def __init__(self, in_channels, out_channels, *, stride=1, norm="BN"): """ Args: in_channels (int): Number of input channels. out_channels (int): Number of output channels. stride (int): Stride for the first conv. norm (str or callable): normalization for all conv layers. See :func:`layers.get_norm` for supported format. """ super().__init__(in_channels, out_channels, stride) if in_channels != out_channels: self.shortcut = Conv2d( in_channels, out_channels, kernel_size=1, stride=stride, bias=False, norm=get_norm(norm, out_channels), ) else: self.shortcut = None self.conv1 = Conv2d( in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False, norm=get_norm(norm, out_channels), ) self.conv2 = Conv2d( out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False, norm=get_norm(norm, out_channels), ) for layer in [self.conv1, self.conv2, self.shortcut]: if layer is not None: # shortcut can be None weight_init.c2_msra_fill(layer)
def __init__(self, in_channels=3, out_channels=64, norm="BN"): """ Args: norm (str or callable): norm after the first conv layer. See :func:`layers.get_norm` for supported format. """ super().__init__(in_channels, out_channels, 4) self.in_channels = in_channels self.conv1 = Conv2d( in_channels, out_channels, kernel_size=7, stride=2, padding=3, bias=False, norm=get_norm(norm, out_channels), ) weight_init.c2_msra_fill(self.conv1)
def __init__( self, in_channels, out_channels, *, bottleneck_channels, stride=1, num_groups=1, norm="BN", stride_in_1x1=False, dilation=1, ): """ Args: bottleneck_channels (int): number of output channels for the 3x3 "bottleneck" conv layers. num_groups (int): number of groups for the 3x3 conv layer. norm (str or callable): normalization for all conv layers. See :func:`layers.get_norm` for supported format. stride_in_1x1 (bool): when stride>1, whether to put stride in the first 1x1 convolution or the bottleneck 3x3 convolution. dilation (int): the dilation rate of the 3x3 conv layer. """ super().__init__(in_channels, out_channels, stride) if in_channels != out_channels: self.shortcut = Conv2d( in_channels, out_channels, kernel_size=1, stride=stride, bias=False, norm=get_norm(norm, out_channels), ) else: self.shortcut = None # The original MSRA ResNet models have stride in the first 1x1 conv # The subsequent fb.torch.resnet and Caffe2 ResNe[X]t implementations have # stride in the 3x3 conv stride_1x1, stride_3x3 = (stride, 1) if stride_in_1x1 else (1, stride) self.conv1 = Conv2d( in_channels, bottleneck_channels, kernel_size=1, stride=stride_1x1, bias=False, norm=get_norm(norm, bottleneck_channels), ) self.conv2 = Conv2d( bottleneck_channels, bottleneck_channels, kernel_size=3, stride=stride_3x3, padding=1 * dilation, bias=False, groups=num_groups, dilation=dilation, norm=get_norm(norm, bottleneck_channels), ) self.conv3 = Conv2d( bottleneck_channels, out_channels, kernel_size=1, bias=False, norm=get_norm(norm, out_channels), ) for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]: if layer is not None: # shortcut can be None weight_init.c2_msra_fill(layer)
def __init__( self, in_channels, out_channels, *, bottleneck_channels, stride=1, num_groups=1, norm="BN", stride_in_1x1=False, dilation=1, deform_modulated=False, deform_num_groups=1, ): super().__init__(in_channels, out_channels, stride) self.deform_modulated = deform_modulated if in_channels != out_channels: self.shortcut = Conv2d( in_channels, out_channels, kernel_size=1, stride=stride, bias=False, norm=get_norm(norm, out_channels), ) else: self.shortcut = None stride_1x1, stride_3x3 = (stride, 1) if stride_in_1x1 else (1, stride) self.conv1 = Conv2d( in_channels, bottleneck_channels, kernel_size=1, stride=stride_1x1, bias=False, norm=get_norm(norm, bottleneck_channels), ) if deform_modulated: deform_conv_op = ModulatedDeformConv # offset channels are 2 or 3 (if with modulated) * kernel_size * kernel_size offset_channels = 27 else: deform_conv_op = DeformConv offset_channels = 18 self.conv2_offset = Conv2d( bottleneck_channels, offset_channels * deform_num_groups, kernel_size=3, stride=stride_3x3, padding=1 * dilation, dilation=dilation, ) self.conv2 = deform_conv_op( bottleneck_channels, bottleneck_channels, kernel_size=3, stride=stride_3x3, padding=1 * dilation, bias=False, groups=num_groups, dilation=dilation, deformable_groups=deform_num_groups, norm=get_norm(norm, bottleneck_channels), ) self.conv3 = Conv2d( bottleneck_channels, out_channels, kernel_size=1, bias=False, norm=get_norm(norm, out_channels), ) for layer in [self.conv1, self.conv2, self.conv3, self.shortcut]: if layer is not None: # shortcut can be None weight_init.c2_msra_fill(layer) nn.init.constant_(self.conv2_offset.weight, 0) nn.init.constant_(self.conv2_offset.bias, 0)
def __init__( self, *, input_shape: Dict[str,ShapeSpec], num_classes: Dict[str, int], norm="", prior_prob=0.01, final_channel=512, hierarchy_loss=False, hierarchy_prior=None, ): """ NOTE: this interface is experimental. Args: input_shape (List[ShapeSpec]): input shape num_classes (int): number of classes. Used to label background proposals. num_anchors (int): number of generated anchors conv_dims (List[int]): dimensions for each convolution layer norm (str or callable): Normalization for conv layers except for the two output layers. See :func:`herbarium.layers.get_norm` for supported types. prior_prob (float): Prior weight for computing bias """ super().__init__() if norm == "BN" or norm == "SyncBN": logger = logging.getLogger(__name__) logger.warn("Shared norm does not work well for BN, SyncBN, expect poor results") cls_subnet = defaultdict(list) for input_key in list(input_shape.keys()): in_channels = input_shape[input_key].channels out_channels = final_channel cls_subnet[input_key] = [AttentionConv(in_channels, out_channels, kernel_size=3, stride=1, padding=1)] if norm: cls_subnet[input_key].append(get_norm(norm, out_channels)) cls_subnet[input_key].append(nn.ReLU()) cls_subnet[input_key].append(nn.AdaptiveAvgPool2d((1,1))) cls_subnet[input_key] = nn.Sequential(*cls_subnet[input_key]) self.cls_subnet = nn.ModuleDict(cls_subnet) cls_score = defaultdict(list) for cls_level in list(num_classes.keys()): cls_score[cls_level] = nn.Conv2d( final_channel, num_classes[cls_level], kernel_size=1, stride=1 ) self.cls_score = nn.ModuleDict(cls_score) self.hierarchy_prior = nn.ParameterDict({ k: nn.Parameter(v, requires_grad=False) for k, v in hierarchy_prior.items() }) # Initialization for modules in [self.cls_subnet, self.cls_score]: for layer in modules.modules(): if isinstance(layer, nn.Conv2d): if layer.weight is not None: torch.nn.init.normal_(layer.weight, mean=0, std=0.01) if layer.bias is not None: torch.nn.init.constant_(layer.bias, 0)