def _make_transpose(self, transblock, planes, blocks, stride=1): upsample = None if stride != 1: upsample = nn.Sequential( nn.ConvTranspose2d(self.inplanes * transblock.expansion, planes, kernel_size=2, stride=stride, padding=0, bias=False), SynchronizedBatchNorm2d(planes), ) elif self.inplanes * transblock.expansion != planes: upsample = nn.Sequential( nn.Conv2d(self.inplanes * transblock.expansion, planes, kernel_size=1, stride=stride, bias=False), SynchronizedBatchNorm2d(planes), ) layers = [] for i in range(1, blocks): layers.append(transblock(self.inplanes, self.inplanes * transblock.expansion)) layers.append(transblock(self.inplanes, planes, stride, upsample)) self.inplanes = planes // transblock.expansion return nn.Sequential(*layers)
def __init__(self, inplanes, planes, groups, reduction, stride=1, downsample=None): super(SEResNetBottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False, stride=stride) self.bn1 = SynchronizedBatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1, groups=groups, bias=False) self.bn2 = SynchronizedBatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = SynchronizedBatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.se_module = SEModule(planes * 4, reduction=reduction) self.downsample = downsample self.stride = stride
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6)): super(PPMBilinearDeepsup, self).__init__() self.use_softmax = use_softmax self.ppm = [] for scale in pool_scales: self.ppm.append(nn.Sequential( nn.AdaptiveAvgPool2d(scale), nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True) )) self.ppm = nn.ModuleList(self.ppm) #self.cbr_deepsup = conv3x3_bn_relu(fc_dim // 2, fc_dim // 4, 1) self.aspp_last = nn.Sequential( nn.Conv2d(fc_dim+len(pool_scales)*512, 512, kernel_size=3, padding=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout2d(0.1) ) #self.conv_last_deepsup = nn.Conv2d(fc_dim // 4, num_class, 1, 1, 0) #self.dropout_deepsup = nn.Dropout2d(0.1) for m in self.modules(): if isinstance(m,nn.Conv2d): our_kaiming_normal_(m.weight,0.1) if m.bias is not None: constant_(m.bias,0) elif isinstance(m,nn.BatchNorm2d): constant_(m.weight,1) constant_(m.bias,0)
def __init__(self, inplanes, planes, groups, reduction, stride=1, downsample=None, base_width=4): super(SEResNeXtBottleneck, self).__init__() width = math.floor(planes * (base_width / 64)) * groups self.conv1 = nn.Conv2d(inplanes, width, kernel_size=1, bias=False, stride=1) self.bn1 = SynchronizedBatchNorm2d(width) self.conv2 = nn.Conv2d(width, width, kernel_size=3, stride=stride, padding=1, groups=groups, bias=False) self.bn2 = SynchronizedBatchNorm2d(width) self.conv3 = nn.Conv2d(width, planes * 4, kernel_size=1, bias=False) self.bn3 = SynchronizedBatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.se_module = SEModule(planes * 4, reduction=reduction) self.downsample = downsample self.stride = stride
def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck_AWM, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = SynchronizedBatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = SynchronizedBatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = SynchronizedBatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride self.avgpool = nn.AdaptiveAvgPool2d(1) self.fc1 = nn.Linear(inplanes, inplanes, bias=False) self.fc2 = nn.Linear(planes * 4, planes * 4, bias=False) self.combine_Linear = nn.Sequential( nn.ReLU(inplace=True), nn.Linear(inplanes + planes * 4, (inplanes + planes * 4) // 2), nn.Linear((inplanes + planes * 4) // 2, 2), nn.Sigmoid())
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6)): super(PPMBilinearDeepsup, self).__init__() self.use_softmax = use_softmax self.ppm = [] for scale in pool_scales: self.ppm.append(nn.Sequential( nn.AdaptiveAvgPool2d(scale), nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True) )) self.ppm = nn.ModuleList(self.ppm) self.cbr_deepsup = conv3x3_bn_relu(fc_dim // 2, fc_dim // 4, 1) self.conv_last = nn.Sequential( nn.Conv2d(fc_dim+len(pool_scales)*512, 512, kernel_size=3, padding=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout2d(0.1), nn.Conv2d(512, num_class, kernel_size=1) ) self.conv_last_deepsup = nn.Conv2d(fc_dim // 4, num_class, 1, 1, 0) self.dropout_deepsup = nn.Dropout2d(0.1)
def __init__(self, block, layers, num_classes=1000): self.inplanes = 128 super(ResNet, self).__init__() self.conv1 = conv3x3(3, 64, stride=2) self.bn1 = SynchronizedBatchNorm2d(64) self.relu1 = nn.ReLU(inplace=True) self.conv2 = conv3x3(64, 64) self.bn2 = SynchronizedBatchNorm2d(64) self.relu2 = nn.ReLU(inplace=True) self.conv3 = conv3x3(64, 128) self.bn3 = SynchronizedBatchNorm2d(128) self.relu3 = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AvgPool2d(7, stride=1) self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, SynchronizedBatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_()
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6)): super(PSPBilinear, self).__init__() self.use_softmax = use_softmax self.psp = [] for scale in pool_scales: self.psp.append( nn.Sequential( nn.AdaptiveAvgPool2d(scale), nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True))) self.psp = nn.ModuleList(self.psp) self.conv_last = nn.Sequential( nn.Conv2d(fc_dim + len(pool_scales) * 512, 512, kernel_size=3, padding=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout2d(0.1), nn.Conv2d(512, num_class, kernel_size=1))
def __init__(self, inplanes, planes, stride=1, downsample=None, cbam=False): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = SynchronizedBatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = SynchronizedBatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = SynchronizedBatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride self.cbam = cbam if self.cbam: gate_channel = planes * 4 reduction_rate = 16 self.gate = AttentionGate(gate_channel, size_reduction_ratio=2, reduction_ratio=reduction_rate, version='v3')
def __init__(self, in_planes, out_planes, kernel=23, stride=1, has_bias=False): super(GCN, self).__init__() #self.psp_conv = conv3x3_bn_relu(in_planes, out_planes, 1) #in_planes = out_planes #out_planes = cfg.MODEL.NUM_CLASSES self.gcn23x23_0 = nn.Sequential( nn.Conv2d(in_planes, out_planes, kernel_size=[1, kernel], stride=stride, padding=[0, kernel // 2], dilation=(1, 1), bias=has_bias, groups=cfg.RESNETS.NUM_GROUPS), SynchronizedBatchNorm2d(out_planes), nn.ReLU(inplace=True)) self.gcn23x23_1 = nn.Sequential( nn.Conv2d(in_planes, out_planes, kernel_size=[kernel, 1], stride=stride, padding=[kernel // 2, 0], bias=has_bias, groups=cfg.RESNETS.NUM_GROUPS), SynchronizedBatchNorm2d(out_planes), nn.ReLU(inplace=True)) self.gcn23x23_2 = nn.Sequential( nn.Conv2d(out_planes, out_planes, kernel_size=[kernel, 1], stride=stride, padding=[kernel // 2, 0], bias=has_bias, groups=cfg.RESNETS.NUM_GROUPS), SynchronizedBatchNorm2d(out_planes), nn.ReLU(inplace=True)) self.gcn23x23_3 = nn.Sequential( nn.Conv2d(out_planes, out_planes, kernel_size=[1, kernel], stride=stride, padding=[0, kernel // 2], bias=has_bias, groups=cfg.RESNETS.NUM_GROUPS), SynchronizedBatchNorm2d(out_planes), nn.ReLU(inplace=True)) #self.br_side = nn.Sequential( # nn.Conv2d(out_planes, cfg.MODEL.NUM_CLASSES, 3, padding=1, stride=1), # SynchronizedBatchNorm2d(cfg.MODEL.NUM_CLASSES), # nn.ReLU(inplace=True), # nn.Conv2d(cfg.MODEL.NUM_CLASSES, cfg.MODEL.NUM_CLASSES, 3, padding=1, stride=1)) #self.conv_last = nn.Conv2d(out_planes, cfg.MODEL.NUM_CLASSES, 1, padding=0, stride=1) self.apply(self.weights_init)
def __init__(self, inplanes, planes, stride=1, downsample=None): super(BasicBlock, self).__init__() self.conv1 = conv3x3(inplanes, planes, stride) self.bn1 = SynchronizedBatchNorm2d(planes) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = SynchronizedBatchNorm2d(planes) self.downsample = downsample self.stride = stride
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6), fpn_inplanes=(256, 512, 1024, 2048), fpn_dim=256): super(UPerNet, self).__init__() self.use_softmax = use_softmax # PPM Module self.ppm_pooling = [] self.ppm_conv = [] for scale in pool_scales: self.ppm_pooling.append(nn.AdaptiveAvgPool2d(scale)) self.ppm_conv.append( nn.Sequential( nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True))) self.ppm_pooling = nn.ModuleList(self.ppm_pooling) self.ppm_conv = nn.ModuleList(self.ppm_conv) if 'deform_conv' in cfg.MODEL.CONV_BODY and False: self.ppm_last_conv = conv3x3_bn_relu( fc_dim + len(pool_scales) * 512, fpn_dim, 1) self.ppm_last_conv_drop = nn.Dropout2d(0.1) else: self.ppm_last_conv = conv3x3_bn_relu( fc_dim + len(pool_scales) * 512, fpn_dim, 1) # FPN Module self.fpn_in = [] for fpn_inplane in fpn_inplanes[:-1]: # skip the top layer self.fpn_in.append( nn.Sequential( nn.Conv2d(fpn_inplane, fpn_dim, kernel_size=1, bias=False), SynchronizedBatchNorm2d(fpn_dim), nn.ReLU(inplace=True))) self.fpn_in = nn.ModuleList(self.fpn_in) self.fpn_out = [] for i in range(len(fpn_inplanes) - 1): # skip the top layer if not cfg.SEM.GCN_ON: self.fpn_out.append( nn.Sequential(conv3x3_bn_relu(fpn_dim, fpn_dim, 1), )) else: self.fpn_out.append( nn.Sequential(GCN(fpn_dim, fpn_dim, kernel=15))) self.fpn_out = nn.ModuleList(self.fpn_out) if 'deform_conv' in cfg.MODEL.CONV_BODY and False: self.conv_last = nn.Sequential( conv3x3_bn_relu(len(fpn_inplanes) * fpn_dim, fpn_dim, 1), nn.Dropout2d(0.9), nn.Conv2d(fpn_dim, num_class, kernel_size=1)) else: self.conv_last = nn.Sequential( conv3x3_bn_relu(len(fpn_inplanes) * fpn_dim, fpn_dim, 1), nn.Conv2d(fpn_dim, num_class, kernel_size=1))
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6), fpn_inplanes=(256, 512, 1024, 2048), fpn_dim=256): super(CspnUPerNet, self).__init__() self.use_softmax = use_softmax # PPM Module self.ppm_pooling = [] self.ppm_conv = [] for scale in pool_scales: self.ppm_pooling.append(nn.AdaptiveAvgPool2d(scale)) self.ppm_conv.append( nn.Sequential( nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True))) self.ppm_pooling = nn.ModuleList(self.ppm_pooling) self.ppm_conv = nn.ModuleList(self.ppm_conv) self.ppm_last_conv = nn.Sequential( conv3x3_bn_relu(fc_dim + len(pool_scales) * 512, fpn_dim, 1), nn.Dropout2d(0.1)) # FPN Module self.fpn_in = [] for fpn_inplane in fpn_inplanes[:-1]: # skip the top layer self.fpn_in.append( nn.Sequential( nn.Conv2d(fpn_inplane, fpn_dim, kernel_size=1, bias=False), SynchronizedBatchNorm2d(fpn_dim), nn.ReLU(inplace=True))) self.fpn_in = nn.ModuleList(self.fpn_in) self.fpn_out = [] for i in range(len(fpn_inplanes) - 1): # skip the top layer self.fpn_out.append( nn.Sequential(conv3x3_bn_relu(fpn_dim, fpn_dim, 1), )) self.fpn_out = nn.ModuleList(self.fpn_out) self.fpn_out_last = nn.Sequential( conv3x3_bn_relu(len(fpn_inplanes) * fpn_dim, fpn_dim, 1), nn.Dropout2d(0.9), ) self.conv_last = nn.Conv2d(fpn_dim, num_class, kernel_size=1) self.cspn_last = nn.Sequential( nn.Conv2d(fpn_dim, 8 * cfg.MODEL.NUM_CLASSES, 3, padding=1, groups=cfg.RESNETS.NUM_GROUPS), SynchronizedBatchNorm2d(8 * cfg.MODEL.NUM_CLASSES), ) self.cspn_net = Affinity_Propagate()
def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck, self).__init__() self.conv1 = conv1x1(inplanes, planes) self.bn1 = SynchronizedBatchNorm2d(planes) self.conv2 = conv3x3(planes, planes, stride) self.bn2 = SynchronizedBatchNorm2d(planes) self.conv3 = conv1x1(planes, planes * self.expansion) self.bn3 = SynchronizedBatchNorm2d(planes * self.expansion) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride
def __init__(self, inplanes, planes, stride=1, groups=1, downsample=None): super(GroupBottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = SynchronizedBatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, groups=groups, bias=False) self.bn2 = SynchronizedBatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 2, kernel_size=1, bias=False) self.bn3 = SynchronizedBatchNorm2d(planes * 2) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6)): super(PPMBilinearDeepsup, self).__init__() self.use_softmax = use_softmax self.ppm = [] for scale in pool_scales: self.ppm.append( nn.Sequential( nn.AdaptiveAvgPool2d(scale), nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True))) self.ppm = nn.ModuleList(self.ppm) self.cbr_deepsup = conv3x3_bn_relu(fc_dim // 2, fc_dim // 4, 1) self.conv_last = nn.Sequential( nn.Conv2d(fc_dim + len(pool_scales) * 512, 512, kernel_size=3, padding=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout2d(0.25), # nn.Conv2d(512, num_class, kernel_size=1) # ConvLSTM((128, 128), 5, [512], (3, 3), 1, batch_first=True, return_all_layers=False), ) # self.channel_wise = ChannelWiseBlock(512, 64) # self.spatial_wise = SpatialWiseBlock(512) self.LSTM_previous = nn.Conv2d(512, 64, kernel_size=3, padding=1) self.LSTM = ConvLSTM((128, 128), 128, [64], (3, 3), 1, batch_first=True, return_all_layers=False) self.LSTM_after = nn.Conv2d(64, num_class, kernel_size=1) self.LSTM_framemunis = ConvLSTM((128, 128), 64, [64], (3, 3), 1, batch_first=True, return_all_layers=False) # self.LSTM_framemunis_after = nn.Conv2d(16, num_class, kernel_size=1) # self.classify_conv = nn.Conv2d(512, num_class, kernel_size=1) self.conv_last_deepsup = nn.Conv2d(fc_dim // 4, num_class, 1, 1, 0) self.dropout_deepsup = nn.Dropout2d(0.1)
def __init__(self, inplanes, planes, stride=1, upsample=None, **kwargs): super(TransBasicBlock, self).__init__() self.conv1 = conv3x3(inplanes, inplanes) self.bn1 = SynchronizedBatchNorm2d(inplanes) self.relu = nn.ReLU(inplace=True) if upsample is not None and stride != 1: self.conv2 = nn.ConvTranspose2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, output_padding=1, bias=False) else: self.conv2 = conv3x3(inplanes, planes, stride) self.bn2 = SynchronizedBatchNorm2d(planes) self.upsample = upsample self.stride = stride
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6)): super(SPN_PPMBilinearDeepsup, self).__init__() self.use_softmax = use_softmax self.ppm = [] for scale in pool_scales: self.ppm.append(nn.Sequential( nn.AdaptiveAvgPool2d(scale), nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True) )) self.ppm = nn.ModuleList(self.ppm) self.conv_last = nn.Sequential( nn.Conv2d(fc_dim+len(pool_scales)*512, 512, kernel_size=3, padding=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout2d(0.1), nn.Conv2d(512, num_class, kernel_size=1) ) self.cbr_guidance = conv3x3_bn_relu(fc_dim // 2, fc_dim // 4, 1) self.dropout_guidance = nn.Dropout2d(0.1) self.conv_last_guidance = nn.Conv2d(fc_dim // 4, num_class*12, 1, 1, 0) # spn model: # Input: score map + guidance network output # Output: refined map # score map: N*W*H*Class # guidance network output: N*W*H*(21*12=252) self.propagator_l2r = GateRecurrent2dnoind(True, False) # left->right self.propagator_r2l = GateRecurrent2dnoind(True, True) # right->left self.propagator_t2b = GateRecurrent2dnoind(False, False) # top->bottom self.propagator_b2t = GateRecurrent2dnoind(False, True) # bottom->top self.conv_spn = nn.Sequential( nn.Conv2d(fc_dim+len(pool_scales)*512, 512, kernel_size=3, padding=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout2d(0.1), nn.Conv2d(512, num_class, kernel_size=1) )
def __init__(self, orig_resnet): super(Resnet, self).__init__() # take pretrained resnet, except AvgPool and FC self.conv1 = orig_resnet.conv1 self.bn1 = orig_resnet.bn1 self.relu1 = orig_resnet.relu1 self.conv2 = orig_resnet.conv2 self.bn2 = orig_resnet.bn2 self.relu2 = orig_resnet.relu2 self.conv3 = orig_resnet.conv3 self.bn3 = orig_resnet.bn3 self.relu3 = orig_resnet.relu3 self.maxpool = orig_resnet.maxpool self.layer1 = orig_resnet.layer1 self.layer2 = orig_resnet.layer2 self.layer3 = orig_resnet.layer3 self.layer4 = orig_resnet.layer4 self.correlation=CorrelationLayer1D(max_disp=40,stride_2=1) self.conv_rdi = nn.Sequential(nn.Conv2d(512, 256, kernel_size=1, stride=1, padding=0), nn.ReLU(inplace=True)) self.conv_r = nn.Conv2d(357, 512, kernel_size=3, stride=1,padding=1, bias=False) self.bn4=SynchronizedBatchNorm2d(512)
def _make_layer(self, block, planes, blocks, groups, reduction, stride=1, downsample_kernel_size=1, downsample_padding=0): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=downsample_kernel_size, stride=stride, padding=downsample_padding, bias=False), SynchronizedBatchNorm2d(planes * block.expansion), ) layers = [] layers.append( block(self.inplanes, planes, groups, reduction, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes, groups, reduction)) return nn.Sequential(*layers)
def __init__(self, in_channels, out_channels, kernel_size, stride, padding, dilation, relu=True, need_bn=False): super(_ConvBatchNormReLU, self).__init__() self.add_module( "conv", nn.Conv2d( in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, bias=False, ), ) if need_bn: self.add_module("bn", SynchronizedBatchNorm2d(out_channels)) if relu: self.add_module("relu", nn.LeakyReLU(negative_slope=0.2, inplace=True))
def __init__(self, block, layers, num_classes=1000, zero_init_residual=False, freeze_until=None): super(PTResNet, self).__init__() self.inplanes = 64 self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = SynchronizedBatchNorm2d(64) self.relu1 = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) self.num_classes = num_classes if num_classes is not None: self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, SynchronizedBatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_() # Zero-initialize the last BN in each residual branch, # so that the residual branch starts with zeros, and each residual block behaves like an identity. # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677 if zero_init_residual: for m in self.modules(): if isinstance(m, Bottleneck): nn.init.constant_(m.bn3.weight, 0) elif isinstance(m, BasicBlock): nn.init.constant_(m.bn2.weight, 0) if freeze_until is not None: if freeze_until.startswith('layer'): self.conv1.weight.requires_grad = False done_freeze = False for idx in range(1, 5): layername = 'layer%d' % (idx) if layername == freeze_until: done_freeze = True layermod = getattr(self, layername) print("Freezing %s" % (layername)) for m in layermod.parameters(): m.requires_grad = False if done_freeze: break else: raise NotImplementedError()
def __init__(self, block, layers, num_classes=1000): self.inplanes = 64 super(ResNet152, self).__init__() if cfg.SEM.FREEZE_BN: print("Freezing BN and using AffineChannel2d as Batchnorm2d!") from lib.nn import AffineChannel2d SynchronizedBatchNorm2d = AffineChannel2d self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=True) #self.conv1 = nnl.SpatialConvolution(3, 64, 7, 7, 2, 2, 3, 3) self.bn1 = SynchronizedBatchNorm2d(64) self.relu = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, layers[0]) self.layer2 = self._make_layer(block, 128, layers[1], stride=2) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AvgPool2d(7) self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels m.weight.data.normal_(0, math.sqrt(2. / n)) elif isinstance(m, SynchronizedBatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_()
def __init__(self, num_class=150, fc_dim=4096, use_softmax=False, pool_scales=(1, 2, 3, 6), ppm_last_conv_dim=512, fpn_inplanes=(256,512,1024,2048), fpn_dim=256, T=1 ): super(UPerNet, self).__init__() self.use_softmax = use_softmax self.T = T # PPM Module self.ppm_pooling = [] self.ppm_conv = [] for scale in pool_scales: self.ppm_pooling.append(nn.AdaptiveAvgPool2d(scale)) self.ppm_conv.append(nn.Sequential( nn.Conv2d(fc_dim, ppm_last_conv_dim, kernel_size=1, bias=False), SynchronizedBatchNorm2d(ppm_last_conv_dim), nn.ReLU(inplace=True) )) self.ppm_pooling = nn.ModuleList(self.ppm_pooling) self.ppm_conv = nn.ModuleList(self.ppm_conv) self.ppm_last_conv = conv3x3_bn_relu(fc_dim + len(pool_scales)*ppm_last_conv_dim, fpn_dim, 1) # FPN Module self.fpn_in = [] for fpn_inplane in fpn_inplanes[:-1]: # skip the top layer self.fpn_in.append(nn.Sequential( nn.Conv2d(fpn_inplane, fpn_dim, kernel_size=1, bias=False), SynchronizedBatchNorm2d(fpn_dim), nn.ReLU(inplace=True) )) self.fpn_in = nn.ModuleList(self.fpn_in) self.fpn_out = [] for i in range(len(fpn_inplanes) - 1): # skip the top layer self.fpn_out.append(nn.Sequential( conv3x3_bn_relu(fpn_dim, fpn_dim, 1), )) self.fpn_out = nn.ModuleList(self.fpn_out) self.conv_last = nn.Sequential( conv3x3_bn_relu(len(fpn_inplanes) * fpn_dim, fpn_dim, 1), nn.Conv2d(fpn_dim, num_class, kernel_size=1) )
def __init__(self, num_class=150, fc_dim=2048, use_softmax=False, pool_scales=(1, 2, 3, 6), quad_inplanes=(128, 256, 512, 1024, 2048), quad_dim=256): super(QuadNet, self).__init__() self.use_softmax = use_softmax # PPM Module self.ppm_pooling = [] self.ppm_conv = [] for scale in pool_scales: self.ppm_pooling.append(nn.AdaptiveAvgPool2d(scale)) self.ppm_conv.append( nn.Sequential( nn.Conv2d(fc_dim, 512, kernel_size=1, bias=False), SynchronizedBatchNorm2d(512), nn.ReLU(inplace=True))) self.ppm_pooling = nn.ModuleList(self.ppm_pooling) self.ppm_conv = nn.ModuleList(self.ppm_conv) self.ppm_last_conv = conv3x3_bn_relu(fc_dim + len(pool_scales) * 512, quad_dim, 1) # GCN Module self.quad_in = [] for quad_inplane in quad_inplanes[:-1]: # skip the top layer self.quad_in.append( nn.Sequential( nn.Conv2d(quad_inplane, quad_dim, kernel_size=1, bias=False), SynchronizedBatchNorm2d(quad_dim), nn.ReLU(inplace=True))) self.quad_in = nn.ModuleList(self.quad_in) self.quad_gcn = nn.Sequential( nn.Conv2d(quad_dim * 6, quad_dim, kernel_size=1, bias=False), SynchronizedBatchNorm2d(quad_dim), nn.ReLU(inplace=True)) self.quad_out = [] for i in range(len(quad_inplanes) - 1): # skip the bottom layer self.quad_out.append( nn.Conv2d(quad_dim, num_class + 1, kernel_size=1, bias=False)) self.quad_out = nn.ModuleList(self.quad_out)
def __init__(self): super(SegmentationModuleBase, self).__init__() print("hello") # For cache self.mapping_to_detectron = None self.orphans_in_detectron = None self.iter=0 self.draw=False builder = semseg_heads.ModelBuilder() #define encoder if cfg.SEM.USE_RESNET: self.encoder = get_func(cfg.MODEL.CONV_BODY)() else: builder = semseg_heads.ModelBuilder() self.encoder = builder.build_encoder( arch=cfg.SEM.ARCH_ENCODER, fc_dim=cfg.SEM.FC_DIM, weights=cfg.RESNETS.IMAGENET_PRETRAINED_WEIGHTS ) #define shape weights self.decoder = builder.build_decoder( arch=cfg.SEM.DECODER_TYPE, fc_dim=cfg.SEM.FC_DIM, num_class=cfg.MODEL.NUM_CLASSES, use_softmax=not self.training, weights='') self.crit = nn.NLLLoss(ignore_index=255) self.deep_sup_scale = cfg.SEM.DEEP_SUB_SCALE if cfg.DISP.ORIGINAL: self.conv_last_disp = nn.Conv2d(cfg.DISP.DIM*2,1,kernel_size=3,padding=1,bias=False) self.conv_last_disp.apply(self._init_weights_normal) if cfg.DISP.USE_CRL_DISPFUL: self.conv_last_disp = CRL.DispFulNetSubset() if cfg.DISP.USE_CRL_DISPRES: self.conv_last_disp = CRL.DispResNetSubset(), self.conv_last_disp.apply(self._init_weights_normal) self.SmoothL1Loss = nn.SmoothL1Loss(reduction='none') #elementwise_mean #self.disp_loss = self._disp_loss #self.hardtanh = nn.Hardtanh(-1, 1,inplace=True) if len(cfg.SEM.DOWNSAMPLE) > 1: self.disp_deepsup=nn.Sequential( nn.Conv2d(cfg.SEM.FC_DIM // 2, cfg.SEM.FC_DIM // 4, kernel_size=3, stride=1, padding=1, bias=None), SynchronizedBatchNorm2d(cfg.SEM.FC_DIM // 4), nn.ReLU(inplace=True), nn.Dropout2d(0.1), nn.Conv2d(cfg.SEM.FC_DIM // 4, 1, kernel_size=3, stride=1, padding=1, bias=None) ) self.disp_deepsup.apply(self._init_weights_kaiming)
def _make_skip_layer(self, inplanes, planes): layers = nn.Sequential( nn.Conv2d(inplanes, planes, kernel_size=1, stride=1, padding=0, bias=False), SynchronizedBatchNorm2d(planes), nn.ReLU(inplace=True) ) return layers
def __init__(self, inp, oup, stride, expand_ratio): super(InvertedResidual, self).__init__() self.stride = stride assert stride in [1, 2] hidden_dim = round(inp * expand_ratio) self.use_res_connect = self.stride == 1 and inp == oup if expand_ratio == 1: self.conv = nn.Sequential( # dw nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False), SynchronizedBatchNorm2d(hidden_dim), nn.ReLU6(inplace=True), # pw-linear nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False), SynchronizedBatchNorm2d(oup), ) else: self.conv = nn.Sequential( # pw nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False), SynchronizedBatchNorm2d(hidden_dim), nn.ReLU6(inplace=True), # dw nn.Conv2d(hidden_dim, hidden_dim, 3, stride, 1, groups=hidden_dim, bias=False), SynchronizedBatchNorm2d(hidden_dim), nn.ReLU6(inplace=True), # pw-linear nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False), SynchronizedBatchNorm2d(oup), )
def __init__(self, overall_stride=32): super(Xception, self).__init__() self.relu = nn.ReLU(inplace=True) self.conv1 = nn.Conv2d(3, 32, 3,2, 0, bias=False) self.bn1 = SynchronizedBatchNorm2d(32) self.conv2 = nn.Conv2d(32,64,3,bias=False) self.bn2 = SynchronizedBatchNorm2d(64) #do relu here dilation = 1 self.block1=Block(64,128,2,2,start_with_relu=False,grow_first=True) #block(in_dim,out_dim,reps,stride) self.block2=Block(128,256,2,2,start_with_relu=True,grow_first=True) if overall_stride == 8: dilation *= 2 self.block3=Block(256,728,2,1,start_with_relu=True,grow_first=True) # pooling is at end of the block else: self.block3=Block(256,728,2,2,start_with_relu=True,grow_first=True) self.block4=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block5=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block6=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block7=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block8=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block9=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block10=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) self.block11=Block(728,728,3,1,start_with_relu=True,grow_first=True,dilation=dilation) if overall_stride == 8 or overall_stride == 16: dilation *= 2 self.block12=Block(728,1024,2,1,start_with_relu=True,grow_first=False,dilation=dilation) else: self.block12=Block(728,1024,2,2,start_with_relu=True,grow_first=False,dilation=dilation) self.conv3 = SeparableConv2d(1024,1536,3,1,dilation*2,dilation=dilation*2) # SeparableConv2d(in_dim,out_dim,kernel,stride,pad), dilation with multi-grid (1,2,4) self.bn3 = SynchronizedBatchNorm2d(1536) #do relu here self.conv4 = SeparableConv2d(1536,2048,3,1,dilation*4,dilation=dilation*4) # dilation with multi-grid (1,2,4) self.bn4 = SynchronizedBatchNorm2d(2048)
def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck_GE, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = SynchronizedBatchNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = SynchronizedBatchNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = SynchronizedBatchNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride self.Sigmoid = nn.Sigmoid() if cfg.SEM.USE_GE_BLOCK: self.AvgPool2d = nn.Sequential(nn.AdaptiveAvgPool2d(1)) """