Implemented a workaround to deal with the problem that padding with the minimum value causes the output error of MaxPool2D to be maximized only when quantizing with INT8 quantization. #444

[PINTO0309]

1. Content and background

• MaxPool

  • Implemented a workaround to deal with the problem that padding with the minimum value causes the output error of MaxPool2D to be maximized only when quantizing with INT8 quantization. [OSNet] int8 tflite model - catastrophic accuracy degradation  #444

    

    Float32 model outputs flattened shape: (512,)
    Int8 model outputs flattened shape: (512,)
    Euclidean Distance: 2.0942165851593018
    

2. Summary of corrections

3. Before/After (If there is an operating log that can be used as a reference)

4. Issue number (only if there is a related issue)

• [OSNet] int8 tflite model - catastrophic accuracy degradation #444