本文整理汇总了Python中torch.nn.functional.lp_pool2d方法的典型用法代码示例。如果您正苦于以下问题：Python functional.lp_pool2d方法的具体用法？Python functional.lp_pool2d怎么用？Python functional.lp_pool2d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.lp_pool2d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: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import lp_pool2d [as 别名]
def forward(self, x):
channel_att_sum = None
for pool_type in self.pool_types:
if pool_type=='avg':
avg_pool = F.avg_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( avg_pool )
elif pool_type=='max':
max_pool = F.max_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( max_pool )
elif pool_type=='lp':
lp_pool = F.lp_pool2d( x, 2, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( lp_pool )
elif pool_type=='lse':
# LSE pool only
lse_pool = logsumexp_2d(x)
channel_att_raw = self.mlp( lse_pool )
if channel_att_sum is None:
channel_att_sum = channel_att_raw
else:
channel_att_sum = channel_att_sum + channel_att_raw
scale = torch.sigmoid( channel_att_sum ).unsqueeze(2).unsqueeze(3).expand_as(x)
return x * scale 示例2: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import lp_pool2d [as 别名]
def forward(self, x):
channel_att_sum = None
for pool_type in self.pool_types:
if pool_type=='avg':
avg_pool = F.avg_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( avg_pool )
elif pool_type=='max':
max_pool = F.max_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( max_pool )
elif pool_type=='lp':
lp_pool = F.lp_pool2d( x, 2, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( lp_pool )
elif pool_type=='lse':
# LSE pool only
lse_pool = logsumexp_2d(x)
channel_att_raw = self.mlp( lse_pool )
if channel_att_sum is None:
channel_att_sum = channel_att_raw
else:
channel_att_sum = channel_att_sum + channel_att_raw
scale = torch.sigmoid( channel_att_sum ).unsqueeze(2).unsqueeze(3)
return scale 示例3: forward
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import lp_pool2d [as 别名]
def forward(self, x):
channel_att_sum = None
for pool_type in self.pool_types:
if pool_type=='avg':
avg_pool = F.avg_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( avg_pool )
elif pool_type=='max':
max_pool = F.max_pool2d( x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( max_pool )
elif pool_type=='lp':
lp_pool = F.lp_pool2d( x, 2, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp( lp_pool )
elif pool_type=='lse':
# LSE pool only
lse_pool = logsumexp_2d(x)
channel_att_raw = self.mlp( lse_pool )
if channel_att_sum is None:
channel_att_sum = channel_att_raw
else:
channel_att_sum = channel_att_sum + channel_att_raw
scale = F.sigmoid( channel_att_sum ).unsqueeze(2).unsqueeze(3).expand_as(x)
return x * scale 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 lp_pool2d [as 别名]
def forward(self, x):
channel_att_sum = None
for pool_type in self.pool_types:
if pool_type == 'avg':
avg_pool = F.avg_pool2d(x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp(avg_pool)
elif pool_type == 'max':
max_pool = F.max_pool2d(x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp(max_pool)
elif pool_type == 'lp':
lp_pool = F.lp_pool2d(x, 2, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp(lp_pool)
elif pool_type == 'lse':
# LSE pool only
lse_pool = logsumexp_2d(x)
channel_att_raw = self.mlp(lse_pool)
if channel_att_sum is None:
channel_att_sum = channel_att_raw
else:
channel_att_sum = channel_att_sum + channel_att_raw
scale = torch.sigmoid(channel_att_sum).unsqueeze(2).unsqueeze(3).expand_as(x)
return x * scale 示例5: gem
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import lp_pool2d [as 别名]
def gem(x, p=3, eps=1e-6):
return F.avg_pool2d(x.clamp(min=eps).pow(p), (x.size(-2), x.size(-1))).pow(1./p)
# return F.lp_pool2d(F.threshold(x, eps, eps), p, (x.size(-2), x.size(-1))) # alternative 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 lp_pool2d [as 别名]
def forward(self, x):
channel_att_sum = None
for pool_type in self.pool_types:
if pool_type == 'avg':
avg_pool = F.avg_pool2d(
x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp(avg_pool)
elif pool_type == 'max':
max_pool = F.max_pool2d(
x, (x.size(2), x.size(3)), stride=(x.size(2), x.size(3)))
channel_att_raw = self.mlp(max_pool)
elif pool_type == 'lp':
lp_pool = F.lp_pool2d(
x, 2, (x.size(2), x.size(3)), stride=(
x.size(2), x.size(3)))
channel_att_raw = self.mlp(lp_pool)
elif pool_type == 'lse':
# LSE pool only
lse_pool = logsumexp_2d(x)
channel_att_raw = self.mlp(lse_pool)
if channel_att_sum is None:
channel_att_sum = channel_att_raw
else:
channel_att_sum = channel_att_sum + channel_att_raw
scale = torch.sigmoid(channel_att_sum).unsqueeze(
2).unsqueeze(3).expand_as(x)
return x * scale 示例7: test_lp_pool2d
# 需要导入模块: from torch.nn import functional [as 别名]
# 或者: from torch.nn.functional import lp_pool2d [as 别名]
def test_lp_pool2d(self):
#torch.nn.LPPool2d(norm_type, kernel_size, stride=None, ceil_mode=False)
inp = torch.randn(1, 32, 64, 64, device='cuda', dtype=self.dtype)
output = F.lp_pool2d(inp, 2, 3, stride=2, ceil_mode=True)