We are trying to import a mobilenetv2 tflite model to the TDA4VM. We tried using a trained and quantized tflite model but the results were very unsatisfactory. We narrowed down the problem to the quantization after we followed the Troubleshooting recommendations in this link. The weights in the "*_paramDebug.csv" file had too big discrepancies. We have tried both using the example configs without changing them and following the recommended steps in this link. The best performance in terms of accuracy that we achieved was without any calibration, which was ~10% less than tflite model. We also tried using floating point tflite model, but the results were even worse.
We also tried importing it with Edge-AI Benchmark Tool and there the drop in the accuracy was ~40%.
We also tried to import efficientnet lite models directly downloaded from TF Hub and use the configs that were present in the ti-processor-sdk-rtos-j721e-evm-08_00_00_12/tidl_j721e_08_06_00_10/.. but the results were again unsatisfactory.
Could you please investigate the quantization in the Importer as we suspect there might be a problem with it?