grid_embedder
allennlp.modules.vision.grid_embedder
GridEmbedder¶
class GridEmbedder(nn.Module, Registrable)
A GridEmbedder takes a batch of images as a tensor with shape
(batch_size, color_channels, height, width), and returns an ordered dictionary
of tensors with shape (batch_size, *), each representing a specific feature.
forward¶
class GridEmbedder(nn.Module, Registrable):
| ...
| def forward(
| self,
| images: FloatTensor,
| sizes: IntTensor
| ) -> "OrderedDict[str, FloatTensor]"
get_feature_names¶
class GridEmbedder(nn.Module, Registrable):
| ...
| def get_feature_names(self) -> Tuple[str, ...]
Returns the feature names, in order, i.e. the keys of the ordered output
dictionary from .forward().
NullGridEmbedder¶
@GridEmbedder.register("null")
class NullGridEmbedder(GridEmbedder)
A GridEmbedder that returns the input image as given.
forward¶
class NullGridEmbedder(GridEmbedder):
| ...
| def forward(
| self,
| images: FloatTensor,
| sizes: IntTensor
| ) -> "OrderedDict[str, FloatTensor]"
get_feature_names¶
class NullGridEmbedder(GridEmbedder):
| ...
| def get_feature_names(self) -> Tuple[str, ...]
ResnetBackbone¶
@GridEmbedder.register("resnet_backbone")
class ResnetBackbone(GridEmbedder):
| def __init__(self) -> None
Runs an image through ResNet, as implemented by torchvision.
forward¶
class ResnetBackbone(GridEmbedder):
| ...
| def forward(
| self,
| images: FloatTensor,
| sizes: IntTensor
| ) -> "OrderedDict[str, FloatTensor]"
get_feature_names¶
class ResnetBackbone(GridEmbedder):
| ...
| def get_feature_names(self) -> Tuple[str, ...]