0), trd_index]
                c = c.reshape(y.shape[0], 1, -1)
                gx *= numpy.broadcast_to(c, gx.shape)
            gx *= (t != self.ignore_label).reshape((len(t), 1, -1))
            gx = gx.reshape(y.shape)
        gx *= gloss * self._coeff
        return gx, None