Table 4 in Identification of morphologically cryptic species with computer vision models: wall lizards (Squamata: Lacertidae: Podarcis) as a case study

NIAID Data Ecosystem2026-05-02 收录

下载链接：

https://zenodo.org/record/15133842

下载链接

链接失效反馈

官方服务：

资源简介：

Table 4. Evaluation of the three tested architectures and their combined predictions in the four datasets for the nineclass experiment. Models with the highest accuracy are highlighted in bold SexViewMetricInception V3ResNet 50Inception ResNetV2Combined predictionsMalesDorsalAccuracy0.8490.8320.8530.886F1 macro0.8260.8060.8290.866Head lateralAccuracy0.8320.8400.8280.876F1 macro0.8110.8170.8070.854FemalesDorsalAccuracy0.7990.7830.8190.854F1 macro0.7720.7580.7930.827Head lateralAccuracy0.7830.7630.8040.830F1 macro0.7440.7270.7750.802

创建时间：

2025-04-05