Package: animl 3.2.0

Kyra Swanson

animl: A Collection of ML Tools for Conservation Research

Functions required to classify subjects within camera trap field data. The package can handle both images and videos. The authors recommend a two-step approach using Microsoft's 'MegaDector' model and then a second model trained on the classes of interest.

Authors:Kyra Swanson [aut, cre], Mathias Tobler [aut]

animl_3.2.0.tar.gz
animl_3.2.0.tar.gz(r-4.7-any)animl_3.2.0.tar.gz(r-4.6-any)
animl_3.2.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
card.svg |card.png
animl/json (API)

# Install 'animl' in R:
install.packages('animl', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

On CRAN:

Conda:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

1.70 score 9 scripts 216 downloads 46 exports 13 dependencies

Last updated from:509b7812c0. Checks:4 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-x86_64OK106
source / vignettesOK151
linux-release-x86_64OK100
wasm-releaseOK101

Exports:animl_installaniml_install_instructionsbuild_file_manifestcheck_pythonclassifycompute_batched_distance_matrixcompute_distance_matrixcosine_distancecreate_pyenvdelete_pyenvdetectdownload_modeleuclidean_squared_distanceexport_camtrapRexport_cocoexport_foldersexport_megadetectorexport_timelapseextract_framesextract_miew_embeddingsget_animalsget_emptyget_frame_as_imagelist_modelsload_animlload_class_listload_classifierload_dataload_detectorload_jsonload_miewparse_detectionsplot_all_bounding_boxesplot_boxremove_diagonalremove_linksave_classifiersave_jsonsequence_classificationsingle_classificationtest_maintrain_maintrain_val_testupdate_animl_pyupdate_labels_from_foldersWorkingDirectory

Dependencies:herejsonlitelatticeMatrixpbapplypngrappdirsRcppRcppTOMLreticulaterlangrprojrootwithr

Readme and manuals

Help Manual

Help pageTopics
Load animl-py if availableaniml_install
Installation Instructions for animl-r Python dependenciesaniml_install_instructions
File Management Modulebuild_file_manifest
Check for files existence and prompt user if they want to loadcheck_file
Check that the python version is compatible with the current version of animl-pycheck_python
Infer Species for Given Detectionsclassify
Computes the distance matrix in a batched manner to save memory.compute_batched_distance_matrix
A wrapper function for computing distance matrix.compute_distance_matrix
Computes cosine distance of two sets of vectorscosine_distance
Install python if necessary and create the environment animl_envcreate_pyenv
Delete the animl_env environmentdelete_pyenv
Apply MegaDetector to a Given Batch of Imagesdetect
Download specified model to the given directory.download_model
Computes euclidean squared distance of two sets of vectorseuclidean_squared_distance
Export data into sorted folders organized by stationexport_camtrapR
Converts the .csv file to a COCO-formatted .json file.export_coco
Create SymLink Directories and Sort Classified Imagesexport_folders
Converts the .csv file to the MD-formatted .json file.export_megadetector
Converts the Manifests to a csv file that contains columns needed for TimeLapse conversion in later stepexport_timelapse
Extract frames from video for classificationextract_frames
Extract Embeddings from MiewIDextract_miew_embeddings
Return a dataframe of only MD animalsget_animals
Return MD empty, vehicle and human images in a dataframeget_empty
Given a video path, return a specific frame as an RGB imageget_frame_as_image
List available models for download.list_models
Load animl-py if availableload_animl
Load class list .csv fileload_class_list
Load a Classifier Model and Class_listload_classifier
Load .csv or .Rdata fileload_data
Load an Object Detectorload_detector
Load data from a JSON file.load_json
Load MiewID modelload_miew
Parse MD results into a simple dataframeparse_detections
Plot all bounding boxes in a manifestplot_all_bounding_boxes
Plot bounding boxes on image from md resultsplot_box
Removes the diagonal elements from a square matrix.remove_diagonal
Remove Sorted Linksremove_link
Save model state weightssave_classifier
Save Data to Given Filesave_data
Save data to a JSON file.save_json
Leverage sequences to classify imagessequence_classification
Get Maximum likelihood label for each Detectionsingle_classification
Test a model with a Config filetest_main
Model Trainingtrain_main
Splits the manifest into training validation and test datasets for trainingtrain_val_test
Update animl-py version for the given environmentupdate_animl_py
Udate Results from File Browserupdate_labels_from_folders
Set Working Directory and Save File Global VariablesWorkingDirectory