single_classification

Get Maximum likelihood label for each Detection

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.

Kyra Swanson

animl

A Collection of ML Tools for Conservation Research

Mathias Tobler

single_classification function

<dl><dt>animals</dt>
<dd>manifest of animal detections</dd>
<dt>empty</dt>
<dd>manifest of md human, vehicle and empty images</dd>
<dt>predictions_raw</dt>
<dd>softmaxed likelihoods from predict_species</dd>
<dt>class_list</dt>
<dd>list of class labels</dd>
<dt>best</dt>
<dd>whether to return one prediction per file</dd></dl>

Arguments

Get Maximum likelihood label for each Detection — single_classification

<dl>

<dt>animals</dt>
<dd>manifest of animal detections</dd>


<dt>empty</dt>
<dd>manifest of md human, vehicle and empty images</dd>


<dt>predictions_raw</dt>
<dd>softmaxed likelihoods from predict_species</dd>


<dt>class_list</dt>
<dd>list of class labels</dd>


<dt>best</dt>
<dd>whether to return one prediction per file</dd>

</dl>

single_classification: Get Maximum likelihood label for each Detection

Description

Usage

Value

Arguments

Examples