RKNN2 SDK V2.5.0 · Модели с динамической формой и развёртывание

# Python
dynamic_input = [
    [[1,3,224,224]], # set the first shape for all inputs
    [[1,3,192,192]], # set the second shape for all inputs
    [[1,3,160,160]], # set the third shape for all inputs
]

# Pre-process config
rknn.config(mean_values=[103.94, 116.78, 123.68], std_values=[58.82, 58.82, 58.82],
quant_img_RGB2BGR=True, dynamic_input=dynamic_shapes)

W config: The 'dynamic_input' function has been enabled, the MaxShape is dynamic_input[0] = [[1,224],[1,40]]!
The following functions are subject to the MaxShape:
1. The quantified dataset needs to be configured according to MaxShape
2. The eval_perf or eval_memory return the results of MaxShape

// Query the input shapes supported by the model
rknn_input_range dyn_range[io_num.n_input];
memset(dyn_range, 0, io_num.n_input * sizeof(rknn_input_range));
for (uint32_t i = 0; i < io_num.n_input; i++)
{
    dyn_range[i].index = i;
    ret = rknn_query(ctx, RKNN_QUERY_INPUT_DYNAMIC_RANGE, &dyn_range[i], sizeof(rknn_input_range));
    if (ret != RKNN_SUCC)
    {
        fprintf(stderr, "rknn_query error! ret=%d\n", ret);
        return -1;
    }
    dump_input_dynamic_range(&dyn_range[i]);
}

/**
 dynamic inputs shape range:
 index=0, name=data, shape_number=2, range=[[1, 224, 224, 3],[1, 112, 224, 3]], fmt = NHWC
**/
input_attrs[0].dims[0] = 1;
input_attrs[0].dims[1] = 224;
input_attrs[0].dims[2] = 224;
input_attrs[0].dims[3] = 3;
input_attrs[0].fmt=RKNN_TENSOR_NHWC;
ret = rknn_set_input_shapes(ctx, io_num.n_input, input_attrs);
if (ret < 0) {
  fprintf(stderr, "rknn_set_input_shapes error! ret=%d\n", ret);
  return -1;
}

// Get the input and output shapes of the current inference
rknn_tensor_attr cur_input_attrs[io_num.n_input];
memset(cur_input_attrs, 0, io_num.n_input * sizeof(rknn_tensor_attr));
for (uint32_t i = 0; i < io_num.n_input; i++)
{
    cur_input_attrs[i].index = i;
    ret = rknn_query(ctx, RKNN_QUERY_CURRENT_INPUT_ATTR, &(cur_input_attrs[i]), sizeof(rknn_tensor_attr));
    if (ret < 0)
    {
        printf("rknn_init error! ret=%d\n", ret);
        return -1;
    }
    dump_tensor_attr(&cur_input_attrs[i]);
}
rknn_tensor_attr cur_output_attrs[io_num.n_output];
memset(cur_output_attrs, 0, io_num.n_output * sizeof(rknn_tensor_attr));
for (uint32_t i = 0; i < io_num.n_output; i++)
{
    cur_output_attrs[i].index = i;
    ret = rknn_query(ctx, RKNN_QUERY_CURRENT_OUTPUT_ATTR, &(cur_output_attrs[i]), sizeof(rknn_tensor_attr));
    if (ret != RKNN_SUCC)
    {
        printf("rknn_query fail! ret=%d\n", ret);
        return -1;
    }
    dump_tensor_attr(&cur_output_attrs[i]);
}

// Set input information
rknn_input inputs[io_num.n_input];
memset(inputs, 0, io_num.n_input * sizeof(rknn_input));
for (int i = 0; i < io_num.n_input; i++)
{
    int height = cur_input_attrs[i].fmt == RKNN_TENSOR_NHWC ? cur_input_attrs[i].dims[1] : cur_input_attrs[i].dims[2];
    int width = cur_input_attrs[i].fmt == RKNN_TENSOR_NHWC ? cur_input_attrs[i].dims[2] : cur_input_attrs[i].dims[3];
    cv::resize(imgs[i], imgs[i], cv::Size(width, height));
    inputs[i].index = i;
    inputs[i].pass_through = 0;
    inputs[i].type = RKNN_TENSOR_UINT8;
    inputs[i].fmt = RKNN_TENSOR_NHWC;
    inputs[i].buf = imgs[i].data;
    inputs[i].size = imgs[i].total() * imgs[i].channels();
}

// Convert the input data into the correct format and put it into the input buffer
ret = rknn_inputs_set(ctx, io_num.n_input, inputs);
if (ret < 0)
{
    printf("rknn_input_set fail! ret=%d\n", ret);
    return -1;
}

// Run inference
printf("Begin perf ...\n");
double total_time = 0;
for (int i = 0; i < loop_count; ++i)
{
    int64_t start_us = getCurrentTimeUs();
    ret = rknn_run(ctx, NULL);
    int64_t elapse_us = getCurrentTimeUs() - start_us;
    if (ret < 0)
    {
        printf("rknn run error %d\n", ret);
        return -1;
    }
    total_time += elapse_us / 1000.f;
    printf("%4d: Elapse Time = %.2fms, FPS = %.2f\n", i, elapse_us / 1000.f, 1000.f
* 1000.f / elapse_us);
}
printf("Avg FPS = %.3f\n", loop_count * 1000.f / total_time);

// Get output results
rknn_output outputs[io_num.n_output];
memset(outputs, 0, io_num.n_output * sizeof(rknn_output));
for (uint32_t i = 0; i < io_num.n_output; ++i)
{
    outputs[i].want_float = 1;
    outputs[i].index = i;
    outputs[i].is_prealloc = 0;
}

ret = rknn_outputs_get(ctx, io_num.n_output, outputs, NULL);
if (ret < 0)
{
    printf("rknn_outputs_get fail! ret=%d\n", ret);
    return ret;
}

// Release the output buffer
ret = rknn_outputs_release(ctx, io_num.n_output, outputs);

// Create the largest input tensor memory
rknn_tensor_mem *input_mems[io_num.n_input];
for (int i = 0; i < io_num.n_input; i++) {
    // default input type is int8 (normalize and quantize need compute in outside)
    // if set uint8, will fuse normalize and quantize to npu
    input_attrs[i].type = RKNN_TENSOR_UINT8;
    // default fmt is NHWC, npu only support NHWC in zero copy mode
    input_attrs[i].fmt = RKNN_TENSOR_NHWC;
    input_mems[i] = rknn_create_mem(ctx, input_attrs[i].size_with_stride);
...
// Create the largest output tensor memory
rknn_tensor_mem *output_mems[io_num.n_output];
for (uint32_t i = 0; i < io_num.n_output; ++i) {
    // default output type is depend on model, this require float32 to compute top5
    // allocate float32 output tensor
    int output_size = output_attrs[i].size * sizeof(float);
    output_mems[i] = rknn_create_mem(ctx, output_size);
...
// Load the input and set the model input shape, which is called once each time the input shape is switched
for (int s = 0; s < shape_num; ++s) {
    for (int i = 0; i < io_num.n_input; i++) {
        for (int j = 0; j < input_attrs[i].n_dims; ++j) {
           input_attrs[i].dims[j] = shape_range[i].dyn_range[s][j];
    .....
    ret = rknn_set_input_shapes(ctx, io_num.n_input, input_attrs);
    if (ret < 0) {
        fprintf(stderr, "rknn_set_input_shape error! ret=%d\n", ret);
        return -1;
    ....
    // Get the input and output shapes of the current inference
    printf("current input tensors:\n");
    rknn_tensor_attr cur_input_attrs[io_num.n_input];
    memset(cur_input_attrs, 0, io_num.n_input * sizeof(rknn_tensor_attr));
    for (uint32_t i = 0; i < io_num.n_input; i++) {
        cur_input_attrs[i].index = i;
        // query info
        ret = rknn_query(ctx, RKNN_QUERY_CURRENT_INPUT_ATTR, &(cur_input_attrs[i]), sizeof(rknn_tensor_attr));
        if (ret < 0) {
           printf("rknn_init error! ret=%d\n", ret);
           return -1;
        dump_tensor_attr(&cur_input_attrs[i]);
        ...
        printf("current output tensors:\n");
    rknn_tensor_attr cur_output_attrs[io_num.n_output];
    memset(cur_output_attrs, 0, io_num.n_output * sizeof(rknn_tensor_attr));
    for (uint32_t i = 0; i < io_num.n_output; i++) {
        cur_output_attrs[i].index = i;
        // query info
        ret = rknn_query(ctx, RKNN_QUERY_CURRENT_OUTPUT_ATTR, &
(cur_output_attrs[i]), sizeof(rknn_tensor_attr));
        if (ret != RKNN_SUCC) {
           printf("rknn_query fail! ret=%d\n", ret);
           return -1;
        ...
        dump_tensor_attr(&cur_output_attrs[i]);
    // Specify the number of NPU cores, only 3588/3576 is supported
    rknn_set_core_mask(ctx, (rknn_core_mask)core_mask);
    // Set input information
    rknn_input inputs[io_num.n_input];
    memset(inputs, 0, io_num.n_input * sizeof(rknn_input));
    std::vector<cv::Mat> resize_imgs;
    resize_imgs.resize(io_num.n_input);
    for (int i = 0; i < io_num.n_input; i++) {
        int height = cur_input_attrs[i].fmt == RKNN_TENSOR_NHWC ? cur_input_attrs[i].dims[1] : cur_input_attrs[i].dims[2];
        int width = cur_input_attrs[i].fmt == RKNN_TENSOR_NHWC ? cur_input_attrs[i].dims[2] : cur_input_attrs[i].dims[3];
        int stride = cur_input_attrs[i].w_stride;
        cv::resize(imgs[i], resize_imgs[i], cv::Size(width, height));
        int input_size = resize_imgs[i].total() * resize_imgs[i].channels();
        // Copy external data to the zero-copy input buffer
        if (width == stride)
           memcpy(input_mems[i]->virt_addr, resize_imgs[i].data, input_size);
        else {
           int height = cur_input_attrs[i].dims[1];
           int channel = cur_input_attrs[i].dims[3];
           // copy from src to dst with stride
           uint8_t *src_ptr = resize_imgs[i].data;
           uint8_t *dst_ptr = (uint8_t *)input_mems[i]->virt_addr;
           // width-channel elements
           int src_wc_elems = width * channel;
           int dst_wc_elems = stride * channel;
           for (int b = 0; b < cur_input_attrs[i].dims[0]; b++) {
               for (int h = 0; h < height; ++h) {
                   memcpy(dst_ptr, src_ptr, src_wc_elems);
                   src_ptr += src_wc_elems;
                   dst_ptr += dst_wc_elems;
           ....
    // Update the input zero-copy buffer memory
    for (int i = 0; i < io_num.n_input; i++) {
        cur_input_attrs[i].type = RKNN_TENSOR_UINT8;
        ret = rknn_set_io_mem(ctx, input_mems[i], &cur_input_attrs[i]);
        if (ret < 0) {
           printf("rknn_set_io_mem fail! ret=%d\n", ret);
           return -1;
     ....
    // Update the output zero-copy buffer memory
    for (uint32_t i = 0; i < io_num.n_output; ++i) {
        // default output type is depend on model, this require float32 to compute top5
        cur_output_attrs[i].type = RKNN_TENSOR_FLOAT32;
        cur_output_attrs[i].fmt = RKNN_TENSOR_NCHW;
        // set output memory and attribute
        ret = rknn_set_io_mem(ctx, output_mems[i], &cur_output_attrs[i]);
        if (ret < 0) {
           printf("rknn_set_io_mem fail! ret=%d\n", ret);
           return -1;
      ....
    // Inference
    printf("Begin perf ...\n");
    double total_time = 0;
    for (int i = 0; i < loop_count; ++i) {
        int64_t start_us = getCurrentTimeUs();
        ret = rknn_run(ctx, NULL);
        int64_t elapse_us = getCurrentTimeUs() - start_us;
        if (ret < 0) {
           printf("rknn run error %d\n", ret);
           return -1;
        ...
        total_time += elapse_us / 1000.f;
        printf("%4d: Elapse Time = %.2fms, FPS = %.2f\n", i, elapse_us / 1000.f, 1000.f * 1000.f / elapse_us);
    printf("Avg FPS = %.3f\n", loop_count * 1000.f / total_time);