Guides

Let Kaimei explain a model it cannot run itself by calling an HTTPS endpoint you host.

Store attributions you already compute, with TreeSHAP or anything else, next to the predictions they explain.

Log production traffic, catch input drift on a schedule and explain the predictions that look wrong.

Ship a retrained model as a new version, compare what the two learned, and retire the old one.

Upload a convolutional network, explain photos with Grad-CAM, occlusion and LIME, and see what each layer responds to.

Upload networks with thousands of layers and hundreds of millions of parameters, and work with them block by block.

Run the Kaimei API on your own infrastructure, against SQLite on a laptop or Postgres for a team.