Intel FPGA AI Sutie Inference Engine

Hello @JohnT_Intel,

Same behaviour.

I changed to create the blobs before the loop and only filling them in the loop:

        // Create blobs only once before the loop
        using Blob_t = std::vector<std::map<std::string, Blob::Ptr>>;
        std::vector<std::pair<Blob_t, Blob_t>> ioBlobs = vectorMapWithIndex<std::pair<Blob_t, Blob_t>>(
            exeNetworks, [&](ExecutableNetwork* const& exeNetwork, uint32_t index) mutable {
                Blob_t inputBlobs;
                Blob_t outputBlobs;
                ConstInputsDataMap inputInfo = exeNetwork->GetInputsInfo();
                ConstOutputsDataMap outputInfo = exeNetwork->GetOutputsInfo();
                
                for (uint32_t batch = 0; batch < num_batches; batch++) {
                    std::map<std::string, Blob::Ptr> outputBlobsMap;
                    for (auto& item : outputInfo) {
                        auto& precision = item.second->getTensorDesc().getPrecision();
                        if (precision != Precision::FP32) {
                            THROW_IE_EXCEPTION << "Output blob creation only supports FP32 precision. Instead got: " + precision;
                        }
                        auto outputBlob = make_shared_blob<PrecisionTrait<Precision::FP32>::value_type>(item.second->getTensorDesc());
                        outputBlob->allocate();
                        outputBlobsMap[item.first] = (outputBlob);
                    }

                    std::map<std::string, Blob::Ptr> inputBlobsMap;
                    for (auto& item : inputInfo) {
                        Blob::Ptr inputBlob = nullptr;
                        auto& precision = item.second->getTensorDesc().getPrecision();
                        if (precision == Precision::FP32) {
                            inputBlob = make_shared_blob<PrecisionTrait<Precision::FP32>::value_type>(item.second->getTensorDesc());
                        } else if (precision == Precision::U8) {
                            inputBlob = make_shared_blob<PrecisionTrait<Precision::U8>::value_type>(item.second->getTensorDesc());
                        } else {
                            THROW_IE_EXCEPTION << "Input blob creation only supports FP32 and U8 precision. Instead got: " + precision;
                        }
                        inputBlob->allocate();
                        inputBlobsMap[item.first] = (inputBlob);
                    }

                    inputBlobs.push_back(inputBlobsMap);
                    outputBlobs.push_back(outputBlobsMap);
                }
                
                return std::make_pair(inputBlobs, outputBlobs);
            }
        );

        std::cout << "Blobs initialized once before the loop.\n";

        while (1) {
        ...
          // Fill blobs with new input values (DO NOT re-create them)
          for (size_t i = 0; i < exeNetworks.size(); i++) {
                slog::info << "Filling input blobs for network ( " << topology_names[i] << " )" << slog::endl;
                fillBlobs(inputs, ioBlobs[i].first);  // Only fill the existing blobs
           }
       ...
        }

Error: dlia_infer_request.cpp:53 Number of inference requests exceed the maximum number of inference requests supported per instance