def __init__(self, backbone='resnet101', output_stride=16, num_classes=21, bn='bn', freeze_bn=False, modal_num=3): super(DeepLab, self).__init__() if backbone == 'drn': output_stride = 8 self.best_iou = 0 if bn == 'sync_bn': BatchNorm = SynchronizedBatchNorm2d elif bn == 'bn': BatchNorm = nn.BatchNorm2d elif bn == 'gn': BatchNorm = nn.GroupNorm else: raise NotImplementedError('batch norm choice {} is not implemented'.format(bn)) self.backbone = build_backbone(backbone, output_stride, BatchNorm) # aspp/decoder-branches self.modal_num = modal_num self.aspps = [] self.decoders = [] for item in range(modal_num): self.aspps.append(build_aspp(backbone, output_stride, BatchNorm)) self.decoders.append(build_decoder(num_classes, backbone, BatchNorm)) self.aspps = nn.ModuleList(self.aspps) self.decoders = nn.ModuleList(self.decoders) # attention-branch self.attention_decoder = build_attention_decoder(num_classes, modal_num, backbone, BatchNorm) if freeze_bn: self.freeze_bn()
def __init__(self, backbone='resnet101', output_stride=16, num_classes=21, bn='bn', freeze_bn=False): super(DeepLab, self).__init__() if backbone == 'drn': output_stride = 8 self.best_iou = 0 if bn == 'sync_bn': BatchNorm = SynchronizedBatchNorm2d # elif bn == 'sync_abn': # BatchNorm = InPlaceABNSync elif bn == 'bn': BatchNorm = nn.BatchNorm2d # elif bn == 'abn': # BatchNorm = InPlaceABN elif bn == 'gn': BatchNorm = nn.GroupNorm else: raise NotImplementedError( 'batch norm choice {} is not implemented'.format(bn)) self.backbone = build_backbone(backbone, output_stride, BatchNorm) # self.backbone._load_pretrained_model() self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.decoder = build_decoder(num_classes, backbone, BatchNorm) if freeze_bn: self.freeze_bn()
def __init__(self, backbone='resnet', n_in_channels=1, output_stride=16, num_classes=1, n_bottleneck_channels=1, sync_bn=True, freeze_bn=False, pretrained_backbone=False): super(DeepLabBottleNeck, self).__init__() if backbone == 'drn': output_stride = 8 if sync_bn == True: BatchNorm = SynchronizedBatchNorm2d else: BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, n_in_channels, output_stride, BatchNorm, pretrained_backbone) self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.decoder = build_decoder(num_classes, backbone, BatchNorm, n_bottleneck_channels) self.activate_tanh = nn.Tanh() self.activate_sigmoid = nn.Sigmoid() self.freeze_bn = freeze_bn
def __init__(self, backbone='mobilenet', output_stride=8, num_classes=1, sync_bn=True, freeze_bn=False): super(ShadowNet2, self).__init__() if backbone == 'drn': output_stride = 8 if sync_bn == True: BatchNorm = SynchronizedBatchNorm2d else: BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, output_stride, BatchNorm) self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.reduce1 = LayerConv(320, 256, 1, 1, 0, False) self.dsc = DSC_Module(256, 256) self.reduce2 = LayerConv(512, 256, 1, 1, 0, False) self.decoder = build_decoder(num_classes, backbone, BatchNorm) if freeze_bn: self.freeze_bn()
def __init__(self, backbone='resnet18', in_channels=3, output_stride=16, num_classes=1, aux_classes=3, sync_bn=True, freeze_bn=False, pretrained=False, fusion_type='fusion', is_concat=False, **kwargs): super(PairwiseDeepLab, self).__init__() if backbone == 'drn': output_stride = 8 if sync_bn == True: BatchNorm = SynchronizedBatchNorm2d else: BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, in_channels, output_stride, BatchNorm, pretrained) ## branch1 self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.decoder = build_decoder(num_classes, backbone, BatchNorm) ## branch2 # self.br2_aspp = build_aspp(backbone, output_stride, BatchNorm) # self.br2_decoder = build_decoder(num_classes, backbone, BatchNorm) ## fusion self.fusion_type = fusion_type if self.fusion_type == 'attention_fusion': print('fusion_type is attention_fusion') self.fusion = build_attention_fusion(aux_classes, backbone, BatchNorm, is_concat=is_concat) elif self.fusion_type == 'fusion': print('init fusion_type') self.fusion = build_fusion(aux_classes, backbone, BatchNorm, is_concat=is_concat) else: raise NotImplementedError if freeze_bn: self.freeze_bn()
def __init__(self, backbone='mobilenet', output_stride=8, num_classes=1, sync_bn=True, freeze_bn=False): super(ShadowNetUncertaintyGuide, self).__init__() if backbone == 'drn': output_stride = 8 if sync_bn == True: BatchNorm = SynchronizedBatchNorm2d else: BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, output_stride, BatchNorm) self.temp_predict = nn.Sequential( nn.Conv2d(320, 256, kernel_size=3, stride=1, padding=1, bias=False), BatchNorm(256), nn.ReLU(), nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False), BatchNorm(256), nn.ReLU(), nn.Conv2d(256, num_classes, kernel_size=1, stride=1)) self.temp_uncertainty = nn.Sequential( nn.Conv2d(320, 256, kernel_size=3, stride=1, padding=1, bias=False), BatchNorm(256), nn.ReLU(), nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False), BatchNorm(256), nn.ReLU(), nn.Conv2d(256, num_classes, kernel_size=1, stride=1)) self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.reduce1 = LayerConv(320, 256, 1, 1, 0, False) self.dsc = DSC_Module(256, 256) self.reduce2 = LayerConv(512, 256, 1, 1, 0, False) self.decoder = build_decoder(num_classes, backbone, BatchNorm) # self.last_conv = nn.Sequential(nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False), # BatchNorm(256), # nn.ReLU(), # # nn.Dropout(0.5), # nn.Conv2d(256, 256, kernel_size=3, stride=1, padding=1, bias=False), # BatchNorm(256), # nn.ReLU(), # nn.Conv2d(256, num_classes, kernel_size=1, stride=1)) if freeze_bn: self.freeze_bn()
def __init__(self, backbone='resnet', n_in_channels=1, output_stride=16, num_classes=1, pretrained_backbone=False): super(DeepLab, self).__init__() if backbone == 'drn': output_stride = 8 BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, n_in_channels, output_stride, BatchNorm, pretrained_backbone) self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.decoder = build_decoder(num_classes, backbone, BatchNorm) return
def __init__(self, backbone='resnet', output_stride=16, num_class=21, sync_bn=True, freeze_bn=False): super(DeepLab, self).__init__() if sync_bn: batch_norm = SynchronizedBatchNorm2d else: batch_norm = nn.BatchNorm2d self.backbone = build_backbone(backbone, output_stride, batch_norm) self.aspp = build_aspp(backbone, output_stride, batch_norm) self.decoder = build_decoder(num_class, backbone, batch_norm) self.freeze_bn = freeze_bn
def __init__(self, backbone='resnet18', in_channels=3, output_stride=8, num_classes=1, sync_bn=True, freeze_bn=False, pretrained=False, **kwargs): super(ConsistentDeepLab, self).__init__() if backbone in ['drn', 'resnet18', 'resnet34']: output_stride = 8 if sync_bn == True: BatchNorm = SynchronizedBatchNorm2d else: BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, in_channels, output_stride, BatchNorm, pretrained) self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.decoder = build_decoder(num_classes, backbone, BatchNorm) if freeze_bn: self.freeze_bn()
def __init__(self, backbone='resnet', output_stride=16, num_classes=21, sync_bn=True, freeze_bn=False, pretrained=False): super(DeepLab, self).__init__() if backbone == 'drn': output_stride = 8 if sync_bn == True: BatchNorm = SynchronizedBatchNorm2d else: BatchNorm = nn.BatchNorm2d self.backbone = build_backbone(backbone, output_stride, BatchNorm, pretrained=pretrained) self.aspp = build_aspp(backbone, output_stride, BatchNorm) self.decoder = build_decoder(num_classes, backbone, BatchNorm) if freeze_bn: self.freeze_bn()
def __init__(self, n_vocab, max_seq_len, z_dim, c_dim, emb_dim, pretrained_emb, freeze_embeddings, flow, flow_type, E_args, G_args, C_args): super(RNN_VAE, self).__init__() self.MAX_SEQ_LEN = max_seq_len self.n_vocab = n_vocab self.z_dim = z_dim self.c_dim = c_dim self.device = torch.device('cuda') """ Word embeddings layer """ self.emb_dim = emb_dim self.word_emb = nn.Embedding(n_vocab, self.emb_dim, PAD_IDX) if pretrained_emb is not None: assert self.emb_dim == pretrained_emb.size( 1), 'emb dim dont match with pretrained' self.word_emb = nn.Embedding(n_vocab, self.emb_dim, PAD_IDX) # Set pretrained embeddings self.word_emb.weight.data.copy_(pretrained_emb) if freeze_embeddings: self.word_emb.weight.requires_grad = False ''' Initialize all the modules ''' self.encoder = build_encoder('gru', emb_dim=self.emb_dim, z_dim=z_dim, **E_args) self.decoder = build_decoder(embedding=self.word_emb, emb_dim=self.emb_dim + z_dim + c_dim, output_dim=n_vocab, h_dim=z_dim + c_dim, **G_args) self.classifier = build_classifier('cnn', self.emb_dim, **C_args) # Intiialize flow self.use_flow = flow > 0 if self.use_flow: self.flow_model = build_flow(flow_type, flow, z_dim)
def __init__(self, config): super(Transducer, self).__init__() #build cnn # self.conv1 = nn.Sequential( # nn.Conv2d(in_channels=1,out_channels=1,kernel_size=5,stride=1,padding=(2,2)), # nn.ReLU(), # nn.MaxPool2d(kernel_size=2,stride=2) # ) # self.conv2 = nn.Sequential( # nn.Conv2d(in_channels=1, out_channels=1, kernel_size=5, stride=1, padding=(2, 2)), # nn.ReLU(), # nn.MaxPool2d(kernel_size=2,stride=2) # ) self.config = config self.alpha = config.alpha # define encoder self.encoder = build_encoder(config.enc) self.fir_enc = buildFir_enc(config.fir_enc) # define decoder self.decoder = build_decoder(config.dec) self.max_target_length = config.max_target_length # define JointNet self.joint = JointNet(input_size=config.joint.input_size, inner_dim=config.joint.inner_size, vocab_size=config.vocab_size) if config.share_embedding: assert self.decoder.embedding.weight.size( ) == self.joint.project_layer.weight.size(), '%d != %d' % ( self.decoder.embedding.weight.size(1), self.joint.project_layer.weight.size(1)) self.joint.project_layer.weight = self.decoder.embedding.weight self.rnnt = RNNTLoss() self.crit = nn.CrossEntropyLoss() #if hiratical lstm or not self.fir_enc_or_not = config.fir_enc_or_not
def __init__(self, backbone='resnet', output_stride=16, num_classes=21): super().__init__() self.backbone = build_backbone(backbone, output_stride) self.aspp = build_ASPP(backbone, output_stride) self.decoder = build_decoder(backbone, num_classes) self._init_weight()