libtorch-yolov3

libtorch-yolov3 copied to clipboard

I want to train model on my custom dataset and deploy in libtorch, which version of yoloV3(darknt or ultralytics?) should I use?

TTgogogo

How do I compile this project on Linux?

1

**Hello,when I use libtorch1.0.0(I download from https://download.pytorch.org/libtorch/cpu/libtorch-shared-with-deps-1.0.0.zip),but I get errors,As shown below.****  What should I do? **This is my computer: Ubuntu 18.04 cmake 3.21.4 gcc 7.5**

tanghao123th

WGFBNBB

I have run your code successfully.Could you add the coco.names in the code？Thank you very much.

StephenZhao1

How to use the PT model trained by the U version of the python model? I tried the following to detect the target

2

as title question ,How to use the PT model trained by the U version of the python model? I tried the following to detect the target

WANGCHAO1996

in make step I meet a error with main.cpp

1

my CmakeList : cmake_minimum_required(VERSION 3.0 FATAL_ERROR) project(yolo-app) find_package( OpenCV 3.4.9 REQUIRED ) include_directories( ${OpenCV_INCLUDE_DIRS} ) message(${OpenCV_INCLUDE_DIRS}) find_package(Torch REQUIRED) aux_source_directory(. DIR_SRCS) add_executable(yolo-app ${DIR_SRCS}) target_link_libraries(yolo-app "${TORCH_LIBRARIES}" "${OpenCV_LIBS}") set_property(TARGET yolo-app PROPERTY CXX_STANDARD 11)...

jackft2

i use libtorch 1.3.0 cuda 10.1 in linux, Error when compile， Can you tell me how to solve it

2

CMakeFiles/yolo-app.dir/main.cpp.o: In function `main': main.cpp:(.text+0x1012): multiple definition of `main' CMakeFiles/yolo-app.dir/detect_cuda_version.cc.o:detect_cuda_version.cc:(.text+0x0): first defined here CMakeFiles/yolo-app.dir/detect_cuda_compute_capabilities.cpp.o: In function `main': detect_cuda_compute_capabilities.cpp:(.text+0x0): multiple definition of `main' CMakeFiles/yolo-app.dir/detect_cuda_version.cc.o:detect_cuda_version.cc:(.text+0x0): first defined here collect2: error: ld returned...

PyNancy

Inference with Grayscale Image

1

Hi, I have trained yolov3 (custom classes and grayscale images) and the inference seems to work good in python. I need to do inference in C++. For this reason I...

Rabia-Saeed

Confidence and class of prediction

1

Hello, I am trying to find the class name and confidence of the predicted result. I understand that the result values from index 1 to 4 are the bounding box...

Rabia-Saeed

Since the original weights are for size 416.

FantasyJXF