cong / yolov5_deepsort_tensorrt Goto Github PK

Hello guys, I am facing this error please help me solve it, it seems that this error is caused by deep sort because the yolov5 engine doesn't give any errors and I can detect with yolov5.engine but the tracker give this error.

Those are the versions of the packages installed on my ubuntu 18 device:

import tensorrt as trt

ModuleNotFoundError: No module named 'tensorrt'

jetson NX

Hi @cong, is it possible to run this repository with yolov3 or v4's tensorRT engine file?

不好意思，我在按照作者的指示轉換deepsort的時候發現他沒法直接轉換，一直回報modulenotfounderror: no module named 'fastreid'
請問有人遇到相同的問題嗎

能再分享一下 下载网址：（链接：http://pan.baidu.com/s/1pJVburD 密码：11m0）这个嘛，链接过期了

Im trying build the application in jetson TX2
Tried Jetpack - 4.4.1 and 4.4
Tensorrt- 7.3.1.0
torch- 1.8
torchvision- 0.9.0

Used v4.0 of yolov5 and tensorrtx git
and generated TRT engine
But still getting this error which says there is mismatch in Tenssorrt version

I don't understand, I have met all the environment requirements you have mentioned but still getting this error

Can you please help on this?

您好，请问下模型运行时所占的内存怎么算出来的？跟模型的权重一样吗？

作者您好，我想问一下这个yolov5+deepsort的模型在转换完.engine之后在在板子上跑也是有跟踪效果的吗？

[TensorRT] ERROR: /home/jenkins/workspace/TensorRT/helpers/rel-7.1/L1_Nightly_Internal/build/source/rtSafe/resources.h (460) - Cuda Error in loadKernel: 3 (initialization error)
[TensorRT] ERROR: INVALID_STATE: std::exception
[TensorRT] ERROR: INVALID_CONFIG: Deserialize the cuda engine failed.
Traceback (most recent call last):
File "demo_trt.py", line 60, in
File "demo_trt.py", line 20, in detect
File "detector_trt.py", line 86, in init
AttributeError: 'NoneType' object has no attribute 'create_execution_context'
[16873] Failed to execute script 'demo_trt' due to unhandled exception!

PyCUDA ERROR: The context stack was not empty upon module cleanup.

A context was still active when the context stack was being
cleaned up. At this point in our execution, CUDA may already
have been deinitialized, so there is no way we can finish
cleanly. The program will be aborted now.
Use Context.pop() to avoid this problem.

已放弃 (核心已转储)

作者你好，您的代码部署到nx上了，但速度大概就是2～3FPS，请问您deepsort部分有加速吗？

Traceback (most recent call last):
File "demo_trt.py", line 58, in
ctypes.CDLL(PLUGIN_LIBRARY)
File "/usr/lib/python3.6/ctypes/init.py", line 348, in init
self._handle = _dlopen(self._name, mode)
OSError: weights/libmyplugins.so: cannot open shared object file: No such file or directory

我在nano上部署了代码 但是在运行demo_trt的过程中，nano直接卡死，请问有没有什么建议。

when i run demo_trt.py i got this error
detector = Detector(engine_file_path)
File "/home/radar/Desktop/yolotrt/yolov5_deepsort_tensorrt/detector_trt.py", line 43, in init
self.cfx = cuda.Device(0).make_context()
pycuda._driver.LogicError: cuDeviceGet failed: initialization error

作者，您好，我就是单纯测试一下效果，libmyplugins.so这个文件从哪里找？