I built a local/offline prediction app using the ONNX weights and the inference Python library but the predictions are significantly different from those on the “Visualize” page. Example: Red = my app [Screenshot 2024-03-18 at 18.14.14] Anything I’m doing wrong? Code of the prediction app: imp…

@Emily in that thread you say that users should tile before sending to the inference server/model. I wanted to understand how tiling is done by Roboflow and it looks like it is done server-side. Could you please refer to the piece of code that does the tiling and un-tiling? Or is this proprietary co…

Hey @Jonas_Haag Are you using tiling as a preprocessing step while creating your dataset? If so, you can use the Inference Slicer utility from Supervision to replicate tiling. We also have this blog post on using SAHI (which is a tiling based inference technique)

Predictions with `inference` library are different from Visualize page

🤝 Community Help

Jonas_Haag March 18, 2024, 5:50pm 2

The answer might be in this post Locally depoloyed model gives different result from the hosted one - #2 by camerayuhang

Topic		Replies	Views
Locally depoloyed model gives different result from the hosted one 🤝 Community Help	7	599	December 18, 2023
Prediction on https://app.roboflow.com/ under "Try this Model" differs from when using Serverless Hosted API 🛠️ Feature Reqs bugs	3	136	March 20, 2025
Bounding box misplaced when inferencing with api 🤝 Community Help	3	70	March 18, 2025
predictions 🤝 Community Help	1	178	November 16, 2022
Can't get inference.js to work 🤝 Community Help	18	348	November 28, 2024

Predictions with `inference` library are different from Visualize page

Related topics