Jingyu Yan
Jingyu Yan
您好，打扰了，想请问一下使用您项目提供的exportOnnx.py把deepsort的模型转换成onnx后，使用opencv dnn和ort进行推理，结果和原来torch推理结果不一致，请问这是什么原因呢
hi, I need to replace the customized landmark for fitting. How to make the new ‘landmark_embedding.npy' file?
使用CoreML后端进行推理会出现以下问题： ``` 2024-08-08 17:25:37.001 test[34133:3542452] Error compiling model compiler error: Error reading protobuf spec. validator error: Layer '640' of type 'Scale' has output rank 2 but expects rank at least...
Remove some try structures from code to prevent crashes on some embedded devices