Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/akira4o4/trtplus
tensorrt-plus framework
https://github.com/akira4o4/trtplus
cpp cpu cuda gpu tensorrt yolo
Last synced: 2 months ago
JSON representation
tensorrt-plus framework
- Host: GitHub
- URL: https://github.com/akira4o4/trtplus
- Owner: akira4O4
- License: gpl-3.0
- Created: 2024-07-08T02:44:04.000Z (7 months ago)
- Default Branch: master
- Last Pushed: 2024-11-13T08:09:26.000Z (3 months ago)
- Last Synced: 2024-11-13T09:20:20.908Z (3 months ago)
- Topics: cpp, cpu, cuda, gpu, tensorrt, yolo
- Language: C++
- Homepage:
- Size: 882 KB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TRTPlus
---
## Introduction
- Easy to Use
- Fast Inference
- Automatic Model Decoding
---
## Support
**Only Testing On Linux.**
| Task | Work |
|-----------------------|:----:|
| segmentation | ✔️ |
| yolov8 classification | ✔️ |
| yolov8 detection | ✔️ |
| yolov8 segmentation | ❔ |
| yolov8 obb detection | ✔️ |
| yolov10 detection | ✔️ |
| yolov11 detection | ✔️ |
## Install
```bash
cd
git clone https://github.com/akira4O4/tensorrt-lab.git
cd tensorrt-lab
```
---
## How to use
### Step1: Write your label.txt
If your project task is a```segmentation```,the ```label.txt``` first line must be ```0_background_```.
E.g. ```classification_label.txt```
```txt
classes1
classes2
...
classes7
classes8
```
E.g. ```segmentation_label.txt```
```txt
0_background_
1_xxx
2_xxx
...
5_xxx
6_xxx
```
### Step2: Modify Your ```main.cpp```
Refer to the ```cpp``` file in the ```examples``` folder to write your code
```bash
examples/
├── yolov10_det.cpp
├── yolov8_cls.cpp
├── yolov8_det.cpp
└── yolov8_seg.cpp
```
---
## Compile & Rund
**Attention**: Configure your CmakeLists.txt
```bash
mkdir build && cd build
cmake ..
sudo make -j8
./main.bin
```