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.
parkNet3dEcoTv_post_ptq_0_tidl_net.binparkNet3dEcoTv_post_ptq_0_tidl_io_1.binpost_input_116.bin
hello,
we found the model output is different between X86 simulation and product board. we share the model and input. we use tidl 0902 to quantize and convert model. I hope ti can help us to fix this problem.
best wishes
Can you please provide the configuration you used for the import and inference, input data (maybe it is post_input_116.bin?), and the original model? I am unable to determine what is different between inference on the board and device with only the .bin files.