Method configure

src/runtime/NEON/functions/NEConvolutionLayer.cpp:65–123

NEConvolutionLayer::~NEConvolutionLayer() = default;

void NEConvolutionLayer::configure(ITensor                   *input,
                                   const ITensor             *weights,
                                   const ITensor             *biases,
                                   ITensor                   *output,
                                   const PadStrideInfo       &conv_info,
                                   const WeightsInfo         &weights_info,
                                   const Size2D              &dilation,
                                   const ActivationLayerInfo &act_info,
                                   bool                       enable_fast_math,
                                   unsigned int               num_groups)
{
    ARM_COMPUTE_TRACE_EVENT(ARM_COMPUTE_PROF_CAT_CPU, ARM_COMPUTE_PROF_LVL_CPU, "NEConvolutionLayer::configure");
    // Perform validate step
    ARM_COMPUTE_ERROR_ON_NULLPTR(input, weights, output);
    ARM_COMPUTE_UNUSED(num_groups);
    ARM_COMPUTE_ERROR_THROW_ON(NEConvolutionLayer::validate(
        input->info(), weights->info(), ((biases != nullptr) ? biases->info() : nullptr), output->info(), conv_info,
        weights_info, dilation, act_info, enable_fast_math, num_groups));
    ARM_COMPUTE_LOG_PARAMS(input, weights, biases, output, conv_info, weights_info, dilation, act_info,
                           enable_fast_math, num_groups);

    const Conv2dInfo info(conv_info, dilation, act_info, enable_fast_math, num_groups);
    switch (cpu::CpuConv2d::get_convolution_method(input->info(), weights->info(), output->info(), conv_info,
                                                   weights_info, dilation, act_info, enable_fast_math))
    {
        case ConvolutionMethod::WINOGRAD:
        case ConvolutionMethod::GEMM:
        case ConvolutionMethod::GEMM_CONV2D:
        case ConvolutionMethod::DIRECT:
        {
            auto f = std::make_unique<cpu::CpuConv2d>();
            f->configure(input->info(), weights->info(), ((biases != nullptr) ? biases->info() : nullptr),
                         output->info(), conv_info, weights_info, dilation, act_info, enable_fast_math, num_groups);
            _impl->op = std::move(f);
            break;
        }
        case ConvolutionMethod::FFT:
        {
            auto f = std::make_unique<NEFFTConvolutionLayer>(_impl->memory_manager);
            f->configure(input, weights, biases, output, conv_info, act_info);
            _impl->func = std::move(f);
            break;
        }
        default:
            ARM_COMPUTE_ERROR("Not supported.");
            break;
    }

    if (_impl->op)
    {
        _impl->memory_group = MemoryGroup(std::move(_impl->memory_manager));
        _impl->aux_mem_req  = _impl->op->workspace();
        _impl->run_pack     = {{ACL_SRC_0, input}, {ACL_SRC_1, weights}, {ACL_SRC_2, biases}, {ACL_DST, output}};
        _impl->prep_pack    = {{ACL_SRC_1, weights}, {ACL_SRC_2, biases}};
        _impl->workspace    = manage_workspace<Tensor>(_impl->aux_mem_req, _impl->memory_group, _impl->run_pack,
                                                    _impl->prep_pack, /* allocate_now */ false);
    }
    _impl->is_prepared = false;