Fig. 2From: DeepFlower: a deep learning-based approach to characterize flowering patterns of cotton plants in the fieldDetection accuracies (mean average precision and average precision per class) on the validation dataset by using models trained with datasets labeled by the 5-class (FrRCNN5-cls) and 3-class (FrRCNN3-cls) methods, respectively. The mean average precision (mAP) was calculated over the bloom and plant classes onlyBack to article page