We show how machine learning techniques can be applied for the classification of topological phases in finite leaky photonic lattices using limited measurement data. We propose an approach based solely on a single real-space bulk intensity image. thus exempt from complicated phase retrieval procedures. In particular. https://www.roneverhart.com/Western-Digital-Re-WD6001FSYZ-6TB-7-2K-RPM-SATA-6Gb-s-128MB-3-5-Hard-Drive/