It runs. Although when I test the .engine with batch size of >1:
/usr/src/tensorrt/bin/trtexec --loadEngine=/data/models/yolov4_resnet18_default.engine --batch=4 --iterations=100 --avgRuns=10 --dumpProfile --dumpOutput --useCudaGraph
I get:
Error Code 3: Internal Error (Parameter check failed at: runtime/api/executionContext.cpp::enqueue::276, condition: batchSize > 0 && batchSize <= mEngine.getMaxBatchSize(). Note: Batch size was: 4, but engine max batch size was: 1
When running through DeepStream it works but I get the same low FPS result as in Problems with Onnx model zoo -> trtexec -> DeepStream 6.0 pipeline
I’ll continue to investigate