Solov2-TensorRT-CPP
Solov2-TensorRT-CPP copied to clipboard
in this repo, we deployed SOLOv2 to TensorRT with C++.
Hello teacher, when I compile your code, I always get this error (c++ 14/17): /home/hermione/library/libtorch/include/ATen/TensorIterator.h:200:3: error: reference to 'DeviceType' is ambiguous DeviceType device_type(int arg=0) const { return device(arg).type(); }. Do...
根据你的方法导出的tensorrt模型,存在计算scores大于1的情况,请问这个可能是什么原因导致的?
#Modify for onnx export, frozen the input size = 800x800, batch size = 1 size = {0: 100, 1: 100, 2: 50, 3: 25, 4: 25} 这句size是干啥的
What are your versions of pytorch and tensorrt? My CUDA for 10.2 pytorch for 1.8 does not configure the environment
When i run "./build/segment ./config/config.yaml", i get an Error "[E] [TRT] 3: [executionContext.cpp::enqueueInternal::322] Error Code 3: Internal Error (Parameter check failed at: runtime/api/executionContext.cpp::enqueueInternal::322, condition: bindings[x] != nullptr)", and what maybe...
onnx转换失败
我发现使用onnx转换后,输出是11个,不是代码里面的三个,而且我用shape 768 1344去转换,直接报错 Traceback (most recent call last): File "onnx_exporter.py", line 231, in check(args, dummy_input, check_onnx=True, check_trt=False) File "onnx_exporter.py", line 126, in check sess = rt.InferenceSession(args.out) File "/home/tao/anaconda3/lib/python3.8/site-packages/onnxruntime/capi/session.py", line 195,...
The link for install SOLO is broken, error: Page not found
hi,professor: is there any possible for deployment solov2 don't use libtorch? just use tensorrt deserialize api, then write some postprocess code? beacause it has fewer dependence, install libtorch on jetson...
hi,professor: when i compile (build_model , i got error: Solov2-TensorRT-CPP/InstanceSegment/common.h:388:9: error: ‘virtual nvinfer1::IBuilder::~IBuilder()’ is protected within this context delete obj; ^~~~~~ why? my enviroment: nvidia jetson tx2 with jetpack4.5.1 tensorrt...