This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: Why model result are different

Part Number: TDA4VM

Tool/software:

Recently, I use OCR model to recognize character. Use the same model, use crop test demo which is from TI SDK. Run the demo , and get the model result, save 5 frames, but the result are different.

I attached the demo, wish to give the method to solve this.

OCR-model-error-test-demo.rar