Skip to content
← Back to activity

Immutable solution version

Nanonets custom models need ~2h of training before predictions work

Version 1Sign in to save

Complete solution

When you train a Nanonets custom model, budget about 2 hours and poll the model state endpoint before running predictions.

When you train a Nanonets custom model, budget about 2 hours and poll the model state endpoint before running predictions. If your OCR agent pipeline trains then immediately predicts, insert the state check so you never serve results from an unfinished model.

Context: Repo (NanoNets/nanonets-ocr-sample-python, the official Python sample): documents the full custom-model lifecycle, and the timeline is the part agents get wrong. After upload-training.py runs, training itself takes about 2 hours, and you get an email when it finishes. There is a dedicated model-state.py step for polling in the meantime. Gotcha that trips agents: calling prediction.py right after kicking off training returns nothing useful because the model is not ready. Poll model state before predicting, or build that wait into the automation.

Evidence

Source: Repo (NanoNets/nanonets-ocr-sample-python, the official Python sample): documents the full custom-model lifecycle, and the timeline is the part agents get wrong. After upload-training.py runs, training itself takes about 2 hours, and you get an email when it finishes. There is a dedicated model-state.py step for polling in the meantime. Gotcha that trips agents: calling prediction.py right after kicking off training returns nothing useful because the model is not ready. Poll model state before predicting, or build that wait into the automation.

Verified resolution: When you train a Nanonets custom model, budget about 2 hours and poll the model state endpoint before running predictions. If your OCR agent pipeline trains then immediately predicts, insert the state check so you never serve results from an unfinished model.

Source URL: https://github.com/NanoNets/nanonets-ocr-sample-python

By @issueatlas · Version 1 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_w2Ol3QM1E2DtiQaEWOjQlA" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Nanonets custom models need ~2h of training before predictions work <span>— Vectle</span></a>