def __init__(self, inchannels, bn_type): super(EmbedModule, self).__init__() inter_channels = inchannels // 4 self.conv = nn.Sequential( nn.Conv2d(inchannels, inter_channels, kernel_size=1, padding=0, bias=False), ModuleHelper.BatchNorm2d(bn_type=bn_type)(inter_channels), nn.ReLU(inplace=True), nn.Conv2d(inter_channels, inter_channels, kernel_size=7, padding=3, stride=1, bias=False), ModuleHelper.BatchNorm2d(bn_type=bn_type)(inter_channels), nn.ReLU(inplace=True), nn.Conv2d(inter_channels, inchannels, kernel_size=1, padding=0, bias=False), ModuleHelper.BatchNorm2d(bn_type=bn_type)(inchannels), nn.ReLU(inplace=True), )
def __init__(self, block, layers, num_classes=1000, bn_type=None): self.inplanes = 128 super(CaffeResNet, self).__init__() self.conv1 = conv3x3(3, 64, stride=2) self.bn1 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(64, momentum=0.1) self.relu1 = nn.ReLU(inplace=True) self.conv2 = conv3x3(64, 64) self.bn2 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(64, momentum=0.1) self.relu2 = nn.ReLU(inplace=True) self.conv3 = conv3x3(64, 128) self.bn3 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(128, momentum=0.1) 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], bn_type=bn_type) self.layer2 = self._make_layer(block, 128, layers[1], stride=2, bn_type=bn_type) self.layer3 = self._make_layer(block, 256, layers[2], stride=2, bn_type=bn_type) self.layer4 = self._make_layer(block, 512, layers[3], stride=2, bn_type=bn_type) 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, ModuleHelper.BatchNorm2d(bn_type=bn_type)): m.weight.data.fill_(1) m.bias.data.zero_()
def __init__(self, num_class=150, fc_dim=4096, bn_type=None): super(PPMBilinearDeepsup, self).__init__() pool_scales = (1, 2, 3, 6) 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), ModuleHelper.BatchNorm2d(bn_type=bn_type)(512), nn.ReLU(inplace=True))) self.ppm = nn.ModuleList(self.ppm) self.cbr_deepsup = _ConvBatchNormReluBlock(fc_dim // 2, fc_dim // 4, 3, 1, bn_type=bn_type) self.conv_last = nn.Sequential( nn.Conv2d(fc_dim + len(pool_scales) * 512, 512, kernel_size=3, padding=1, bias=False), ModuleHelper.BatchNorm2d(bn_type=bn_type)(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, num_input_features, growth_rate, bn_size, drop_rate, bn_type): super(_DenseLayer, self).__init__() self.add_module( 'norm1', ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_input_features)), self.add_module('relu1', nn.ReLU(inplace=True)), self.add_module( 'conv1', nn.Conv2d(num_input_features, bn_size * growth_rate, kernel_size=1, stride=1, bias=False)), self.add_module( 'norm2', ModuleHelper.BatchNorm2d(bn_type=bn_type)(bn_size * growth_rate)), self.add_module('relu2', nn.ReLU(inplace=True)), self.add_module( 'conv2', nn.Conv2d(bn_size * growth_rate, growth_rate, kernel_size=3, stride=1, padding=1, bias=False)), self.drop_rate = drop_rate
def __init__(self, input_num, num1, num2, dilation_rate, drop_out, norm_type): super(_DenseAsppBlock, self).__init__() self.add_module('relu1', nn.ReLU(inplace=False)), self.add_module( 'conv1', nn.Conv2d(in_channels=input_num, out_channels=num1, kernel_size=1)), self.add_module( 'norm2', ModuleHelper.BatchNorm2d(norm_type=norm_type)(num_features=num1)), self.add_module('relu2', nn.ReLU(inplace=False)), self.add_module( 'conv2', nn.Conv2d(in_channels=num1, out_channels=num2, kernel_size=3, dilation=dilation_rate, padding=dilation_rate)), self.add_module( 'norm2', ModuleHelper.BatchNorm2d(norm_type=norm_type)( num_features=input_num)), self.drop_rate = drop_out
def __init__(self, input_nc, ndf=64, n_layers=3, norm_type=None): """Construct a PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int) -- the number of filters in the last conv layer n_layers (int) -- the number of conv layers in the discriminator norm_layer -- normalization layer """ super(NLayerDiscriminator, self).__init__() use_bias = (norm_type == 'instancenorm') kw = 4 padw = 1 sequence = [nn.Conv2d(input_nc, ndf, kernel_size=kw, stride=2, padding=padw), nn.LeakyReLU(0.2, True)] nf_mult = 1 nf_mult_prev = 1 for n in range(1, n_layers): # gradually increase the number of filters nf_mult_prev = nf_mult nf_mult = min(2 ** n, 8) sequence += [ nn.Conv2d(ndf * nf_mult_prev, ndf * nf_mult, kernel_size=kw, stride=2, padding=padw, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(ndf * nf_mult), nn.LeakyReLU(0.2, True) ] nf_mult_prev = nf_mult nf_mult = min(2 ** n_layers, 8) sequence += [ nn.Conv2d(ndf * nf_mult_prev, ndf * nf_mult, kernel_size=kw, stride=1, padding=padw, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(ndf * nf_mult), nn.LeakyReLU(0.2, True) ] sequence += [nn.Conv2d(ndf * nf_mult, 1, kernel_size=kw, stride=1, padding=padw)] # output 1 channel prediction map self.model = nn.Sequential(*sequence)
def __init__(self, inplanes, planes, stride=1, downsample=None, bn_type=None): super(BasicBlock, self).__init__() self.conv1 = conv3x3(inplanes, planes, stride) self.bn1 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes) self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes) self.downsample = downsample self.stride = stride
def freeze_bn(net, norm_type=None): for m in net.modules(): if isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d) or isinstance(m, nn.BatchNorm3d): m.eval() if norm_type is not None: from models.tools.module_helper import ModuleHelper if isinstance(m, ModuleHelper.BatchNorm2d(norm_type=norm_type, ret_cls=True)) \ or isinstance(m, ModuleHelper.BatchNorm1d(norm_type=norm_type, ret_cls=True)) \ or isinstance(m, ModuleHelper.BatchNorm3d(norm_type=norm_type, ret_cls=True)): m.eval()
def __init__(self, inplanes, planes, stride=1, downsample=None, bn_type=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = ModuleHelper.BatchNorm2d(bn_type=bn_type)(planes * 4) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride
def __init__(self, outer_nc, inner_nc, submodule=None, outermost=False, innermost=False, norm_type=None, use_dropout=False): super(UNetSkipConnectionBlock, self).__init__() self.outermost = outermost downconv = nn.Conv2d(outer_nc, inner_nc, kernel_size=4, stride=2, padding=1) downrelu = nn.LeakyReLU(0.2, True) downnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(inner_nc) uprelu = nn.ReLU(True) upnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(outer_nc) if outermost: upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc, kernel_size=4, stride=2, padding=1) down = [downconv] up = [uprelu, upconv, nn.Tanh()] model = down + [submodule] + up elif innermost: upconv = nn.ConvTranspose2d(inner_nc, outer_nc, kernel_size=4, stride=2, padding=1) down = [downrelu, downconv] up = [uprelu, upconv, upnorm] model = down + up else: upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc, kernel_size=4, stride=2, padding=1) down = [downrelu, downconv, downnorm] up = [uprelu, upconv, upnorm] if use_dropout: model = down + [submodule] + up + [nn.Dropout(0.5)] else: model = down + [submodule] + up self.model = nn.Sequential(*model)
def __init__(self, outer_nc, inner_nc, input_nc=None, submodule=None, outermost=False, innermost=False, norm_type=None, use_dropout=False): """Construct a Unet submodule with skip connections. Parameters: outer_nc (int) -- the number of filters in the outer conv layer inner_nc (int) -- the number of filters in the inner conv layer input_nc (int) -- the number of channels in input images/features submodule (UnetSkipConnectionBlock) -- previously defined submodules outermost (bool) -- if this module is the outermost module innermost (bool) -- if this module is the innermost module norm_layer -- normalization layer user_dropout (bool) -- if use dropout layers. """ super(UnetSkipConnectionBlock, self).__init__() self.outermost = outermost use_bias = (norm_type == 'instancenorm') if input_nc is None: input_nc = outer_nc downconv = nn.Conv2d(input_nc, inner_nc, kernel_size=4, stride=2, padding=1, bias=use_bias) downrelu = nn.LeakyReLU(0.2, True) downnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(inner_nc) uprelu = nn.ReLU(True) upnorm = ModuleHelper.BatchNorm2d(norm_type=norm_type)(outer_nc) if outermost: upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc, kernel_size=4, stride=2, padding=1) down = [downconv] up = [uprelu, upconv, nn.Tanh()] model = down + [submodule] + up elif innermost: upconv = nn.ConvTranspose2d(inner_nc, outer_nc, kernel_size=4, stride=2, padding=1, bias=use_bias) down = [downrelu, downconv] up = [uprelu, upconv, upnorm] model = down + up else: upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc, kernel_size=4, stride=2, padding=1, bias=use_bias) down = [downrelu, downconv, downnorm] up = [uprelu, upconv, upnorm] if use_dropout: model = down + [submodule] + up + [nn.Dropout(0.5)] else: model = down + [submodule] + up self.model = nn.Sequential(*model)
def __init__(self, low_in_channels, high_in_channels, key_channels, value_channels, out_channels=None, scale=1, norm_type=None, psp_size=(1, 3, 6, 8)): super(_SelfAttentionBlock, self).__init__() self.scale = scale self.in_channels = low_in_channels self.out_channels = out_channels self.key_channels = key_channels self.value_channels = value_channels if out_channels == None: self.out_channels = high_in_channels self.pool = nn.MaxPool2d(kernel_size=(scale, scale)) self.f_key = nn.Sequential( nn.Conv2d(in_channels=self.in_channels, out_channels=self.key_channels, kernel_size=1, stride=1, padding=0), ModuleHelper.BNReLU(self.key_channels, norm_type=norm_type), ) self.f_query = nn.Sequential( nn.Conv2d(in_channels=high_in_channels, out_channels=self.key_channels, kernel_size=1, stride=1, padding=0), ModuleHelper.BNReLU(self.key_channels, norm_type=norm_type), ) self.f_value = nn.Conv2d(in_channels=self.in_channels, out_channels=self.value_channels, kernel_size=1, stride=1, padding=0) self.W = nn.Conv2d(in_channels=self.value_channels, out_channels=self.out_channels, kernel_size=1, stride=1, padding=0) self.psp = PSPModule(psp_size) nn.init.constant_(self.W.weight, 0) nn.init.constant_(self.W.bias, 0)
def squeezenet_dilated8(self): model = DilatedSqueezeNet() model = ModuleHelper.load_model(model, pretrained=self.configer.get( 'network', 'pretrained'), all_match=False) return model
def __init__(self, configer): self.inplanes = 128 super(DeepLabV3, self).__init__() self.configer = configer self.num_classes = self.configer.get('data', 'num_classes') self.backbone = BackboneSelector(configer).get_backbone() self.head = nn.Sequential( ASPPModule(2048, bn_type=self.configer.get('network', 'bn_type')), nn.Conv2d(512, self.num_classes, kernel_size=1, stride=1, padding=0, bias=True)) self.dsn = nn.Sequential( nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1), ModuleHelper.BNReLU(512, bn_type=self.configer.get( 'network', 'bn_type')), nn.Dropout2d(0.1), nn.Conv2d(512, self.num_classes, kernel_size=1, stride=1, padding=0, bias=True))
def _make_layer(self, block, planes, blocks, stride=1, norm_type=None): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), ModuleHelper.BatchNorm2d(norm_type=norm_type)(planes * block.expansion), ) layers = [] layers.append( block(self.inplanes, planes, stride, downsample, norm_type=norm_type)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes, norm_type=norm_type)) return nn.Sequential(*layers)
def mobilenetv2(self): model = MobileNetV2() model = ModuleHelper.load_model(model, pretrained=self.configer.get( 'network', 'pretrained'), all_match=False) return model
def __init__(self, configer): super(PSPNet, self).__init__() self.configer = configer self.num_classes = self.configer.get('data', 'num_classes') self.backbone = BackboneSelector(configer).get_backbone() num_features = self.backbone.get_num_features() self.dsn = nn.Sequential( _ConvBatchNormReluBlock(num_features // 2, num_features // 4, 3, 1, bn_type=self.configer.get( 'network', 'bn_type')), nn.Dropout2d(0.1), nn.Conv2d(num_features // 4, self.num_classes, 1, 1, 0)) self.ppm = PPMBilinearDeepsup(fc_dim=num_features, bn_type=self.configer.get( 'network', 'bn_type')) self.cls = nn.Sequential( nn.Conv2d(num_features + 4 * 512, 512, kernel_size=3, padding=1, bias=False), ModuleHelper.BNReLU(512, bn_type=self.configer.get( 'network', 'bn_type')), nn.Dropout2d(0.1), nn.Conv2d(512, self.num_classes, kernel_size=1))
def __init__(self, configer): super(DeepLabV3, self).__init__() self.configer = configer self.backbone = BackboneSelector(configer).get_backbone() self.backbone = nn.Sequential( self.backbone.conv1, self.backbone.bn1, self.backbone.relu1, self.backbone.conv2, self.backbone.bn2, self.backbone.relu2, self.backbone.conv3, self.backbone.bn3, self.backbone.relu3, self.backbone.maxpool, self.backbone.layer1, self.backbone.layer2, self.backbone.layer3) self.MG_features = _ResidualBlockMulGrid( inplanes=1024, midplanes=512, outplanes=2048, stride=1, dilation=2, mulgrid=self.configer.get('network', 'multi_grid'), bn_type=self.configer.get('network', 'bn_type')) pyramids = [6, 12, 18] self.aspp = _ASPPModule(2048, 256, pyramids, bn_type=self.configer.get( 'network', 'bn_type')) self.fc1 = nn.Sequential( nn.Conv2d(1280, 256, kernel_size=1), # 256 * 5 = 1280 ModuleHelper.BatchNorm2d( bn_type=self.configer.get('network', 'bn_type'))(256)) self.fc2 = nn.Conv2d(256, self.configer.get('data', 'num_classes'), kernel_size=1)
def __init__(self, low_in_channels, high_in_channels, out_channels, key_channels, value_channels, dropout, sizes=([1]), norm_type=None, psp_size=(1, 3, 6, 8)): super(AFNB, self).__init__() self.stages = [] self.norm_type = norm_type self.psp_size = psp_size self.stages = nn.ModuleList([ self._make_stage([low_in_channels, high_in_channels], out_channels, key_channels, value_channels, size) for size in sizes ]) self.conv_bn_dropout = nn.Sequential( nn.Conv2d(out_channels + high_in_channels, out_channels, kernel_size=1, padding=0), ModuleHelper.BatchNorm2d(norm_type=self.norm_type)(out_channels), nn.Dropout2d(dropout))
def __init__(self, in_channel, out_channel, kernel_size, stride=1, padding=0, dilation=1, groups=1, bn_type=None): super(ConvBnRelu, self).__init__() self.conv_bn_relu = nn.Sequential( nn.Conv2d(in_channel, out_channel, kernel_size, stride, padding, dilation, groups, False), ModuleHelper.BatchNorm2d(bn_type=bn_type)(out_channel), nn.ReLU(True))
def build_conv_block(self, dim, padding_type, norm_type, use_dropout, use_bias): """Construct a convolutional block. Parameters: dim (int) -- the number of channels in the conv layer. padding_type (str) -- the name of padding layer: reflect | replicate | zero norm_layer -- normalization layer use_dropout (bool) -- if use dropout layers. use_bias (bool) -- if the conv layer uses bias or not Returns a conv block (with a conv layer, a normalization layer, and a non-linearity layer (ReLU)) """ conv_block = [] p = 0 if padding_type == 'reflect': conv_block += [nn.ReflectionPad2d(1)] elif padding_type == 'replicate': conv_block += [nn.ReplicationPad2d(1)] elif padding_type == 'zero': p = 1 else: raise NotImplementedError('padding [%s] is not implemented' % padding_type) conv_block += [ nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(dim), nn.ReLU(True) ] if use_dropout: conv_block += [nn.Dropout(0.5)] p = 0 if padding_type == 'reflect': conv_block += [nn.ReflectionPad2d(1)] elif padding_type == 'replicate': conv_block += [nn.ReplicationPad2d(1)] elif padding_type == 'zero': p = 1 else: raise NotImplementedError('padding [%s] is not implemented' % padding_type) conv_block += [ nn.Conv2d(dim, dim, kernel_size=3, padding=p, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(dim) ] return nn.Sequential(*conv_block)
def __init__(self, inplanes, outplanes, kernel_size, stride, padding, dilation, relu=True, bn_type=None): super(_ConvBatchNormReluBlock, self).__init__() self.relu = relu self.conv = nn.Conv2d(in_channels=inplanes,out_channels=outplanes, kernel_size=kernel_size, stride=stride, padding = padding, dilation = dilation, bias=False) self.bn = ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_features=outplanes) self.relu_f = nn.ReLU()
def squeezenet(self): """Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on Places """ model = SqueezeNet() model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained'), all_match=False) return model
def vgg_bn(self, vgg_cfg=None): backbone = self.configer.get('network', 'backbone') model = VGG(cfg_name=backbone, vgg_cfg=vgg_cfg, bn=True) model = ModuleHelper.load_model(model, pretrained=self.configer.get( 'network', 'pretrained'), all_match=False) return model
def __init__(self, input_nc, output_nc, ngf=64, norm_type=None, use_dropout=False, n_blocks=6, padding_type='reflect'): """Construct a Resnet-based generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- the number of channels in output images ngf (int) -- the number of filters in the last conv layer norm_layer -- normalization layer use_dropout (bool) -- if use dropout layers n_blocks (int) -- the number of ResNet blocks padding_type (str) -- the name of padding layer in conv layers: reflect | replicate | zero """ assert(n_blocks >= 0) super(ResNetGenerator, self).__init__() use_bias = (norm_type == 'instancenorm') model = [nn.ReflectionPad2d(3), nn.Conv2d(input_nc, ngf, kernel_size=7, padding=0, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(ngf), nn.ReLU(True)] n_downsampling = 2 for i in range(n_downsampling): # add downsampling layers mult = 2 ** i model += [nn.Conv2d(ngf * mult, ngf * mult * 2, kernel_size=3, stride=2, padding=1, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(ngf * mult * 2), nn.ReLU(True)] mult = 2 ** n_downsampling for i in range(n_blocks): # add ResNet blocks model += [ResnetBlock(ngf * mult, padding_type=padding_type, norm_type=norm_type, use_dropout=use_dropout, use_bias=use_bias)] for i in range(n_downsampling): # add upsampling layers mult = 2 ** (n_downsampling - i) model += [nn.ConvTranspose2d(ngf * mult, int(ngf * mult / 2), kernel_size=3, stride=2, padding=1, output_padding=1, bias=use_bias), ModuleHelper.BatchNorm2d(norm_type=norm_type)(int(ngf * mult / 2)), nn.ReLU(True)] model += [nn.ReflectionPad2d(3)] model += [nn.Conv2d(ngf, output_nc, kernel_size=7, padding=0)] model += [nn.Tanh()] self.model = nn.Sequential(*model)
def __init__(self, configer): super(asymmetric_non_local_network, self).__init__() self.configer = configer self.num_classes = self.configer.get('data', 'num_classes') self.backbone = BackboneSelector(configer).get_backbone() # low_in_channels, high_in_channels, out_channels, key_channels, value_channels, dropout self.fusion = AFNB(1024, 2048, 2048, 256, 256, dropout=0.05, sizes=([1]), norm_type=self.configer.get('network', 'norm_type')) # extra added layers self.context = nn.Sequential( nn.Conv2d(2048, 512, kernel_size=3, stride=1, padding=1), ModuleHelper.BNReLU(512, norm_type=self.configer.get( 'network', 'norm_type')), APNB(in_channels=512, out_channels=512, key_channels=256, value_channels=256, dropout=0.05, sizes=([1]), norm_type=self.configer.get('network', 'norm_type'))) self.cls = nn.Conv2d(512, self.num_classes, kernel_size=1, stride=1, padding=0, bias=True) self.dsn = nn.Sequential( nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1), ModuleHelper.BNReLU(512, norm_type=self.configer.get( 'network', 'norm_type')), nn.Dropout2d(0.05), nn.Conv2d(512, self.num_classes, kernel_size=1, stride=1, padding=0, bias=True))
def darknet53(self): """Constructs a darknet-53 model. """ model = DarkNet([1, 2, 8, 8, 4]) model = ModuleHelper.load_model(model, pretrained=self.configer.get( 'network', 'pretrained'), all_match=False) return model
def resnet34(self, **kwargs): """Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on Places """ model = ResNet(BasicBlock, [3, 4, 6, 3], deep_base=False, bn_type=self.configer.get('network', 'bn_type'), **kwargs) model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained')) return model
def deepbase_resnet101(self, **kwargs): """Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on Places """ model = ResNet(Bottleneck, [3, 4, 23, 3], deep_base=True, bn_type=self.configer.get('network', 'bn_type'), **kwargs) model = ModuleHelper.load_model(model, pretrained=self.configer.get('network', 'pretrained')) return model
def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000, bn_type=None): super(DenseNet, self).__init__() # First convolution self.features = nn.Sequential(OrderedDict([ ('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2, padding=3, bias=False)), ('norm0', ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_init_features)), ('relu0', nn.ReLU(inplace=True)), ('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)), ])) # Each denseblock num_features = num_init_features for i, num_layers in enumerate(block_config): block = _DenseBlock(num_layers=num_layers, num_input_features=num_features, bn_size=bn_size, growth_rate=growth_rate, drop_rate=drop_rate, bn_type=bn_type) self.features.add_module('denseblock%d' % (i + 1), block) num_features = num_features + num_layers * growth_rate if i != len(block_config) - 1: trans = _Transition(num_input_features=num_features, num_output_features=num_features // 2, bn_type=bn_type) avg_pool = nn.AvgPool2d(kernel_size=2, stride=2) self.features.add_module('transition%d' % (i + 1), trans) self.features.add_module('transition%s_pool' % (i + 1), avg_pool) num_features = num_features // 2 self.num_features = num_features # Final batch norm self.features.add_module('norm5', ModuleHelper.BatchNorm2d(bn_type=bn_type)(num_features)) # Linear layer self.classifier = nn.Linear(num_features, num_classes) # Official init from torch repo. for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight) elif isinstance(m, ModuleHelper.BatchNorm2d(bn_type=bn_type)): nn.init.constant_(m.weight, 1) nn.init.constant_(m.bias, 0) elif isinstance(m, nn.Linear): nn.init.constant_(m.bias, 0)