A Python and PyTorch developer, deep-learning worker and open-source activist.
Created by the awesome tool. 😊
- 📝 I regulary write articles on https://www.yuque.com/lart
- 💬 Ask me about Python, PyTorch in ISSUES
- ⚡ Fun fact I am a boy.
- 双线性插值与均匀B-样条完全指南 - 2026-03-24: 本文重点探讨了线性插值与B-样条核函数的等价关系。文章从离散图像的本质出发,指出放大时需要在像素间进行插值计算。通过对比一维空间中的最近邻、线性和三次样条插值方...
- ArXiv 2603 | 用神经元胞自动机训练语言模型:合成数据能超越自然语言吗? - 2026-03-23: 作者认为,LLMs 中涌现的推理能力(few-shot learning、chain-of-thought 等),其本质依赖的是自然语言的底层计算结构,而非其语...
- ArXiv:2603 | Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights - 2026-03-20: 摘要: 本文提出了一种新颖视角,将预训练模型视为参数空间中的“专家灌木丛”(Neural Thickets),而非单一权重起点。研究发现,大型预训练模型周围的参...
- RWKV 的并行训练与 O(1) 推理 - 2026-03-19: 本文分析了Transformer注意力机制在推理时复杂度随序列长度线性增长的数学根源,指出softmax的全局归一化导致历史信息无法压缩。作为解决方案,RWKV...
- 位翻转排列 (Bit-Reversal Permutation) 解析 - 2026-02-24: 位翻转排列是一种将数据索引的二进制位完全倒置的重排操作,本质上是分治算法在底层数据划分上的投影。该技术广泛应用于快速傅里叶变换(FFT)等算法中,通过内存重排实...
- Monarch矩阵:从设计直觉到数学推导与实际应用 - 2026-02-24: Monarch矩阵是一种高效的矩阵参数化方法,旨在解决大模型中的计算和内存瓶颈。它结合块对角矩阵与排列操作,在保持硬件友好性的同时实现全局特征融合。Monarc...
- 从独立性、相关性到复杂动力系统 - 2026-02-23: 本文系统探讨了数据相关性分析的四个认知层级:线性相关(皮尔逊系数)捕捉严格比例关系,广义相关(斯皮尔曼系数)识别单调趋势,独立性检验(距离相关系数)判断变量是否...
- PyTorch 的统计三剑客:bucketize, bincount 与 histogram - 2026-01-13: 本文解析了PyTorch中三个易混淆的函数:torch.bucketize、torch.bincount和torch.histogram。bucketize用于...
- Welford 算法 | 优雅地计算海量数据的均值与方差 - 2025-12-23: 本文介绍了Welford在线算法,这是一种高效计算大数据集统计量的方法。针对内存不足时处理大规模数据的问题,文章对比了传统方差计算方法的缺陷(内存占用大、数值稳...
- 带噪学习 | Ambient Diffusion (NeurIPS 2023)下篇 - 2025-12-17: 本文介绍了Ambient Diffusion模型的采样过程,重点阐述了基于Tweedie公式的分数函数推导。通过分析前向过程的线性高斯特性,证明了分数函数$\n...
View the archives @ csdn@p_lart.
| Name | Stars | Description |
|---|---|---|
| Hands-on-Docker (中文) | 一份详尽的 Docker 使用指南。 | |
| Awesome-Class-Activation-Map | An awesome list of papers and tools about the class activation map (CAM) technology. | |
| PyTorchTricks | Some tricks of pytorch… | |
| MethodsCmp | A Simple Toolkit for Counting the FLOPs/MACs, Parameters and FPS of Pytorch-based Methods. | |
| PySODEvalToolkit | A Python-based salient object detection and video object segmentation evaluation toolbox. | |
| PySODMetrics | A simple and efficient implementation of SOD metrcis. | |
| PyLoss | Some loss functions for deeplearning. | |
| OpticalFlowBasedVOS | A simple and efficient codebase for the optical flow based video object segmentation. | |
| CoSaliencyProj | A project for co-saliency detection. Some codes are borrowed from ICNet. Thanks to ICNet Intra-saliency Correlation Network for Co-Saliency Detection (NIPS2020) | |
| RunIt | A simple program scheduler for your code on different devices. | |
| RegisterIt | Register it: A more flexible register for the DeepLearning project. | |
| mssim.pytorch | A better pytorch-based implementation for the mean structural similarity. Differentiable simpler SSIM and MS-SSIM. | |
| tta.pytorch | Test-Time Augmentation library for Pytorch. | |
| YuQueTools | A simple tool to download your own articles from yuque. | |
| ManageMyAttachments | Manage the attachments of your own obsidian vault. |
| Name | Description |
|---|---|
| lartpang/OVCamo | Open-Vocabulary Camouflaged Object Segmentation |
| yooweey/AugmentedIRSTD1kTestset | Augmented Testset of the IRSTD-1k dataset |




