Python torch.nn.functional.lp_pool2d() Examples

The following are 9 code examples of torch.nn.functional.lp_pool2d(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module torch.nn.functional , or try the search function .
Example #1
Source File: cbam.py    From OISR-PyTorch with BSD 2-Clause "Simplified" License 6 votes vote down vote up 
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
Example #2
Source File: net_utils.py    From One-Shot-Object-Detection with MIT License 6 votes vote down vote up 
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
Example #3
Source File: cbam.py    From PMFNet with MIT License 6 votes vote down vote up 
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
Example #4
Source File: cbam.py    From attention-module with MIT License 6 votes vote down vote up 
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
Example #5
Source File: cbam.py    From ss-ood with MIT License 6 votes vote down vote up 
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
Example #6
Source File: functional.py    From cnnimageretrieval-pytorch with MIT License 5 votes vote down vote up 
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
Example #7
Source File: functional.py    From Landmark2019-1st-and-3rd-Place-Solution with Apache License 2.0 5 votes vote down vote up 
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
Example #8
Source File: cbam_resnext.py    From CIFAR-ZOO with MIT License 5 votes vote down vote up 
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
Example #9
Source File: test_pyprof_nvtx.py    From apex with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
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)