本文整理汇总了Python中torch.nn.functional.relu6方法的典型用法代码示例。如果您正苦于以下问题:Python functional.relu6方法的具体用法?Python functional.relu6怎么用?Python functional.relu6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类torch.nn.functional
的用法示例。
在下文中一共展示了functional.relu6方法的15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: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, source_features):
outputs = []
if self.weight_type == 'const':
for w in F.softplus(self.weights.mul(10)):
outputs.append(w.view(1, 1))
else:
for i, (idx, _) in enumerate(self.pairs):
f = source_features[idx]
f = F.avg_pool2d(f, f.size(2)).view(-1, f.size(1))
if self.weight_type == 'relu':
outputs.append(F.relu(self[i](f)))
elif self.weight_type == 'relu-avg':
outputs.append(F.relu(self[i](f.div(f.size(1)))))
elif self.weight_type == 'relu6':
outputs.append(F.relu6(self[i](f)))
return outputs
示例2: get_activation
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def get_activation(name):
if isinstance(name, nn.Module):
return name
if name == 'default':
return get_activation(get_default_activation())
elif name == 'relu':
return nn.ReLU(inplace=True)
elif name == 'relu6':
return nn.ReLU6(inplace=True)
elif name == 'leaky_relu':
return nn.LeakyReLU(negative_slope=0.1, inplace=True)
elif name == 'sigmoid':
return nn.Sigmoid()
elif name == 'hswish':
return HardSwish(inplace=True)
elif name == 'swish':
return Swish()
else:
raise NotImplementedError("No activation named %s" % name)
示例3: activation
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def activation(input, kind):
#print("Activation: {}".format(kind))
if kind == 'selu':
return F.selu(input)
elif kind == 'relu':
return F.relu(input)
elif kind == 'relu6':
return F.relu6(input)
elif kind == 'sigmoid':
return F.sigmoid(input)
elif kind == 'tanh':
return F.tanh(input)
elif kind == 'elu':
return F.elu(input)
elif kind == 'lrelu':
return F.leaky_relu(input)
elif kind == 'swish':
return input*F.sigmoid(input)
elif kind == 'none':
return input
else:
raise ValueError('Unknown non-linearity type')
示例4: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
out = self.conv1(x)
out = self.bn1(out)
out = F.relu6(out)
out = self.conv2(out)
out = self.bn2(out)
out = F.relu6(out)
out = self.conv3(out)
out = self.bn3(out)
if self.inp == self.oup and self.stride == 1:
return (out + x)
else:
return out
示例5: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x, inp_scale_id):
inp_scale = overall_channel_scale[inp_scale_id]
inp = int(self.base_inp * inp_scale)
scale_tensor = torch.FloatTensor([inp_scale/self.max_overall_scale]).to(x.device)
fc11_out = F.relu(self.fc11(scale_tensor))
conv1_weight = self.fc12(fc11_out).view(self.base_oup, self.max_inp_channel, 1, 1)
out = F.conv2d(x, conv1_weight[:, :inp, :, :], bias=None, stride=self.stride, padding=0)
out = self.first_bn[inp_scale_id](out)
out = F.relu6(out)
return out
示例6: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
return x * F.relu6(x + 3., inplace=self.inplace) / 6.
示例7: __init__
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def __init__(self, act_type, auto_optimize=True, **kwargs):
super(Activation, self).__init__()
if act_type == 'relu':
self.act = nn.ReLU(
inplace=True) if auto_optimize else nn.ReLU(**kwargs)
elif act_type == 'relu6':
self.act = nn.ReLU6(
inplace=True) if auto_optimize else nn.ReLU6(**kwargs)
elif act_type == 'h_swish':
self.act = HardSwish(
inplace=True) if auto_optimize else HardSwish(**kwargs)
elif act_type == 'h_sigmoid':
self.act = HardSigmoid(
inplace=True) if auto_optimize else HardSigmoid(**kwargs)
elif act_type == 'swish':
self.act = Swish(**kwargs)
elif act_type == 'sigmoid':
self.act = nn.Sigmoid()
elif act_type == 'lrelu':
self.act = nn.LeakyReLU(inplace=True, **kwargs) if auto_optimize \
else nn.LeakyReLU(**kwargs)
elif act_type == 'prelu':
self.act = nn.PReLU(**kwargs)
else:
raise NotImplementedError(
'{} activation is not implemented.'.format(act_type))
示例8: hard_sigmoid
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def hard_sigmoid(x, inplace=False):
return F.relu6(x + 3, inplace) / 6
示例9: hard_sigmoid
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def hard_sigmoid(x, inplace: bool = False):
if inplace:
return x.add_(3.).clamp_(0., 6.).div_(6.)
else:
return F.relu6(x + 3.) / 6.
示例10: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
out = x * F.relu6(x + 3, inplace=True) / 6
return out
示例11: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
out = F.relu6(x + 3, inplace=True) / 6
return out
示例12: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
return F.relu6(self.conv(x))
示例13: hard_swish
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def hard_swish(x, inplace: bool = False):
inner = F.relu6(x + 3.).div_(6.)
return x.mul_(inner) if inplace else x.mul(inner)
示例14: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
return MishJitAutoFn.apply(x)
# @torch.jit.script
# def hard_swish_jit(x, inplac: bool = False):
# return x.mul(F.relu6(x + 3.).mul_(1./6.))
#
#
# class HardSwishJit(nn.Module):
# def __init__(self, inplace: bool = False):
# super(HardSwishJit, self).__init__()
#
# def forward(self, x):
# return hard_swish_jit(x)
#
#
# @torch.jit.script
# def hard_sigmoid_jit(x, inplace: bool = False):
# return F.relu6(x + 3.).mul(1./6.)
#
#
# class HardSigmoidJit(nn.Module):
# def __init__(self, inplace: bool = False):
# super(HardSigmoidJit, self).__init__()
#
# def forward(self, x):
# return hard_sigmoid_jit(x)
示例15: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import relu6 [as 别名]
def forward(self, x):
return F.relu6(x + 3.0, inplace=True) / 6.0