Here are
20 public repositories
matching this topic...
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
-
Updated
May 22, 2022
-
Python
🍅 Deploy ncnn on mobile phones. Support Android and iOS. 移动端ncnn部署，支持Android与iOS。
QuarkDet lightweight object detection in PyTorch .Real-Time Object Detection on Mobile Devices.
-
Updated
Feb 3, 2021
-
Python
用opencv部署nanodet目标检测，包含C++和Python两种版本程序的实现
Deploy nanodet, the super fast and lightweight object detection, in your web browser with ncnn and webassembly
awesome AI models with NCNN, and how they were converted ✨✨✨
🍉 移动端TNN部署学习笔记，支持Android与iOS。
Tracking-by-Detection形式のMOT(Multi Object Tracking)について、 DetectionとTrackingの処理を分離して寄せ集めたフレームワーク
-
Updated
Jul 7, 2022
-
Python
nanodet int8 量化，实测推理2ms一帧！
手把手教你OpenVINO下部署NanoDet模型，intel i7-7700HQ CPU实测6ms一帧
-
Updated
Apr 23, 2021
-
Makefile
NanoDet: Tiny Object Detection for TFJS and NodeJS
-
Updated
Jul 1, 2022
-
JavaScript
NanoDetをGoogle Colaboratory上で訓練しONNX形式のファイルをエクスポートするサンプル(This is a sample to training NanoDet on Google Colaboratory and export a file in ONNX format)
-
Updated
Sep 20, 2021
-
Jupyter Notebook
NanoDet for a bare Raspberry Pi 4
NanoDetのPythonでのONNX推論サンプル
-
Updated
Sep 21, 2021
-
Jupyter Notebook
A collection of some awesome Anchor-Free series projects.
Some Nanodet trained models
This repo is implemented based on detectron2
-
Updated
Apr 10, 2022
-
Python
NanoDet with tracking for a bare Raspberry Pi 4 using ncnn.
Improve this page
Add a description, image, and links to the
nanodet
topic page so that developers can more easily learn about it.
Curate this topic
Add this topic to your repo
To associate your repository with the
nanodet
topic, visit your repo's landing page and select "manage topics."
Learn more
You can’t perform that action at this time.
You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
这个issue主要讲一下，如何把你自己的模型添加到lite.ai.toolkit。lite.ai.toolkit集成了一些比较新的基础模型，比如人脸检测、人脸识别、抠图、人脸属性分析、图像分类、人脸关键点识别、图像着色、目标检测等等，可以直接用到具体的场景中。但是，毕竟lite.ai.toolkit的模型还是有限的，具体的场景下，可能有你经过优化的模型，比如你自己训了一个目标检测器，可能效果更好。那么，如何把你的模型加入到lite.ai.toolkit中呢？这样既能用到lite.ai.toolkit一些已有的算法能力，也能兼容您的具体场景。这个issue主要是讲这个问题。大家有疑惑的可以提在这个issue，我会尽可能回答~