C++ · 91 watchers
PaddleOCR-ncnn-CPP
C++ implementations of PP-OCRv3/4/5/6 using ncnn for inference.
Folder's repos on GitHub
C++ · 20 watchers
YOLOv5-ncnn-OpenVINO-MNN-ONNXRuntime-OpenCV-CPP
YOLOv5 C++ inference implemented using multiple frameworks: ncnn, OpenVINO, MNN, ONNXRuntime, and OpenCV.
C++ · 16 watchers
optimize-gemm
My gemm optimization on RPi (ARM) achieved a 170x performance boost, showing speeds faster than Eigen and close to OpenBLAS.
C++ · 6 watchers
YOLOX-TensorRT10
A TensorRT 10 C++ implementation of YOLOX with dynamic‑shape support.
Python · 3 watchers
Handcrafted-CNN
A handcrafted convolutional neural network. Matrix multiplication instead of loop operation, very fast.
C · 3 watchers
later
Delay no more? Do it later! - A background/delayed command execution tool for Linux & macOS.
C · 2 watchers
LeetCodeSolution
My LeetCode solutions in C AND C++. Directly executable, and all dynamically allocated memory can be freed.
1 watchers
ImageHostingService
My image hosting and sharing repository
C++ · 1 watchers
Qt-OpenCV-CameraEdgeDetection
A simple edge detection example application using the Qt framework and OpenCV library.
C++ · 1 watchers
SimpleJsonParser
A simple JSON parser implemented by C++17.
C · 1 watchers
TrieDictionary
A Simple Trie Implementation.
C · 0 watchers
conv-layout-study
Simple study on the performance impact of NCHW and NHWC layouts for convolution.
Python · 0 watchers
D-FINE
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
C++ · 0 watchers
Depth-Anything-V2-TensorRT10-CPP
A TensorRT 10 C++ implementation of Depth Anything V2 with dynamic‑shape support.
 |
FolderV2EX member #616174, joined on 2023-02-27 10:18:22 +08:00Today's activity rank 1065182
 40  |
knownoknow.com
Avafly
 |
Per Folder's settings, the topics list is only visible after you sign in |
Deals info, including closed deals, is not hidden
Folder's recent replies
1 day ago Replied to a topic by kaivbv › 上海 › 巴威台风上海影响有限，你们开始囤东西了吗？ |
@goodboyG2 四十昼夜降大雨在地上。
3 days ago Replied to a topic by LonelyM › 程序员 › 🔥 CNBC：美国公司开始更多采用中国 AI 模型 |
不知道这个差距仅 6-9 个月是什么意思. 是说达到了 opus 4.6 的水平了吗?
3 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@zzz22333 #24 标题说的 ARM 开发平台, 总之就是那个意思.
3 days ago Replied to a topic by ujujzhaos › Claude › 今天 fable 还能用？ |
正在用
3 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@dosomethingcool 服务器有个缺点就是大多禁用虚拟化, 没法用 QEMU.
4 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@BingoXuan 这些问题都在 QEMU 里处理好了, 没用下来纯粹是因为 x86 上弄 ARM 实在太慢.
4 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@zzz22333 有问题的是官方的交叉编译套件, 不是调试有问题. 此外直接在服务器上调试舒服很多. 这些是技术选型问题, 另一回事. 我描述的内容就是文章里说的, 有没有适合小型开发的 ARM 主机.
4 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@tangping 使用下来体验如何呢? rk 板子搜评价的时候不少人说内核和驱动问题.
4 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@yxc246800 rk3588 好像有驱动这些问题, 性能很强但是怕又掉入一个坑.
4 days ago Replied to a topic by Folder › 问与答 › 2026 年的 ARM 开发平台选择 |
@lxrmido mac 跑 QEMU 的好处是同为 ARM 可以加速, 基本原生性能.
Select Language