quantization parameters and convert model step by step (AIV-393) about esp-dl HOT 6 CLOSED

Hi,

the value in the dictionary stands for scale for now, which means int_value = scale * fp_value,
the output_exponent value in config json file shoule be -log2(scale)
will export to exponent value in the next version

For your own model, the steps are mostly correct:
1.prepare a float32 model, and convet to onnx model
2. you can basically follow the code in example.py, some modification is needed

model_path = 'mnist_model_example.onnx'

• change to your own onnx model path

calib_dataset = test_images[0:5000:50]

• the calibration dataset should be selected from your own validation dataset

3/4. get the out_exponent from -log2(scale) and then setp3, step4 as you said
the step3/4 will be supported in the quantization tool as well for convenience, but it's still testing, you can experiment it by calling export_coefficient_to_cpp(model, pickle_file_path, target_chip, output_path, name). a new version will be released soon.

If there is any question or suggestion, please feel free to let us know

from esp-dl.

@Auroragan
Hi,
In which dynamic library can I locate this function(export_coefficient_to_cpp), and when will the next version be?

from esp-dl.

Hi, @PureHing

Please check the latest master branch.

the function is in calibrator, you can refer to the code in example.py:
calib.export_coefficient_to_cpp(model_proto, pickle_file_path, 'esp32s3', '.', 'test_mnist', True)

from esp-dl.

@Auroragan Exporting finish, the output files are: ./test_mnist.cpp, ./test_mnist.hpp,and Does the .npy files is necessary for convert.py?

from esp-dl.

the purpose of convert.py is to convert coefficients which are in .npy files to .cpp and .hpp, which is the same as export_coefficient_to_cpp function

if you can use export_coefficient_to_cpp to convert, you don't need to use convert.py anymore

from esp-dl.

Thanks much

from esp-dl.