A PTQ tflite model fails to pass benchmark test

My use case:
Apply post training quantization to a pth model and convert to tflite. The generated tflite model fails to pass benchmark test with following error message:
STARTING!
Log parameter values verbosely: [0]
Graph: [out/ptq_model.tflite]
Loaded model out/ptq_model.tflite
ERROR: tensorflow/lite/kernels/concatenation.cc:179 t->params.scale != output->params.scale (3 != -657359264)
ERROR: Node number 154 (CONCATENATION) failed to prepare.
Failed to allocate tensors!
Benchmarking failed.

Pls refer to the attachment. Thanks.
[test.zip](https://github.com/alibaba/TinyNeuralNetwork/files/9088693/test.zip)

Start by unpacking test.zip and reproducing the benchmark failure with out/ptq_model.tflite. Trace the post-training quantization and model conversion path to investigate the CONCATENATION scale mismatch; the issue is done when the generated TFLite model passes the benchmark test without the tensor-allocation error.

Written by the indexing model from the issue text.