View Source ExVision.ObjectDetection.FasterRCNN_ResNet50_FPN (Ex Vision v0.4.0)

FasterRCNN object detector with ResNet50 backbone and FPN detection head, exported from torchvision.

Summary

Types

Type describing all categories recognised by FasterRCNN ResNet50 FPN

A type describing output of run/2 as a list of a bounding boxes.

t()

An instance of the Elixir.ExVision.ObjectDetection.FasterRCNN_ResNet50_FPN

Functions

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

Returns a list of all categories recognised by FasterRCNN ResNet50 FPN

Creates the model instance

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

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

Types

@type category_t() ::
  :__background__
  | :person
  | :bicycle
  | :car
  | :motorcycle
  | :airplane
  | :bus
  | :train
  | :truck
  | :boat
  | :traffic_light
  | :fire_hydrant
  | :"n/a"
  | :stop_sign
  | :parking_meter
  | :bench
  | :bird
  | :cat
  | :dog
  | :horse
  | :sheep
  | :cow
  | :elephant
  | :bear
  | :zebra
  | :giraffe
  | :backpack
  | :umbrella
  | :handbag
  | :tie
  | :suitcase
  | :frisbee
  | :skis
  | :snowboard
  | :sports_ball
  | :kite
  | :baseball_bat
  | :baseball_glove
  | :skateboard
  | :surfboard
  | :tennis_racket
  | :bottle
  | :wine_glass
  | :cup
  | :fork
  | :knife
  | :spoon
  | :bowl
  | :banana
  | :apple
  | :sandwich
  | :orange
  | :broccoli
  | :carrot
  | :hot_dog
  | :pizza
  | :donut
  | :cake
  | :chair
  | :couch
  | :potted_plant
  | :bed
  | :dining_table
  | :toilet
  | :tv
  | :laptop
  | :mouse
  | :remote
  | :keyboard
  | :cell_phone
  | :microwave
  | :oven
  | :toaster
  | :sink
  | :refrigerator
  | :book
  | :clock
  | :vase
  | :scissors
  | :teddy_bear
  | :hair_drier
  | :toothbrush

Type describing all categories recognised by FasterRCNN ResNet50 FPN

@type output_t() :: [ExVision.Types.BBox.t()]

A type describing output of run/2 as a list of a bounding boxes.

Each bounding box describes the location of the object indicated by the label. It also provides the score field marking the probability of the prediction. Bounding boxes with very low scores should most likely be ignored.

@opaque t()

An instance of the Elixir.ExVision.ObjectDetection.FasterRCNN_ResNet50_FPN

Functions

Link to this function

batched_run(name \\ __MODULE__, input)

View Source
@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.

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

Returns a list of all categories recognised by FasterRCNN ResNet50 FPN

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

Creates the model instance

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

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

@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.