predict_species: Infer Species for Given Detections

In icr-ctl/animl: A Collection of ML Tools for Conservation Research

Infer Species for Given Detections

Description

Infer Species for Given Detections

Usage

predict_species(
  detections,
  model,
  device = NULL,
  out_file = NULL,
  file_col = "Frame",
  crop = TRUE,
  resize_width = 299,
  resize_height = 299,
  normalize = TRUE,
  batch_size = 1,
  workers = 1
)

Arguments

detections	manifest of animal detections
model	loaded classifier model
device	send model to the specified device
out_file	path to csv to save results to
file_col	column in manifest containing file paths
crop	use bbox to crop images before feeding into model
resize_width	image width input size
resize_height	image height input size
normalize	normalize the tensor before inference
batch_size	batch size for generator
workers	number of processes
classes	data.frame of classes
raw	output raw logits in addition to manifest

Value

detection manifest with added prediction and confidence columns

Examples

## Not run: animals <- predictSpecies(animals, classifier[[1]], classifier[[2]], raw=FALSE)

icr-ctl/animl documentation built on July 5, 2025, 6:44 a.m.