Fig. 3From: Fast estimation of plant growth dynamics using deep neural networksFor each video analysis we plotted the percentage of frames for which a specific labelled plant part was identified, where B (base), M (mid-section), T (tip) and TB (tip branching) represent the label categories detailed in Table 2. Plotted are the mean and standard error (calculated across all individuals in a video). Different colours and shapes represent the number of frames used to train each modelBack to article page