K230 nncase开发指南

class CompileOptions:
    benchmark_only: bool
    dump_asm: bool
    dump_dir: str
    dump_ir: bool
    swapRB: bool
    input_range: List[float]
    input_shape: List[int]
    input_type: str
    is_fpga: bool
    mean: List[float]
    std: List[float]
    output_type: str
    preprocess: bool
    quant_type: str
    target: str
    w_quant_type: str
    use_mse_quant_w: bool
    input_layout: str
    output_layout: str
    letterbox_value: float
    tcu_num: int

    def __init__(self) -> None:
        self.benchmark_only = False
        self.dump_asm = True
        self.dump_dir = "tmp"
        self.dump_ir = False
        self.is_fpga = False
        self.quant_type = "uint8"
        self.target = "cpu"
        self.w_quant_type = "uint8"
        self.use_mse_quant_w = True
        self.tcu_num = 0

        self.preprocess = False
        self.swapRB = False
        self.input_range = []
        self.input_shape = []
        self.input_type = "float32"
        self.mean = [0, 0, 0]
        self.std = [1, 1, 1]
        self.input_layout = ""
        self.output_layout = ""
        self.letterbox_value = 0

# compile_options                                                                
compile_options = nncase.CompileOptions()                                           
compile_options.target = args.target                                                
compile_options.preprocess = True                                                   
compile_options.swapRB = False                                                      
compile_options.input_shape = input_shape                                           
compile_options.input_type = 'uint8'                                                
compile_options.input_range = [0, 255]                                              
compile_options.mean = [127.5, 127.5, 127.5]                                        
compile_options.std = [127.5, 127.5, 127.5]                                         
compile_options.input_layout = 'NCHW'                                               
compile_options.dump_ir = True                                                      
compile_options.dump_asm = True                                                     
compile_options.dump_dir = dump_dir                                                 

class ImportOptions:
    def __init__(self) -> None:
        pass

#import_options
import_options = nncase.ImportOptions()

class PTQTensorOptions:
    calibrate_method: str
    input_mean: float
    input_std: float
    samples_count: int
    quant_type: str
    w_quant_type: str
    finetune_weights_method: str
    use_mix_quant: bool
    quant_scheme: str
    export_quant_scheme: bool
    export_weight_range_by_channel: bool
    cali_data: List[RuntimeTensor]

    def __init__(self) -> None:
        self.calibrate_method: str = "Kld"
        self.input_mean: float = 0.5
        self.input_std: float = 0.5
        self.samples_count: int = 5
        self.quant_type: str = "uint8"
        self.w_quant_type: str = "uint8"
        self.finetune_weights_method: str = "NoFineTuneWeights"
        self.use_mix_quant: bool = False
        self.quant_scheme: str = ""
        self.export_quant_scheme: bool = False
        self.export_weight_range_by_channel: bool = False
        self.cali_data: List[RuntimeTensor] = []

    def set_tensor_data(self, data: List[List[np.ndarray]]) -> None:
        reshape_data = list(map(list, zip(*data)))
        self.cali_data = [RuntimeTensor.from_numpy(
            d) for d in itertools.chain.from_iterable(reshape_data)]

# ptq_options
ptq_options = nncase.PTQTensorOptions()
ptq_options.samples_count = 6
ptq_options.set_tensor_data(generate_data(input_shape, ptq_options.samples_count, args.dataset))
compiler.use_ptq(ptq_options)

    def set_tensor_data(self, data: List[List[np.ndarray]]) -> None:
        reshape_data = list(map(list, zip(*data)))
        self.cali_data = [RuntimeTensor.from_numpy(
            d) for d in itertools.chain.from_iterable(reshape_data)]

# ptq_options
ptq_options = nncase.PTQTensorOptions()
ptq_options.samples_count = 6
ptq_options.set_tensor_data(generate_data(input_shape, ptq_options.samples_count, args.dataset))
compiler.use_ptq(ptq_options)

class Compiler:
    _target: _nncase.Target
    _session: _nncase.CompileSession
    _compiler: _nncase.Compiler
    _compile_options: _nncase.CompileOptions
    _quantize_options: _nncase.QuantizeOptions
    _module: IRModule

def import_tflite(self, model_content: bytes, options: ImportOptions) -> None:
    self._compile_options.input_format = "tflite"
    self._import_module(model_content)

model_content = read_model_file(model)
compiler.import_tflite(model_content, import_options)

def import_onnx(self, model_content: bytes, options: ImportOptions) -> None:
    self._compile_options.input_format = "onnx"
    self._import_module(model_content)

model_content = read_model_file(model)
compiler.import_onnx(model_content, import_options)

kmodel = compiler.gencode_tobytes()
with open(os.path.join(infer_dir, 'test.kmodel'), 'wb') as f:
    f.write(kmodel)

import os
import argparse
import numpy as np
from PIL import Image
import nncase

def read_model_file(model_file):
    with open(model_file, 'rb') as f:
        model_content = f.read()
    return model_content

def generate_data(shape, batch, calib_dir):
    img_paths = [os.path.join(calib_dir, p) for p in os.listdir(calib_dir)]
    data = []
    for i in range(batch):
        assert i < len(img_paths), "calibration images not enough."
        img_data = Image.open(img_paths[i]).convert('RGB')
        img_data = img_data.resize((shape[3], shape[2]), Image.BILINEAR)
        img_data = np.asarray(img_data, dtype=np.uint8)
        img_data = np.transpose(img_data, (2, 0, 1))
        data.append([img_data[np.newaxis, ...]])
    return data

def main():
    parser = argparse.ArgumentParser(prog="nncase")
    parser.add_argument("--target", type=str, help='target to run')
    parser.add_argument("--model", type=str, help='model file')
    parser.add_argument("--dataset", type=str, help='calibration_dataset')
    args = parser.parse_args()

    input_shape = [1, 3, 224, 224]
    dump_dir = 'tmp/mbv2_tflite'

    # compile_options
    compile_options = nncase.CompileOptions()
    compile_options.target = args.target
    compile_options.preprocess = True
    compile_options.swapRB = False
    compile_options.input_shape = input_shape
    compile_options.input_type = 'uint8'
    compile_options.input_range = [0, 255]
    compile_options.mean = [127.5, 127.5, 127.5]
    compile_options.std = [127.5, 127.5, 127.5]
    compile_options.input_layout = 'NCHW'
    compile_options.dump_ir = True
    compile_options.dump_asm = True
    compile_options.dump_dir = dump_dir

    # compiler
    compiler = nncase.Compiler(compile_options)

    # import
    model_content = read_model_file(args.model)
    import_options = nncase.ImportOptions()
    compiler.import_tflite(model_content, import_options)

    # ptq_options
    ptq_options = nncase.PTQTensorOptions()
    ptq_options.samples_count = 6
    ptq_options.set_tensor_data(generate_data(input_shape, ptq_options.samples_count, args.dataset))
    compiler.use_ptq(ptq_options)

    # compile
    compiler.compile()

    # kmodel
    kmodel = compiler.gencode_tobytes()
    with open(os.path.join(dump_dir, 'test.kmodel'), 'wb') as f:
        f.write(kmodel)

if __name__ == '__main__':
    main()

root@c285a41a7243:/mnt/# cd src/big/nncase/examples
root@c285a41a7243:/mnt/src/big/nncase/examples# python3 ./scripts/mbv2_tflite.py --target k230 --model models/mbv2.tflite --dataset calibration_dataset

import os
import argparse
import numpy as np
from PIL import Image
import onnxsim
import onnx
import nncase

def parse_model_input_output(model_file):
    onnx_model = onnx.load(model_file)
    input_all = [node.name for node in onnx_model.graph.input]
    input_initializer = [node.name for node in onnx_model.graph.initializer]
    input_names = list(set(input_all) - set(input_initializer))
    input_tensors = [
        node for node in onnx_model.graph.input if node.name in input_names]

    # input
    inputs = []
    for _, e in enumerate(input_tensors):
        onnx_type = e.type.tensor_type
        input_dict = {}
        input_dict['name'] = e.name
        input_dict['dtype'] = onnx.mapping.TENSOR_TYPE_TO_NP_TYPE[onnx_type.elem_type]
        input_dict['shape'] = [(i.dim_value if i.dim_value != 0 else d) for i, d in zip(
            onnx_type.shape.dim, [1, 3, 224, 224])]
        inputs.append(input_dict)

    return onnx_model, inputs


def onnx_simplify(model_file, dump_dir):
    onnx_model, inputs = parse_model_input_output(model_file)
    onnx_model = onnx.shape_inference.infer_shapes(onnx_model)
    input_shapes = {}
    for input in inputs:
        input_shapes[input['name']] = input['shape']

    onnx_model, check = onnxsim.simplify(onnx_model, input_shapes=input_shapes)
    assert check, "Simplified ONNX model could not be validated"

    model_file = os.path.join(dump_dir, 'simplified.onnx')
    onnx.save_model(onnx_model, model_file)
    return model_file


def read_model_file(model_file):
    with open(model_file, 'rb') as f:
        model_content = f.read()
    return model_content

def generate_data_ramdom(shape, batch):
    data = []
    for i in range(batch):
        data.append([np.random.randint(0, 256, shape).astype(np.uint8)])
    return data


def generate_data(shape, batch, calib_dir):
    img_paths = [os.path.join(calib_dir, p) for p in os.listdir(calib_dir)]
    data = []
    for i in range(batch):
        assert i < len(img_paths), "calibration images not enough."
        img_data = Image.open(img_paths[i]).convert('RGB')
        img_data = img_data.resize((shape[3], shape[2]), Image.BILINEAR)
        img_data = np.asarray(img_data, dtype=np.uint8)
        img_data = np.transpose(img_data, (2, 0, 1))
        data.append([img_data[np.newaxis, ...]])
    return data

def main():
    parser = argparse.ArgumentParser(prog="nncase")
    parser.add_argument("--target", type=str, help='target to run')
    parser.add_argument("--model", type=str, help='model file')
    parser.add_argument("--dataset", type=str, help='calibration_dataset')

    args = parser.parse_args()

    input_shape = [1, 3, 320, 320]

    dump_dir = 'tmp/yolov5s_onnx'
    if not os.path.exists(dump_dir):
        os.makedirs(dump_dir)

    # onnx simplify
    model_file = onnx_simplify(args.model, dump_dir)

    # compile_options
    compile_options = nncase.CompileOptions()
    compile_options.target = args.target
    compile_options.preprocess = True
    compile_options.swapRB = False
    compile_options.input_shape = input_shape
    compile_options.input_type = 'uint8'
    compile_options.input_range = [0, 255]
    compile_options.mean = [0, 0, 0]
    compile_options.std = [255, 255, 255]
    compile_options.input_layout = 'NCHW'
    compile_options.output_layout = 'NCHW'
    compile_options.dump_ir = True
    compile_options.dump_asm = True
    compile_options.dump_dir = dump_dir

    # compiler
    compiler = nncase.Compiler(compile_options)

    # import
    model_content = read_model_file(model_file)
    import_options = nncase.ImportOptions()
    compiler.import_onnx(model_content, import_options)

    # ptq_options
    ptq_options = nncase.PTQTensorOptions()
    ptq_options.samples_count = 6
    ptq_options.set_tensor_data(generate_data(input_shape, ptq_options.samples_count, args.dataset))
    compiler.use_ptq(ptq_options)

    # compile
    compiler.compile()

    # kmodel
    kmodel = compiler.gencode_tobytes()
    with open(os.path.join(dump_dir, 'test.kmodel'), 'wb') as f:
        f.write(kmodel)

if __name__ == '__main__':
    main()

root@c285a41a7243:/mnt/# cd src/big/nncase/examples
root@c285a41a7243: /mnt/src/big/nncase/examples # python3 ./scripts/yolov5s_onnx.py --target k230 --model models/yolov5s.onnx --dataset calibration_dataset

py::class_<memory_range>(m, "MemoryRange")
    .def_readwrite("location", &memory_range::memory_location)
    .def_property(
        "dtype", [](const memory_range &range) { return to_dtype(range.datatype); },
        [](memory_range &range, py::object dtype) { range.datatype = from_dtype(py::dtype::from_args(dtype)); })
    .def_readwrite("start", &memory_range::start)
    .def_readwrite("size", &memory_range::size);

py::class_<runtime_tensor>(m, "RuntimeTensor")
    .def_static("from_numpy", [](py::array arr) {
        auto src_buffer = arr.request();
        auto datatype = from_dtype(arr.dtype());
        auto tensor = host_runtime_tensor::create(
            datatype,
            to_rt_shape(src_buffer.shape),
            to_rt_strides(src_buffer.itemsize, src_buffer.strides),
            gsl::make_span(reinterpret_cast<gsl::byte *>(src_buffer.ptr), src_buffer.size * src_buffer.itemsize),
            [=](gsl::byte *) { arr.dec_ref(); })
                          .unwrap_or_throw();
        arr.inc_ref();
        return tensor;
    })
    .def("copy_to", [](runtime_tensor &from, runtime_tensor &to) {
        from.copy_to(to).unwrap_or_throw();
    })
    .def("to_numpy", [](runtime_tensor &tensor) {
        auto host = tensor.as_host().unwrap_or_throw();
        auto src_map = std::move(hrt::map(host, hrt::map_read).unwrap_or_throw());
        auto src_buffer = src_map.buffer();
        return py::array(
            to_dtype(tensor.datatype()),
            tensor.shape(),
            to_py_strides(runtime::get_bytes(tensor.datatype()), tensor.strides()),
            src_buffer.data());
    })
    .def_property_readonly("dtype", [](runtime_tensor &tensor) {
        return to_dtype(tensor.datatype());
    })
    .def_property_readonly("shape", [](runtime_tensor &tensor) {
        return to_py_shape(tensor.shape());
    });

py::class_<interpreter>(m, "Simulator")
    .def(py::init())
    .def("load_model", [](interpreter &interp, gsl::span<const gsl::byte> buffer) { interp.load_model(buffer).unwrap_or_throw(); })
    .def_property_readonly("inputs_size", &interpreter::inputs_size)
    .def_property_readonly("outputs_size", &interpreter::outputs_size)
    .def("get_input_desc", &interpreter::input_desc)
    .def("get_output_desc", &interpreter::output_desc)
    .def("get_input_tensor", [](interpreter &interp, size_t index) { return interp.input_tensor(index).unwrap_or_throw(); })
    .def("set_input_tensor", [](interpreter &interp, size_t index, runtime_tensor tensor) { return interp.input_tensor(index, tensor).unwrap_or_throw(); })
    .def("get_output_tensor", [](interpreter &interp, size_t index) { return interp.output_tensor(index).unwrap_or_throw(); })
    .def("set_output_tensor", [](interpreter &interp, size_t index, runtime_tensor tensor) { return interp.output_tensor(index, tensor).unwrap_or_throw(); })
    .def("run", [](interpreter &interp) { interp.run().unwrap_or_throw(); });

import os
import copy
import argparse
import numpy as np
import onnx
import onnxruntime as ort
import nncase

def read_model_file(model_file):
    with open(model_file, 'rb') as f:
        model_content = f.read()
    return model_content

def cosine(gt, pred):
    return (gt @ pred) / (np.linalg.norm(gt, 2) * np.linalg.norm(pred, 2))

def main():
    parser = argparse.ArgumentParser(prog="nncase")
    parser.add_argument("--model", type=str, help='original model file')
    parser.add_argument("--model_input", type=str, help='input bin file for original model')
    parser.add_argument("--kmodel", type=str, help='kmodel file')
    parser.add_argument("--kmodel_input", type=str, help='input bin file for kmodel')
    args = parser.parse_args()

    # cpu inference
    ort_session = ort.InferenceSession(args.model)
    output_names = []
    model_outputs = ort_session.get_outputs()
    for i in range(len(model_outputs)):
        output_names.append(model_outputs[i].name)
    model_input = ort_session.get_inputs()[0]
    model_input_name = model_input.name
    model_input_type = np.float32
    model_input_shape = model_input.shape
    model_input_data = np.fromfile(args.model_input, model_input_type).reshape(model_input_shape)
    cpu_results = []
    cpu_results = ort_session.run(output_names, { model_input_name : model_input_data })

    # create simulator
    sim = nncase.Simulator()

    # read kmodel
    kmodel = read_model_file(args.kmodel)

    # load kmodel
    sim.load_model(kmodel)

    # read input.bin
    # input_tensor=sim.get_input_tensor(0).to_numpy()
    dtype = sim.get_input_desc(0).dtype
    input = np.fromfile(args.kmodel_input, dtype).reshape([1, 3, 320, 320])

    # set input for simulator
    sim.set_input_tensor(0, nncase.RuntimeTensor.from_numpy(input))

    # simulator inference
    nncase_results = []
    sim.run()
    for i in range(sim.outputs_size):
        nncase_result = sim.get_output_tensor(i).to_numpy()
        nncase_results.append(copy.deepcopy(nncase_result))

    # compare
    for i in range(sim.outputs_size):
        cos = cosine(np.reshape(nncase_results[i], (-1)), np.reshape(cpu_results[i], (-1)))
        print('output {0} cosine similarity : {1}'.format(i, cos))

if __name__ == '__main__':
    main()

root@5f718e19f8a7:/mnt/# cd src/big/nncase/examples
root@5f718e19f8a7:/mnt/src/big/nncase/examples # export PATH=$PATH:/usr/local/lib/python3.8/dist-packages/
root@5f718e19f8a7:/mnt/src/big/nncase/examples # python3 scripts/yolov5s_onnx_simu.py --model models/yolov5s.onnx --model_input object_detect/data/input_fp32.bin --kmodel tmp/yolov5s_onnx/test.kmodel --kmodel_input object_detect/data/input_uint8.bin

output 0 cosine similarity : 0.9997244477272034
output 1 cosine similarity : 0.999757707118988
output 2 cosine similarity : 0.9997308850288391

$ tree -L 3 riscv64/
riscv64/
├── gsl
│   └── gsl-lite.hpp
├── nncase
│   ├── include
│   │   └── nncase
│   └── lib
│       ├── cmake
│       ├── libfunctional_k230.a
│       ├── libnncase.rt_modules.k230.a
│       └── libNncase.Runtime.Native.a
└── rvvlib
    ├── include
    │   ├── k230_math.h
    │   ├── nms.h
    │   └── rvv_math.h
    └── librvv.a

8 directories, 8 files

(1) NNCASE_API result<runtime_tensor> create(typecode_t datatype, dims_t shape, memory_pool_t pool = pool_shared_first) noexcept;
(2) NNCASE_API result<runtime_tensor> create(typecode_t datatype, dims_t shape, gsl::span<gsl::byte> data, bool copy,
       memory_pool_t pool = pool_shared_first) noexcept;
(3)NNCASE_API result<runtime_tensor>create(typecode_t datatype, dims_t shape, strides_t strides, gsl::span<gsl::byte> data, bool copy, memory_pool_t pool = pool_shared_first, uintptr_t physical_address = 0) noexcept;

// create input tensor
auto input_desc = interp.input_desc(0);
auto input_shape = interp.input_shape(0);
auto input_tensor = host_runtime_tensor::create(input_desc.datatype, input_shape, hrt::pool_shared).expect("cannot create input tensor");

hrt::sync(input_tensor, sync_op_t::sync_write_back, true).expect("sync write_back failed");

interpreter interp;
auto model = read_binary_file<unsigned char>(kmodel);
interp.load_model({(const gsl::byte *)model.data(), model.size()}).expect("cannot load model.");

(1) result<runtime_tensor> input_tensor(size_t index) noexcept;
(2) result<void> input_tensor(size_t index, runtime_tensor tensor) noexcept;

(1) result<runtime_tensor>
(2) result<void>
​```cpp

【示例】

​```cpp
// set input
interp.input_tensor(0, input_tensor).expect("cannot set input tensor");

(1) result<runtime_tensor> output_tensor(size_t index) noexcept;
(2) result<void> output_tensor(size_t index, runtime_tensor tensor) noexcept;

(1) result<runtime_tensor>
(2) result<void>

// get output
auto output_tensor = interp.output_tensor(0).expect("cannot get output tensor");

// run
interp.run().expect("error occurred in running model");

#include <chrono>
#include <fstream>
#include <iostream>
#include <nncase/runtime/interpreter.h>
#include <nncase/runtime/runtime_op_utility.h>

#define USE_OPENCV 1
#define preprocess 1

#if USE_OPENCV
#include <opencv2/highgui.hpp>
#include <opencv2/imgcodecs.hpp>
#include <opencv2/imgproc.hpp>
#endif

using namespace nncase;
using namespace nncase::runtime;
using namespace nncase::runtime::detail;

#define INTPUT_HEIGHT 224
#define INTPUT_WIDTH 224
#define INTPUT_CHANNELS 3

template <class T>
std::vector<T> read_binary_file(const std::string &file_name)
{
    std::ifstream ifs(file_name, std::ios::binary);
    ifs.seekg(0, ifs.end);
    size_t len = ifs.tellg();
    std::vector<T> vec(len / sizeof(T), 0);
    ifs.seekg(0, ifs.beg);
    ifs.read(reinterpret_cast<char *>(vec.data()), len);
    ifs.close();
    return vec;
}

void read_binary_file(const char *file_name, char *buffer)
{
    std::ifstream ifs(file_name, std::ios::binary);
    ifs.seekg(0, ifs.end);
    size_t len = ifs.tellg();
    ifs.seekg(0, ifs.beg);
    ifs.read(buffer, len);
    ifs.close();
}

static std::vector<std::string> read_txt_file(const char *file_name)
{
    std::vector<std::string> vec;
    vec.reserve(1024);

    std::ifstream fp(file_name);
    std::string label;

    while (getline(fp, label))
    {
        vec.push_back(label);
    }

    return vec;
}

template<typename T>
static int softmax(const T* src, T* dst, int length)
{
    const T alpha = *std::max_element(src, src + length);
    T denominator{ 0 };

    for (int i = 0; i < length; ++i) {
        dst[i] = std::exp(src[i] - alpha);
        denominator += dst[i];
    }

    for (int i = 0; i < length; ++i) {
        dst[i] /= denominator;
    }

    return 0;
}

#if USE_OPENCV
std::vector<uint8_t> hwc2chw(cv::Mat &img)
{
    std::vector<uint8_t> vec;
    std::vector<cv::Mat> rgbChannels(3);
    cv::split(img, rgbChannels);
    for (auto i = 0; i < rgbChannels.size(); i++)
    {
        std::vector<uint8_t> data = std::vector<uint8_t>(rgbChannels[i].reshape(1, 1));
        vec.insert(vec.end(), data.begin(), data.end());
    }

    return vec;
}
#endif

static int inference(const char *kmodel_file, const char *image_file, const char *label_file)
{
    // load kmodel
    interpreter interp;
    auto kmodel = read_binary_file<unsigned char>(kmodel_file);
    interp.load_model({ (const gsl::byte *)kmodel.data(), kmodel.size() }).expect("cannot load model.");

    // create input tensor
    auto input_desc = interp.input_desc(0);
    auto input_shape = interp.input_shape(0);
    auto input_tensor = host_runtime_tensor::create(input_desc.datatype, input_shape, hrt::pool_shared).expect("cannot create input tensor");
    interp.input_tensor(0, input_tensor).expect("cannot set input tensor");

    // create output tensor
    // auto output_desc = interp.output_desc(0);
    // auto output_shape = interp.output_shape(0);
    // auto output_tensor = host_runtime_tensor::create(output_desc.datatype, output_shape, hrt::pool_shared).expect("cannot create output tensor");
    // interp.output_tensor(0, output_tensor).expect("cannot set output tensor");

    // set input data
    auto dst = input_tensor.impl()->to_host().unwrap()->buffer().as_host().unwrap().map(map_access_::map_write).unwrap().buffer();
#if USE_OPENCV
    cv::Mat img = cv::imread(image_file);
    cv::resize(img, img, cv::Size(INTPUT_WIDTH, INTPUT_HEIGHT), cv::INTER_NEAREST);
    auto input_vec = hwc2chw(img);
    memcpy(reinterpret_cast<char *>(dst.data()), input_vec.data(), input_vec.size());
#else
    read_binary_file(image_file, reinterpret_cast<char *>(dst.data()));
#endif
    hrt::sync(input_tensor, sync_op_t::sync_write_back, true).expect("sync write_back failed");

    // run
    size_t counter = 1;
    auto start = std::chrono::steady_clock::now();
    for (size_t c = 0; c < counter; c++)
    {
        interp.run().expect("error occurred in running model");
    }
    auto stop = std::chrono::steady_clock::now();
    double duration = std::chrono::duration<double, std::milli>(stop - start).count();
    std::cout << "interp.run() took: " << duration / counter << " ms" << std::endl;

    // get output data
    auto output_tensor = interp.output_tensor(0).expect("cannot set output tensor");
    dst = output_tensor.impl()->to_host().unwrap()->buffer().as_host().unwrap().map(map_access_::map_read).unwrap().buffer();
    float *output_data = reinterpret_cast<float *>(dst.data());
    auto out_shape = interp.output_shape(0);
    auto size = compute_size(out_shape);

    // postprogress softmax by cpu
    std::vector<float> softmax_vec(size, 0);
    auto buf = softmax_vec.data();
    softmax(output_data, buf, size);
    auto it = std::max_element(buf, buf + size);
    size_t idx = it - buf;

    // load label
    auto labels = read_txt_file(label_file);
    std::cout << "image classify result: " << labels[idx] << "(" << *it << ")" << std::endl;

    return 0;
}

int main(int argc, char *argv[])
{
    std::cout << "case " << argv[0] << " built at " << __DATE__ << " " << __TIME__ << std::endl;
    if (argc != 4)
    {
        std::cerr << "Usage: " << argv[0] << " <kmodel> <image> <label>" << std::endl;
        return -1;
    }

    int ret = inference(argv[1], argv[2], argv[3]);
    if (ret)
    {
        std::cerr << "inference failed: ret = " << ret << std::endl;
        return -2;
    }

    return 0;
}

enum class ai2d_format
{
    YUV420_NV12 = 0,
    YUV420_NV21 = 1,
    YUV420_I420 = 2,
    NCHW_FMT = 3,
    RGB_packed = 4,
    RAW16 = 5,
}

 enum class ai2d_interp_method
{
    tf_nearest = 0,
    tf_bilinear = 1,
    cv2_nearest = 2,
    cv2_bilinear = 3,
}

enum class ai2d_interp_mode
{
    none = 0,
    align_corner = 1,
    half_pixel = 2,
}

enum class ai2d_pad_mode
{
    constant = 0,
    copy = 1,
    mirror = 2,
}

struct ai2d_datatype_t
{
    ai2d_format src_format;
    ai2d_format dst_format;
    datatype_t src_type;
    datatype_t dst_type;
    ai2d_data_loc src_loc = ai2d_data_loc::ddr;
    ai2d_data_loc dst_loc = ai2d_data_loc::ddr;
}

ai2d_datatype_t ai2d_dtype { ai2d_format::RAW16, ai2d_format::NCHW_FMT, datatype_t::dt_uint16, datatype_t::dt_uint8 };

struct ai2d_crop_param_t
{
    bool crop_flag = false;
    int32_t start_x = 0;
    int32_t start_y = 0;
    int32_t width = 0;
    int32_t height = 0;
}

ai2d_crop_param_t crop_param { true, 40, 30, 400, 600 };

struct ai2d_shift_param_t
{
    bool shift_flag = false;
    int32_t shift_val = 0;
}

struct ai2d_pad_param_t
{
    bool pad_flag = false;
    runtime_paddings_t paddings;
    ai2d_pad_mode pad_mode = ai2d_pad_mode::constant;
    std::vector<int32_t> pad_val; // by channel
}

ai2d_pad_param_t pad_param { false, { { 0, 0 }, { 0, 0 }, { 0, 0 }, { 60, 60 } }, ai2d_pad_mode::constant, { 255 } };

struct ai2d_resize_param_t
{
    bool resize_flag = false;
    ai2d_interp_method interp_method = ai2d_interp_method::tf_bilinear;
    ai2d_interp_mode interp_mode = ai2d_interp_mode::none;
}

ai2d_resize_param_t resize_param { true, ai2d_interp_method::tf_bilinear, ai2d_interp_mode::half_pixel };

struct ai2d_affine_param_t
{
    bool affine_flag = false;
    ai2d_interp_method interp_method = ai2d_interp_method::cv2_bilinear;
    uint32_t cord_round = 0;
    uint32_t bound_ind = 0;
    int32_t bound_val = 0;
    uint32_t bound_smooth = 0;
    std::vector<float> M;
}

ai2d_affine_param_t affine_param { true, ai2d_interp_method::cv2_bilinear, 0, 0, 127, 1, { 0.5, 0.1, 0.0, 0.1, 0.5, 0.0 } };

ai2d_builder(dims_t &input_shape, dims_t &output_shape, ai2d_datatype_t ai2d_dtype, ai2d_crop_param_t crop_param, ai2d_shift_param_t shift_param, ai2d_pad_param_t pad_param, ai2d_resize_param_t resize_param, ai2d_affine_param_t affine_param);