We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
same way succeed in YOLOV8, but failed in YOLOV11
from ultralytics import YOLO model = YOLO('yolo11n.pt') model.export( imgsz=192, format='tflite', # simplify=True, opset=14, int8=True )
using yolo11n_integer_quant.tflite
std::unique_ptr<tflite::Interpreter> interpreter;; std::unique_ptr<tflite::FlatBufferModel> model = tflite::FlatBufferModel::BuildFromFile(model_test.c_str()); tflite::ops::builtin::BuiltinOpResolver resolver; tflite::InterpreterBuilder(*model.get(), resolver)(&interpreter); tflite::tools::ToolParams params; ProvidedDelegateList providers(¶ms); providers.AddAllDelegateParams(); params.Set<std::string>("external_delegate_path", "/usr/lib/libvx_delegate.so", 1); interpreter->SetAllowFp16PrecisionForFp32(true); memcpy(input_tensor->data.f, inputImg.ptr<float>(0), HEIGHT*WIDTH*3* sizeof(float)); auto start = std::chrono::high_resolution_clock::now(); interpreter->Invoke();
The text was updated successfully, but these errors were encountered:
No branches or pull requests
same way succeed in YOLOV8, but failed in YOLOV11
using yolo11n_integer_quant.tflite
The text was updated successfully, but these errors were encountered: