search

pytorch / android-demo-app

PyTorch android examples of usage in applications
1.46k stars 604 forks source link

ObjectDetection does not match yoloV5 6.0. How do I modify it？ #201

Open Amy9876 opened 2 years ago

Amy9876 commented 2 years ago

Tensor[] outputTuple = mModule.forward(IValue.from(inputTensor)).toTensorList();

The previous version output was [16,25200,85], Now 6.0 version is a tensor list, [16,3,80,80,85][16,3,40,40,85][16,3,20,20,85], i tried to fix it but failed.May I ask how to modify it? @jeffxtang thanks image

Amy9876 commented 2 years ago

Lite Interpreter verson number does not match. The model version must be between 3 and 5But the model version is 7

image

Amy9876 commented 2 years ago

ObjectDetection does not match yoloV5 6.0. How do I modify it？

JosephKKim commented 2 years ago

Lite Interpreter verson number does not match. The model version must be between 3 and 5But the model version is 7

image

Getting the same issue... Since I'm not familiar with android I don't under stand the model version... Plz help Keep getting the message "Lite Interpreter verson number does not match. The model version must be between 3 and 5But the model version is 7 ()"