what is the INPUT_BLOB_NAME and OUTPUT_BLOB_NAME, when trensorrt forward?

[xinsuinizhuan]

yolov5 is:
const char* INPUT_BLOB_NAME = "data";
const char* OUTPUT_BLOB_NAME = "prob";

yolov6 is:
const char* INPUT_BLOB_NAME = "image_arrays";
const char* OUTPUT_BLOB_NAME = "outputs";

yolov7 input is images and output is putput
const char* INPUT_BLOB_NAME = "images";
const char* OUTPUT_BLOB_NAME = "output";

yolov7, use the above, all is -1, as below:
IRuntime* runtime = createInferRuntime(gLogger);
assert(runtime != nullptr);
ICudaEngine* engine = runtime->deserializeCudaEngine(trtModelStream, size);
assert(engine != nullptr);
IExecutionContext* context = engine->createExecutionContext();
assert(context != nullptr);
delete[] trtModelStream;
const ICudaEngine& engine = context.getEngine();
const int inputIndex = engine.getBindingIndex(INPUT_BLOB_NAME); //return -1
const int outputIndex = engine.getBindingIndex(OUTPUT_BLOB_NAME); //return -1

[xinsuinizhuan]

I export the pt to onnx，then convert then onnx to tensorrt model, the use the tensorrt model to forward, all yolov5 and yolov6 is ok, but when yolov7 forward,
const int inputIndex = engine.getBindingIndex(INPUT_BLOB_NAME); //return -1
const int outputIndex = engine.getBindingIndex(OUTPUT_BLOB_NAME); //return -1

[philipp-schmidt]

output_names=['classes', 'boxes'] if y is None else ['output']

Maybe this? Classes and boxes

[xinsuinizhuan]

I test with classes and boxes, still return -1