A YOLOv11 model, trained on the Roboflow ALPR dataset for license plate recognition, was converted to TFLite format. When using Ultralytics’ inference pipeline, both the original .pt and the converted .tflite models achieve 100% accuracy in detecting Persian numbers. However, when the same TFLite model is used directly with TensorFlow, it fails to produce correct detections, with output data either incorrect or missing. The model was trained with images sized at 640×640 pixels and a batch size of 1. The discrepancy in performance between the two platforms raises questions about necessary preprocessing or post-processing steps for TensorFlow inference. The model can be tested using a provided download link.
To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behavior or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions.
Functional
Always active
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
Preferences
The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
Statistics
The technical storage or access that is used exclusively for statistical purposes.The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
Marketing
The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.
