Python torch.nn.functional.adaptive_avg_pool1d() Examples

The following are 9 code examples of torch.nn.functional.adaptive_avg_pool1d(). 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: frontend.py    From pase with MIT License 6 votes vote down vote up 
def fuse_skip(self, input_, skip):
        #print('input_ shape: ', input_.shape)
        #print('skip shape: ', skip.shape)
        dfactor = skip.shape[2] // input_.shape[2]
        if dfactor > 1:
            #print('dfactor: ', dfactor)
            # downsample skips
            # [B, F, T]
            maxlen = input_.shape[2] * dfactor
            skip = skip[:, :, :maxlen]
            bsz, feats, slen = skip.shape
            skip_re = skip.view(bsz, feats, slen // dfactor, dfactor)
            skip = torch.mean(skip_re, dim=3)
            #skip = F.adaptive_avg_pool1d(skip, input_.shape[2])
        if self.densemerge == 'concat':
            return torch.cat((input_, skip), dim=1)
        elif self.densemerge == 'sum':
            return input_ + skip
        else:
            raise TypeError('Unknown densemerge: ', self.densemerge)
Example #2
Source File: spectral.py    From torchsupport with MIT License 6 votes vote down vote up 
def forward(self, graph):
    nodes = graph.node_tensor

    out = self.preprocess(nodes)
    out = out.reshape(out.size(0), out.size(1) * out.size(2), 1)
    out += self.merge(nodes).reshape(out.size(0), out.size(1) * out.size(2), 1)
    out = self.activation(out)
    for _ in range(self.depth - 1):
      out -= graph.laplacian_action(out)
      out = self.propagate(out)
      out += self.merge(nodes).reshape(out.size(0), out.size(1) * out.size(2), 1)
      out = self.activation(out)

    out = out.reshape(nodes.size(0), nodes.size(1), self.width)
    out = func.adaptive_avg_pool1d(out, 1).reshape(
      nodes.size(0), -1
    ).unsqueeze(2)
    result = graph.new_like()
    result.node_tensor = out
    return result
Example #3
Source File: frontend.py    From pase with MIT License 5 votes vote down vote up 
def fuse(self, out):
        last_feature = out[-1]
        for i in range(len(out) - 1):
            out[i] = F.adaptive_avg_pool1d(out[i], last_feature.shape[-1])
        return out
Example #4
Source File: spectral.py    From torchsupport with MIT License 5 votes vote down vote up 
def forward(self, data, structure):
    out = self.preprocess(data, data, structure)
    for block in self.blocks:
      out = block(out, data, structure)
    out = self.postprocess(out, data, structure)
    out = out.reshape(data.size(0), -1, self.width)
    return func.adaptive_avg_pool1d(out, 1)
Example #5
Source File: layers.py    From TorchFusion with MIT License 5 votes vote down vote up 
def pool(self, input):

        return F.adaptive_avg_pool1d(input,1)
Example #6
Source File: conv.py    From seq2seq.pytorch with MIT License 5 votes vote down vote up 
def forward(self, inputs, state):
        x = self.embedder(inputs)
        x = x.transpose(1, 2)
        state = F.adaptive_avg_pool1d(state, x.size(2))
        x = torch.cat([x, state], 1)
        x = self.convs(x)
        x = x.transpose(1, 2)  # BxTxN
        x = x.contiguous().view(-1, x.size(2))
        x = self.classifier(x)
        x = x.view(inputs.size(0), inputs.size(1), -1)  # BxTxN
        return x
Example #7
Source File: test_pyprof_nvtx.py    From apex with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def test_adaptive_avg_pool1d(self):
        inp = torch.randn(1, 1, 28, device='cuda', dtype=self.dtype)
        out = F.adaptive_avg_pool1d(inp, output_size=5)
Example #8
Source File: bpv.py    From ecom-rakuten with MIT License 5 votes vote down vote up 
def pool(self, x, bs, is_max):
        f = F.adaptive_max_pool1d if is_max else F.adaptive_avg_pool1d
        return f(x.permute(1, 2, 0), (1,)).view(bs, -1)
Example #9
Source File: feature_model.py    From starsem2018-entity-linking with Apache License 2.0 4 votes vote down vote up 
def forward(self, e_x, e_sig, x, x_sig):
        e_x = e_x.long()
        x = x.float()
        x_sig = x_sig.float()
        e_sig = e_sig.float()
        choices = x.size(1)

        e_x = self._pos_embeddings(e_x)
        e_x = e_x.transpose(1, 2)
        e_x = F.adaptive_avg_pool1d(e_x, 1).view(*e_x.size()[:2])
        e_x = e_x.unsqueeze(1)
        e_x = e_x.expand(e_x.size(0), choices, e_x.size(2)).contiguous()
        e_sig = e_sig.unsqueeze(1)
        e_sig = e_sig.expand(e_sig.size(0), choices, e_sig.size(2)).contiguous()

        x = torch.cat((
            x,
            x_sig,
            e_x,
            e_sig), dim=-1)
        x = x.view(-1, x.size(-1))

        i = self.individual_weights(x)
        i = F.relu(i)
        i = self.hidden_weights(i)
        i = F.relu(i)
        i = i.view(-1, choices, i.size(-1))

        s = i.transpose(1, 2)
        s = F.adaptive_max_pool1d(s, 1)
        s = s.transpose(1, 2)

        v = s.expand_as(i)
        v = torch.cat((i, v), dim=-1)
        v = v.view(-1, v.size(-1))

        v = self._dropout(v)
        x = self.score_weights(v)
        x = x.view(-1, choices)
        # x = F.relu(x)

        z = s.view(-1,  s.size(-1))

        z = self._dropout(z)
        z = self.negative_weights(z)

        # x = torch.cat((z, x), dim=-1)

        return F.sigmoid(z.squeeze(dim=-1)), F.softmax(x, dim=-1)