本文整理汇总了Python中mxnet.nd.square方法的典型用法代码示例。如果您正苦于以下问题:Python nd.square方法的具体用法?Python nd.square怎么用?Python nd.square使用的例子?那么恭喜您, 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类mxnet.nd
的用法示例。
在下文中一共展示了nd.square方法的9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: CapLoss
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def CapLoss(y_pred, y_true):
L = y_true * nd.square(nd.maximum(0., 0.9 - y_pred)) + \
0.5 * (1 - y_true) * nd.square(nd.maximum(0., y_pred - 0.1))
return nd.mean(nd.sum(L, 1))
示例2: squash
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def squash(x, axis):
s_squared_norm = nd.sum(nd.square(x), axis, keepdims=True)
# if s_squared_norm is really small, we will be in trouble
# so I removed the s_quare terms
# scale = s_squared_norm / ((1 + s_squared_norm) * nd.sqrt(s_squared_norm + 1e-9))
# return x * scale
scale = nd.sqrt(s_squared_norm + 1e-9)
return x / scale
示例3: Route
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def Route(self, x):
# print x.context
b_mat = nd.zeros((x.shape[0],1,self.num_cap, self.num_locations), ctx=x.context)
x_expand = nd.expand_dims(nd.expand_dims(x, axis=2),2)
w_expand = nd.repeat(nd.expand_dims(self.w_ij.data(x.context),axis=0), repeats=x.shape[0], axis=0)
u_ = w_expand*x_expand
u = nd.sum(u_, axis = 1)
# u_ = nd.square(w_expand - x_expand)
# u = -nd.sum(u_, axis = 1)
u_no_gradient = nd.stop_gradient(u)
for i in range(self.route_num):
# c_mat = nd.softmax(b_mat, axis=2)
c_mat = nd.sigmoid(b_mat)
if i == self.route_num -1:
s = nd.sum(u * c_mat, axis=-1)
else:
s = nd.sum(u_no_gradient * c_mat, axis=-1)
v = squash(s, 1)
if i != self.route_num - 1:
v1 = nd.expand_dims(v, axis=-1)
update_term = nd.sum(u_no_gradient*v1, axis=1, keepdims=True)
b_mat = b_mat + update_term
# b_mat = update_term
# else:
# v = s
return v
示例4: forward
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def forward(self, x):
x = nd.sqrt(nd.sum(nd.square(x), 1))
return x
示例5: forward
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def forward(self, cls_pred, box_pred, cls_target, box_target):
"""Compute loss in entire batch across devices."""
# require results across different devices at this time
cls_pred, box_pred, cls_target, box_target = [_as_list(x) \
for x in (cls_pred, box_pred, cls_target, box_target)]
# cross device reduction to obtain positive samples in entire batch
num_pos = []
for cp, bp, ct, bt in zip(*[cls_pred, box_pred, cls_target, box_target]):
pos_samples = (ct > 0)
num_pos.append(pos_samples.sum())
num_pos_all = sum([p.asscalar() for p in num_pos])
if num_pos_all < 1:
# no positive samples found, return dummy losses
return nd.zeros((1,)), nd.zeros((1,)), nd.zeros((1,))
# compute element-wise cross entropy loss and sort, then perform negative mining
cls_losses = []
box_losses = []
sum_losses = []
for cp, bp, ct, bt in zip(*[cls_pred, box_pred, cls_target, box_target]):
pred = nd.log_softmax(cp, axis=-1)
pos = ct > 0
cls_loss = -nd.pick(pred, ct, axis=-1, keepdims=False)
rank = (cls_loss * (pos - 1)).argsort(axis=1).argsort(axis=1)
hard_negative = rank < (pos.sum(axis=1) * self._negative_mining_ratio).expand_dims(-1)
# mask out if not positive or negative
cls_loss = nd.where((pos + hard_negative) > 0, cls_loss, nd.zeros_like(cls_loss))
cls_losses.append(nd.sum(cls_loss, axis=0, exclude=True) / num_pos_all)
bp = _reshape_like(nd, bp, bt)
box_loss = nd.abs(bp - bt)
box_loss = nd.where(box_loss > self._rho, box_loss - 0.5 * self._rho,
(0.5 / self._rho) * nd.square(box_loss))
# box loss only apply to positive samples
box_loss = box_loss * pos.expand_dims(axis=-1)
box_losses.append(nd.sum(box_loss, axis=0, exclude=True) / num_pos_all)
sum_losses.append(cls_losses[-1] + self._lambd * box_losses[-1])
return sum_losses, cls_losses, box_losses
示例6: loss
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def loss(y_pred,y_true):
L = y_true * nd.square(nd.maximum(0., 0.9 - y_pred)) + \
0.5 * (1 - y_true) * nd.square(nd.maximum(0., y_pred - 0.1))
return nd.mean(nd.sum(L, 1))
示例7: squash
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def squash(self,vectors,axis):
epsilon = 1e-9
vectors_l2norm = nd.square(vectors).sum(axis=axis,keepdims=True)#.expand_dims(axis=axis)
scale_factor = vectors_l2norm / (1 + vectors_l2norm)
vectors_squashed = scale_factor * (vectors / nd.sqrt(vectors_l2norm+epsilon)) # element-wise
return vectors_squashed
示例8: forward
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def forward(self, x):
#(batch_size, 1, 10, 16, 1) =>(batch_size,10, 16)=> (batch_size, 10, 1)
x_shape = x.shape
x = x.reshape(shape=(x_shape[0],x_shape[2],x_shape[3]))
x_l2norm = nd.sqrt((x.square()).sum(axis=-1))
# prob = nd.softmax(x_l2norm, axis=-1)
return x_l2norm
示例9: forward
# 需要导入模块: from mxnet import nd [as 别名]
# 或者: from mxnet.nd import square [as 别名]
def forward(self, cls_pred, box_pred, cls_target, box_target):
"""Compute loss in entire batch across devices."""
# require results across different devices at this time
cls_pred, box_pred, cls_target, box_target = [_as_list(x) \
for x in (cls_pred, box_pred, cls_target, box_target)]
# cross device reduction to obtain positive samples in entire batch
num_pos = []
for cp, bp, ct, bt in zip(*[cls_pred, box_pred, cls_target, box_target]):
pos_samples = (ct > 0)
num_pos.append(pos_samples.sum())
num_pos_all = sum([p.asscalar() for p in num_pos])
if num_pos_all < 1 and self._min_hard_negatives < 1:
# no positive samples and no hard negatives, return dummy losses
cls_losses = [nd.sum(cp * 0) for cp in cls_pred]
box_losses = [nd.sum(bp * 0) for bp in box_pred]
sum_losses = [nd.sum(cp * 0) + nd.sum(bp * 0) for cp, bp in zip(cls_pred, box_pred)]
return sum_losses, cls_losses, box_losses
# compute element-wise cross entropy loss and sort, then perform negative mining
cls_losses = []
box_losses = []
sum_losses = []
for cp, bp, ct, bt in zip(*[cls_pred, box_pred, cls_target, box_target]):
pred = nd.log_softmax(cp, axis=-1)
pos = ct > 0
cls_loss = -nd.pick(pred, ct, axis=-1, keepdims=False)
rank = (cls_loss * (pos - 1)).argsort(axis=1).argsort(axis=1)
hard_negative = rank < nd.maximum(self._min_hard_negatives, pos.sum(axis=1)
* self._negative_mining_ratio).expand_dims(-1)
# mask out if not positive or negative
cls_loss = nd.where((pos + hard_negative) > 0, cls_loss, nd.zeros_like(cls_loss))
cls_losses.append(nd.sum(cls_loss, axis=0, exclude=True) / max(1., num_pos_all))
bp = _reshape_like(nd, bp, bt)
box_loss = nd.abs(bp - bt)
box_loss = nd.where(box_loss > self._rho, box_loss - 0.5 * self._rho,
(0.5 / self._rho) * nd.square(box_loss))
# box loss only apply to positive samples
box_loss = box_loss * pos.expand_dims(axis=-1)
box_losses.append(nd.sum(box_loss, axis=0, exclude=True) / max(1., num_pos_all))
sum_losses.append(cls_losses[-1] + self._lambd * box_losses[-1])
return sum_losses, cls_losses, box_losses