Python torch.nn.functional.avg_pool2d() Examples
The following are 30
code examples of torch.nn.functional.avg_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
.
![](https://www.programcreek.com/common/static/images/search.png)
Example #1
Source File: inception.py From fast-MPN-COV with MIT License | 6 votes |
def forward(self, x): branch1x1 = self.branch1x1(x) branch3x3 = self.branch3x3_1(x) branch3x3 = [ self.branch3x3_2a(branch3x3), self.branch3x3_2b(branch3x3), ] branch3x3 = torch.cat(branch3x3, 1) branch3x3dbl = self.branch3x3dbl_1(x) branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl) branch3x3dbl = [ self.branch3x3dbl_3a(branch3x3dbl), self.branch3x3dbl_3b(branch3x3dbl), ] branch3x3dbl = torch.cat(branch3x3dbl, 1) branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool] return torch.cat(outputs, 1)
Example #2
Source File: vision_encoders.py From Character-Level-Language-Modeling-with-Deeper-Self-Attention-pytorch with MIT License | 6 votes |
def forward(self, x): with torch.set_grad_enabled(self.finetune): x = self.model.conv1(x) x = self.model.bn1(x) x = self.model.relu(x) x = self.model.maxpool(x) x = self.model.layer1(x) x = self.model.layer2(x) x = self.model.layer3(x) x = self.model.layer4(x) if not self.spatial_context: x = F.avg_pool2d(x, kernel_size=7).view(x.size(0), x.size(1)) if hasattr(self, 'context_transform'): x = self.context_transform(x) if hasattr(self, 'context_nonlinearity'): x = self.context_nonlinearity(x) return x
Example #3
Source File: models.py From AdaptiveWingLoss with Apache License 2.0 | 6 votes |
def _forward(self, level, inp): # Upper branch up1 = inp up1 = self._modules['b1_' + str(level)](up1) # Lower branch low1 = F.avg_pool2d(inp, 2, stride=2) low1 = self._modules['b2_' + str(level)](low1) if level > 1: low2 = self._forward(level - 1, low1) else: low2 = low1 low2 = self._modules['b2_plus_' + str(level)](low2) low3 = low2 low3 = self._modules['b3_' + str(level)](low3) up2 = F.upsample(low3, scale_factor=2, mode='nearest') return up1 + up2
Example #4
Source File: WideResNet.py From overhaul-distillation with MIT License | 6 votes |
def extract_feature(self, x, preReLU=False): out = self.conv1(x) feat1 = self.block1(out) feat2 = self.block2(feat1) feat3 = self.block3(feat2) out = self.relu(self.bn1(feat3)) out = F.avg_pool2d(out, 8) out = out.view(-1, self.nChannels[3]) out = self.fc(out) if preReLU: feat1 = self.block2.layer[0].bn1(feat1) feat2 = self.block3.layer[0].bn1(feat2) feat3 = self.bn1(feat3) return [feat1, feat2, feat3], out
Example #5
Source File: pytorch_ops.py From deep_architect with MIT License | 6 votes |
def avg_pool2d(h_kernel_size, h_stride=1): def compile_fn(di, dh): (_, _, height, width) = di['in'].size() padding = nn.ZeroPad2d( calculate_same_padding(height, width, dh['stride'], dh['kernel_size'])) avg_pool = nn.AvgPool2d(dh['kernel_size'], stride=dh['stride']) def fn(di): x = padding(di['in']) return {'out': avg_pool(x)} return fn, [padding, avg_pool] return siso_pytorch_module('AvgPool2D', compile_fn, { 'kernel_size': h_kernel_size, 'stride': h_stride })
Example #6
Source File: fpn.py From seamseg with BSD 3-Clause "New" or "Revised" License | 6 votes |
def forward(self, x): """ROI head module for FPN Parameters ---------- x : torch.Tensor A tensor of input features with shape N x C x H x W Returns ------- cls_logits : torch.Tensor A tensor of classification logits with shape S x (num_thing + 1) bbx_logits : torch.Tensor A tensor of class-specific bounding box regression logits with shape S x num_thing x 4 """ x = functional.avg_pool2d(x, 2) # Run head x = self.fc(x.view(x.size(0), -1)) return self.roi_cls(x), self.roi_bbx(x).view(x.size(0), -1, 4)
Example #7
Source File: inception.py From fast-MPN-COV with MIT License | 6 votes |
def forward(self, x): branch1x1 = self.branch1x1(x) branch7x7 = self.branch7x7_1(x) branch7x7 = self.branch7x7_2(branch7x7) branch7x7 = self.branch7x7_3(branch7x7) branch7x7dbl = self.branch7x7dbl_1(x) branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl) branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl) branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl) branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl) branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool] return torch.cat(outputs, 1)
Example #8
Source File: models.py From VTuber_Unity with MIT License | 6 votes |
def _forward(self, level, inp): # Upper branch up1 = inp up1 = self._modules['b1_' + str(level)](up1) # Lower branch low1 = F.avg_pool2d(inp, 2, stride=2) low1 = self._modules['b2_' + str(level)](low1) if level > 1: low2 = self._forward(level - 1, low1) else: low2 = low1 low2 = self._modules['b2_plus_' + str(level)](low2) low3 = low2 low3 = self._modules['b3_' + str(level)](low3) up2 = F.interpolate(low3, scale_factor=2, mode='nearest') return up1 + up2
Example #9
Source File: models.py From AdaptiveWingLoss with Apache License 2.0 | 5 votes |
def forward(self, x): x, _ = self.conv1(x) x = F.relu(self.bn1(x), True) # x = F.relu(self.bn1(self.conv1(x)), True) x = F.avg_pool2d(self.conv2(x), 2, stride=2) x = self.conv3(x) x = self.conv4(x) previous = x outputs = [] boundary_channels = [] tmp_out = None for i in range(self.num_modules): hg, boundary_channel = self._modules['m' + str(i)](previous, tmp_out) ll = hg ll = self._modules['top_m_' + str(i)](ll) ll = F.relu(self._modules['bn_end' + str(i)] (self._modules['conv_last' + str(i)](ll)), True) # Predict heatmaps tmp_out = self._modules['l' + str(i)](ll) if self.end_relu: tmp_out = F.relu(tmp_out) # HACK: Added relu outputs.append(tmp_out) boundary_channels.append(boundary_channel) if i < self.num_modules - 1: ll = self._modules['bl' + str(i)](ll) tmp_out_ = self._modules['al' + str(i)](tmp_out) previous = previous + ll + tmp_out_ return outputs, boundary_channels
Example #10
Source File: downsampler.py From BMSG-GAN with MIT License | 5 votes |
def main(args): """ Main function for the script :param args: parsed command line arguments :return: None """ img_file = os.path.join(args.image_path) if args.npz_file: img = np.load(img_file) else: img = np.array(Image.open(img_file)) img = np.expand_dims(img, axis=0).transpose(0, 3, 1, 2) img = th.from_numpy(img).float() # make a tensor out of image # progressively downsample the image and save it at the given location dim = img.shape[-1] # gives the highest dimension ds_img = img # start from the highest resolution image images = [ds_img] # original image already in while dim > 4: ds_img = avg_pool2d(ds_img, kernel_size=2, stride=2) images.append(ds_img) dim //= 2 images = progressive_upscaling(list(reversed(images))) # save the images: for count in range(len(images)): imsave(os.path.join(args.out_dir, str(count + 1) + ".png"), images[count].squeeze(0).permute(1, 2, 0))
Example #11
Source File: models.py From VTuber_Unity with MIT License | 5 votes |
def forward(self, x): x = F.relu(self.bn1(self.conv1(x)), True) x = F.avg_pool2d(self.conv2(x), 2, stride=2) x = self.conv3(x) x = self.conv4(x) previous = x outputs = [] for i in range(self.num_modules): hg = self._modules['m' + str(i)](previous) ll = hg ll = self._modules['top_m_' + str(i)](ll) ll = F.relu(self._modules['bn_end' + str(i)] (self._modules['conv_last' + str(i)](ll)), True) # Predict heatmaps tmp_out = self._modules['l' + str(i)](ll) outputs.append(tmp_out) if i < self.num_modules - 1: ll = self._modules['bl' + str(i)](ll) tmp_out_ = self._modules['al' + str(i)](tmp_out) previous += ll + tmp_out_ return outputs
Example #12
Source File: densenet.py From pneumothorax-segmentation with MIT License | 5 votes |
def forward(self, x): features = self.features(x) out = F.relu(features, inplace=True) out = F.avg_pool2d(out, kernel_size=7, stride=1).view(features.size(0), -1) out = self.classifier(out) return out
Example #13
Source File: fpn.py From seamseg with BSD 3-Clause "New" or "Revised" License | 5 votes |
def _global_pooling(self, x): pooling_size = (min(try_index(self.pooling_size, 0), x.shape[2]), min(try_index(self.pooling_size, 1), x.shape[3])) padding = ( (pooling_size[1] - 1) // 2, (pooling_size[1] - 1) // 2 if pooling_size[1] % 2 == 1 else (pooling_size[1] - 1) // 2 + 1, (pooling_size[0] - 1) // 2, (pooling_size[0] - 1) // 2 if pooling_size[0] % 2 == 1 else (pooling_size[0] - 1) // 2 + 1 ) pool = functional.avg_pool2d(x, pooling_size, stride=1) pool = functional.pad(pool, pad=padding, mode="replicate") return pool
Example #14
Source File: fpn.py From seamseg with BSD 3-Clause "New" or "Revised" License | 5 votes |
def forward(self, x, do_cls_bbx=True, do_msk=True): """ROI head module for FPN Parameters ---------- x : torch.Tensor A tensor of input features with shape N x C x H x W do_cls_bbx : bool Whether to compute or not the class and bounding box regression predictions do_msk : bool Whether to compute or not the mask predictions Returns ------- cls_logits : torch.Tensor A tensor of classification logits with shape S x (num_thing + 1) bbx_logits : torch.Tensor A tensor of class-specific bounding box regression logits with shape S x num_thing x 4 msk_logits : torch.Tensor A tensor of class-specific mask logits with shape S x num_thing x (H_roi * 2) x (W_roi * 2) """ # Run fully-connected head if do_cls_bbx: x_fc = functional.avg_pool2d(x, 2) x_fc = self.fc(x_fc.view(x_fc.size(0), -1)) cls_logits = self.roi_cls(x_fc) bbx_logits = self.roi_bbx(x_fc).view(x_fc.size(0), -1, 4) else: cls_logits = None bbx_logits = None # Run convolutional head if do_msk: x = self.conv(x) msk_logits = self.roi_msk(x) else: msk_logits = None return cls_logits, bbx_logits, msk_logits
Example #15
Source File: pytorch_ops.py From deep_architect with MIT License | 5 votes |
def global_pool2d(): def compile_fn(di, dh): (_, _, height, width) = di['in'].size() def fn(di): x = F.avg_pool2d(di['in'], (height, width)) x = torch.squeeze(x, 2) return {'out': torch.squeeze(x, 2)} return fn, [] return siso_pytorch_module('GlobalAveragePool', compile_fn, {})
Example #16
Source File: HRFPN.py From Parsing-R-CNN with MIT License | 5 votes |
def __init__(self, dim_in, spatial_scale): super().__init__() self.dim_in = sum(dim_in) self.spatial_scale = spatial_scale hrfpn_dim = cfg.FPN.HRFPN.DIM # 256 use_lite = cfg.FPN.HRFPN.USE_LITE use_bn = cfg.FPN.HRFPN.USE_BN use_gn = cfg.FPN.HRFPN.USE_GN if cfg.FPN.HRFPN.POOLING_TYPE == 'AVG': self.pooling = F.avg_pool2d else: self.pooling = F.max_pool2d self.num_extra_pooling = cfg.FPN.HRFPN.NUM_EXTRA_POOLING # 1 self.num_output = len(dim_in) + self.num_extra_pooling # 5 self.reduction_conv = make_conv(self.dim_in, hrfpn_dim, kernel=1, use_bn=use_bn, use_gn=use_gn) self.dim_in = hrfpn_dim self.fpn_conv = nn.ModuleList() for i in range(self.num_output): self.fpn_conv.append( make_conv(self.dim_in, hrfpn_dim, kernel=3, use_dwconv=use_lite, use_bn=use_bn, use_gn=use_gn, suffix_1x1=use_lite) ) self.dim_in = hrfpn_dim if self.num_extra_pooling: self.spatial_scale.append(self.spatial_scale[-1] * 0.5) self.dim_out = [self.dim_in for _ in range(self.num_output)] self._init_weights()
Example #17
Source File: dpn.py From pneumothorax-segmentation with MIT License | 5 votes |
def logits(self, features): if not self.training and self.test_time_pool: x = F.avg_pool2d(features, kernel_size=7, stride=1) out = self.classifier(x) # The extra test time pool should be pooling an img_size//32 - 6 size patch out = adaptive_avgmax_pool2d(out, pool_type='avgmax') else: x = adaptive_avgmax_pool2d(features, pool_type='avg') out = self.classifier(x) return out.view(out.size(0), -1)
Example #18
Source File: wide_resnet.py From dfw with MIT License | 5 votes |
def forward(self, x): out = self.conv1(x) out = self.block1(out) out = self.block2(out) out = self.block3(out) out = self.relu(self.bn1(out)) out = F.avg_pool2d(out, 8) out = out.view(-1, self.nChannels) return self.fc(out)
Example #19
Source File: densenet.py From dfw with MIT License | 5 votes |
def forward(self, x): out = self.conv1(x) out = self.trans1(self.block1(out)) out = self.trans2(self.block2(out)) out = self.block3(out) out = self.relu(self.bn1(out)) out = F.avg_pool2d(out, 8) out = out.view(-1, self.in_planes) return self.fc(out)
Example #20
Source File: densenet.py From dfw with MIT License | 5 votes |
def forward(self, x): out = self.conv1(self.relu(self.bn1(x))) if self.droprate > 0: out = F.dropout(out, p=self.droprate, inplace=False, training=self.training) return F.avg_pool2d(out, 2)
Example #21
Source File: rnn_aux_skip_attention.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): if self.scale_factor >= 2: x = F.avg_pool2d(x, self.scale_factor) x = self.conv(x) x = self.bn(x) x = self.relu(x) return x
Example #22
Source File: train_l2t_ww.py From L2T-ww with MIT License | 5 votes |
def forward(self, source_features): outputs = [] for i, (idx, _) in enumerate(self.pairs): f = source_features[idx] f = F.avg_pool2d(f, f.size(2)).view(-1, f.size(1)) outputs.append(F.softmax(self[i](f), 1)) return outputs
Example #23
Source File: WideResNet.py From overhaul-distillation with MIT License | 5 votes |
def forward(self, x): out = self.conv1(x) out = self.block1(out) out = self.block2(out) out = self.block3(out) out = self.relu(self.bn1(out)) out = F.avg_pool2d(out, 8) out = out.view(-1, self.nChannels[3]) return self.fc(out)
Example #24
Source File: simple_kaggle.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = F.avg_pool2d(x, 2) return x
Example #25
Source File: simple_attention.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = F.avg_pool2d(x, 2) return x
Example #26
Source File: skip_attention.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = F.avg_pool2d(x, 2) return x
Example #27
Source File: wideresnet.py From JEM with Apache License 2.0 | 5 votes |
def forward(self, x, vx=None): out = self.conv1(x) out = self.layer1(out) out = self.layer2(out) out = self.layer3(out) out = self.lrelu(self.bn1(out)) if self.sum_pool: out = out.view(out.size(0), out.size(1), -1).sum(2) else: out = F.avg_pool2d(out, 8) out = out.view(out.size(0), -1) return out
Example #28
Source File: aux_skip_attention.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): if self.scale_factor >= 2: x = F.avg_pool2d(x, self.scale_factor) x = self.conv(x) x = self.bn(x) x = self.relu(x) return x
Example #29
Source File: rnn_aux_skip_attention.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = F.avg_pool2d(x, 2) return x
Example #30
Source File: aux_skip_attention.py From argus-freesound with MIT License | 5 votes |
def forward(self, x): x = self.conv1(x) x = self.conv2(x) x = F.avg_pool2d(x, 2) return x