当前位置: 首页>>代码示例>>Python>>正文


Python loss.Loss方法代码示例

本文整理汇总了Python中mxnet.gluon.loss.Loss方法的典型用法代码示例。如果您正苦于以下问题:Python loss.Loss方法的具体用法?Python loss.Loss怎么用?Python loss.Loss使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在mxnet.gluon.loss的用法示例。


在下文中一共展示了loss.Loss方法的7个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: hybrid_forward

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def hybrid_forward(self, F, pred, label, sample_weight=None):
        """Loss forward"""
        if not self._from_logits:
            pred = F.sigmoid(pred)
        if self._sparse_label:
            one_hot = F.one_hot(label, self._num_class)
        else:
            one_hot = label > 0
        pt = F.where(one_hot, pred, 1 - pred)
        t = F.ones_like(one_hot)
        alpha = F.where(one_hot, self._alpha * t, (1 - self._alpha) * t)
        loss = -alpha * ((1 - pt) ** self._gamma) * F.log(F.minimum(pt + self._eps, 1))
        loss = _apply_weighting(F, loss, self._weight, sample_weight)
        if self._size_average:
            return F.mean(loss, axis=self._batch_axis, exclude=True)
        else:
            return F.sum(loss, axis=self._batch_axis, exclude=True) 
开发者ID:dmlc,项目名称:gluon-cv,代码行数:19,代码来源:loss.py

示例2: hybrid_forward

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def hybrid_forward(self, F, fts, ys, ftt, yt):
        """
        Semantic Alignment Loss
        :param F: Function
        :param yt: label for the target domain [N]
        :param ftt: features for the target domain [N, K]
        :param ys: label for the source domain [M]
        :param fts: features for the source domain [M, K]
        :return:
        """
        if self._fn:
            # Normalize ft
            fts = F.L2Normalization(fts, mode='instance')
            ftt = F.L2Normalization(ftt, mode='instance')

        fts_rpt = F.broadcast_to(fts.expand_dims(axis=0), shape=(self._bs_tgt, self._bs_src, self._embed_size))
        ftt_rpt = F.broadcast_to(ftt.expand_dims(axis=1), shape=(self._bs_tgt, self._bs_src, self._embed_size))

        dists = F.sum(F.square(ftt_rpt - fts_rpt), axis=2)

        yt_rpt = F.broadcast_to(yt.expand_dims(axis=1), shape=(self._bs_tgt, self._bs_src)).astype('int32')
        ys_rpt = F.broadcast_to(ys.expand_dims(axis=0), shape=(self._bs_tgt, self._bs_src)).astype('int32')

        y_same = F.equal(yt_rpt, ys_rpt).astype('float32')
        y_diff = F.not_equal(yt_rpt, ys_rpt).astype('float32')

        intra_cls_dists = dists * y_same
        inter_cls_dists = dists * y_diff

        max_dists = F.max(dists, axis=1, keepdims=True)
        max_dists = F.broadcast_to(max_dists, shape=(self._bs_tgt, self._bs_src))
        revised_inter_cls_dists = F.where(y_same, max_dists, inter_cls_dists)

        max_intra_cls_dist = F.max(intra_cls_dists, axis=1)
        min_inter_cls_dist = F.min(revised_inter_cls_dists, axis=1)

        loss = F.relu(max_intra_cls_dist - min_inter_cls_dist + self._margin)

        return loss 
开发者ID:aws-samples,项目名称:d-SNE,代码行数:41,代码来源:custom_layers.py

示例3: __init__

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def __init__(self, loss_type: Loss=L2Loss, weight: float=1, batch_axis: int=0) -> None:
        """
        Loss for Q-Value Head.

        :param loss_type: loss function with default of mean squared error (i.e. L2Loss).
        :param weight: scalar used to adjust relative weight of loss (if using this loss with others).
        :param batch_axis: axis used for mini-batch (default is 0) and excluded from loss aggregation.
        """
        super(QHeadLoss, self).__init__(weight=weight, batch_axis=batch_axis)
        with self.name_scope():
            self.loss_fn = loss_type(weight=weight, batch_axis=batch_axis) 
开发者ID:NervanaSystems,项目名称:coach,代码行数:13,代码来源:q_head.py

示例4: loss

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def loss(self) -> Loss:
        """
        Specifies loss block to be used for specific value head implementation.

        :return: loss block (can be called as function) for outputs returned by the head network.
        """
        return QHeadLoss(loss_type=self.loss_type, weight=self.loss_weight) 
开发者ID:NervanaSystems,项目名称:coach,代码行数:9,代码来源:q_head.py

示例5: __init__

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def __init__(self, loss_type: Loss=L2Loss, weight: float=1, batch_axis: int=0) -> None:
        """
        Loss for Value Head.

        :param loss_type: loss function with default of mean squared error (i.e. L2Loss).
        :param weight: scalar used to adjust relative weight of loss (if using this loss with others).
        :param batch_axis: axis used for mini-batch (default is 0) and excluded from loss aggregation.
        """
        super(VHeadLoss, self).__init__(weight=weight, batch_axis=batch_axis)
        with self.name_scope():
            self.loss_fn = loss_type(weight=weight, batch_axis=batch_axis) 
开发者ID:NervanaSystems,项目名称:coach,代码行数:13,代码来源:v_head.py

示例6: loss

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def loss(self) -> Loss:
        """
        Specifies loss block to be used for specific value head implementation.

        :return: loss block (can be called as function) for outputs returned by the head network.
        """
        return VHeadLoss(loss_type=self.loss_type, weight=self.loss_weight) 
开发者ID:NervanaSystems,项目名称:coach,代码行数:9,代码来源:v_head.py

示例7: hybrid_forward

# 需要导入模块: from mxnet.gluon import loss [as 别名]
# 或者: from mxnet.gluon.loss import Loss [as 别名]
def hybrid_forward(self, F, objness, box_centers, box_scales, cls_preds,
                       objness_t, center_t, scale_t, weight_t, class_t, class_mask):
        """Compute YOLOv3 losses.

        Parameters
        ----------
        objness : mxnet.nd.NDArray
            Predicted objectness (B, N), range (0, 1).
        box_centers : mxnet.nd.NDArray
            Predicted box centers (x, y) (B, N, 2), range (0, 1).
        box_scales : mxnet.nd.NDArray
            Predicted box scales (width, height) (B, N, 2).
        cls_preds : mxnet.nd.NDArray
            Predicted class predictions (B, N, num_class), range (0, 1).
        objness_t : mxnet.nd.NDArray
            Objectness target, (B, N), 0 for negative 1 for positive, -1 for ignore.
        center_t : mxnet.nd.NDArray
            Center (x, y) targets (B, N, 2).
        scale_t : mxnet.nd.NDArray
            Scale (width, height) targets (B, N, 2).
        weight_t : mxnet.nd.NDArray
            Loss Multipliers for center and scale targets (B, N, 2).
        class_t : mxnet.nd.NDArray
            Class targets (B, N, num_class).
            It's relaxed one-hot vector, i.e., (1, 0, 1, 0, 0).
            It can contain more than one positive class.
        class_mask : mxnet.nd.NDArray
            0 or 1 mask array to mask out ignored samples (B, N, num_class).

        Returns
        -------
        tuple of NDArrays
            obj_loss: sum of objectness logistic loss
            center_loss: sum of box center logistic regression loss
            scale_loss: sum of box scale l1 loss
            cls_loss: sum of per class logistic loss

        """
        # compute some normalization count, except batch-size
        denorm = F.cast(
            F.shape_array(objness_t).slice_axis(axis=0, begin=1, end=None).prod(), 'float32')
        weight_t = F.broadcast_mul(weight_t, objness_t)
        hard_objness_t = F.where(objness_t > 0, F.ones_like(objness_t), objness_t)
        new_objness_mask = F.where(objness_t > 0, objness_t, objness_t >= 0)
        obj_loss = F.broadcast_mul(
            self._sigmoid_ce(objness, hard_objness_t, new_objness_mask), denorm)
        center_loss = F.broadcast_mul(self._sigmoid_ce(box_centers, center_t, weight_t), denorm * 2)
        scale_loss = F.broadcast_mul(self._l1_loss(box_scales, scale_t, weight_t), denorm * 2)
        denorm_class = F.cast(
            F.shape_array(class_t).slice_axis(axis=0, begin=1, end=None).prod(), 'float32')
        class_mask = F.broadcast_mul(class_mask, objness_t)
        cls_loss = F.broadcast_mul(self._sigmoid_ce(cls_preds, class_t, class_mask), denorm_class)
        return obj_loss, center_loss, scale_loss, cls_loss 
开发者ID:becauseofAI,项目名称:MobileFace,代码行数:55,代码来源:loss.py


注:本文中的mxnet.gluon.loss.Loss方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。