View Source ExVision.SemanticSegmentation.DeepLabV3_MobileNetV3 (Ex Vision v0.4.0)

A semantic segmentation model for MobileNetV3 Backbone. Exported from torchvision.

Summary

Types

category_t()

Type describing all categories recognised by DeepLabV3 MobileNetV3

output_t()

t()

An instance of the Elixir.ExVision.SemanticSegmentation.DeepLabV3_MobileNetV3

Functions

batched_run(name \\ __MODULE__, input)

Submits the input for inference to the process running the Nx.Serving for this model.

categories()

Returns a list of all categories recognised by DeepLabV3 MobileNetV3

load(options \\ [])

Creates the model instance

load!(opts \\ [])

Same as load/1, but raises and error on failure.

run(model, input)

Immediatelly applies the model to the given input, in the scope of the current process.

Types

category_t()

@type category_t() ::
  :__background__
  | :aeroplane
  | :bicycle
  | :bird
  | :boat
  | :bottle
  | :bus
  | :car
  | :cat
  | :chair
  | :cow
  | :diningtable
  | :dog
  | :horse
  | :motorbike
  | :person
  | :pottedplant
  | :sheep
  | :sofa
  | :train
  | :tvmonitor

Type describing all categories recognised by DeepLabV3 MobileNetV3

output_t()

@type output_t() :: %{required(category_t()) => Nx.Tensor.t()}

t()

@opaque t()

An instance of the Elixir.ExVision.SemanticSegmentation.DeepLabV3_MobileNetV3

Functions

batched_run(name \\ MODULE, input)

@spec batched_run(atom(), ExVision.Model.input_t()) :: output_t() | [output_t()]

Submits the input for inference to the process running the Nx.Serving for this model.

categories()

@spec categories() :: [category_t()]

Returns a list of all categories recognised by DeepLabV3 MobileNetV3

load(options \\ [])

@spec load([ExVision.Model.Definition.Ortex.load_option_t()]) ::
  {:ok, t()} | {:error, reason :: atom()}

Creates the model instance

load!(opts \\ [])

@spec load!(keyword()) :: t()

Same as load/1, but raises and error on failure.

run(model, input)

@spec run(t(), ExVision.Model.input_t()) :: output_t() | [output_t()]

Immediatelly applies the model to the given input, in the scope of the current process.