visual_backbone¶
-
class
CNNBlockBase(in_channels, out_channels, stride)[source]¶ Bases:
paddle.fluid.dygraph.layers.Layer
-
ResNetBlockBase¶ alias of
paddlenlp.transformers.layoutxlm.visual_backbone.CNNBlockBase
-
class
ShapeSpec(channels=None, height=None, width=None, stride=None)[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone._ShapeSpec
-
get_norm(norm, out_channels)[source]¶ - Parameters
norm (str or callable) – either one of BN, SyncBN, FrozenBN, GN; or a callable that takes a channel number and returns the normalization layer as a nn.Layer.
out_channels (int) – out_channels
- Returns
the normalization layer
- Return type
nn.Layer or None
-
class
BasicBlock(in_channels, out_channels, *, stride=1, norm='BN')[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone.CNNBlockBaseThe basic residual block for ResNet-18 and ResNet-34 defined in :paper:`ResNet`, with two 3x3 conv layers and a projection shortcut if needed.
-
class
BottleneckBlock(in_channels, out_channels, *, bottleneck_channels, stride=1, num_groups=1, norm='BN', stride_in_1x1=False, dilation=1)[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone.CNNBlockBaseThe standard bottleneck residual block used by ResNet-50, 101 and 152 defined in :paper:`ResNet`. It contains 3 conv layers with kernels 1x1, 3x3, 1x1, and a projection shortcut if needed.
-
class
DeformBottleneckBlock(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)[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone.CNNBlockBaseSimilar to
BottleneckBlock, but with :paper:`deformable conv <deformconv>` in the 3x3 convolution.
-
class
BasicStem(in_channels=3, out_channels=64, norm='BN')[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone.CNNBlockBaseThe standard ResNet stem (layers before the first residual block), with a conv, relu and max_pool.
-
class
ResNet(stem, stages, num_classes=None, out_features=None, freeze_at=0)[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone.Backbone-
forward(x)[source]¶ - Parameters
x – Tensor of shape (N,C,H,W). H, W must be a multiple of
self.size_divisibility.- Returns
names and the corresponding features
- Return type
dict[str->Tensor]
-
static
make_stage(block_class, num_blocks, *, in_channels, out_channels, **kwargs)[source]¶ Create a list of blocks of the same type that forms one ResNet stage.
- Parameters
block_class (type) – a subclass of CNNBlockBase that’s used to create all blocks in this stage. A module of this type must not change spatial resolution of inputs unless its stride != 1.
num_blocks (int) – number of blocks in this stage
in_channels (int) – input channels of the entire stage.
out_channels (int) – output channels of every block in the stage.
kwargs – other arguments passed to the constructor of
block_class. If the argument name is “xx_per_block”, the argument is a list of values to be passed to each block in the stage. Otherwise, the same argument is passed to every block in the stage.
- Returns
a list of block module.
- Return type
list[CNNBlockBase]
Examples:
stage = ResNet.make_stage( BottleneckBlock, 3, in_channels=16, out_channels=64, bottleneck_channels=16, num_groups=1, stride_per_block=[2, 1, 1], dilations_per_block=[1, 1, 2] )
Usually, layers that produce the same feature map spatial size are defined as one “stage” (in :paper:`FPN`). Under such definition,
stride_per_block[1:]should all be 1.
-
static
make_default_stages(depth, block_class=None, **kwargs)[source]¶ Created list of ResNet stages from pre-defined depth (one of 18, 34, 50, 101, 152). If it doesn’t create the ResNet variant you need, please use
make_stage()instead for fine-grained customization.- Parameters
depth (int) – depth of ResNet
block_class (type) – the CNN block class. Has to accept
bottleneck_channelsargument for depth > 50. By default it is BasicBlock or BottleneckBlock, based on the depth.kwargs – other arguments to pass to
make_stage. Should not contain stride and channels, as they are predefined for each depth.
- Returns
- modules in all stages; see arguments of
ResNet.__init__.
- Return type
list[list[CNNBlockBase]]
-
-
class
LastLevelMaxPool[source]¶ Bases:
paddle.fluid.dygraph.layers.LayerThis module is used in the original FPN to generate a downsampled P6 feature from P5.
-
class
FPN(bottom_up, in_features, out_channels, norm='', top_block=None, fuse_type='sum')[source]¶ Bases:
paddlenlp.transformers.layoutxlm.visual_backbone.Backbone-
forward(x)[source]¶ - Parameters
x (dict[str->Tensor]) – mapping feature map name (e.g., “res5”) to feature map tensor for each feature level in high to low resolution order.
- Returns
mapping from feature map name to FPN feature map tensor in high to low resolution order. Returned feature names follow the FPN paper convention: “p<stage>”, where stage has stride = 2 ** stage e.g., [“p2”, “p3”, …, “p6”].
- Return type
dict[str->Tensor]
-