Manually add test images?

• image-tools

  10 81 0.0 Python

  Tools for creating image-based datasets for machine learning (by lobe)

  

We don't have a way of manually adding test images at the moment, but Lobe will keep an 80% train / 20% test split randomly from the data you import. It should be having 4 test images if you have 20 overall. If you want to use an outside folder as a test set of images, check out the image-tools repo we have that can help run an exported Lobe model and organize images into a folder structure based on the predicted label: https://github.com/lobe/image-tools#folder-of-images

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project