maxzcl的博客

content summarized by title, easy read, good stuff.

paper: https://arxiv.org/pdf/2309.06180.pdfrepo: GitHub - vllm-project/vllm: A high-throughput and memory-efficient inference and serving engine for LLMshighlights blog by authors: vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention | vLLM BlogLLMs

DeConv fundamentals

SourceGRU stands for Gated Recurrent Unit, which is a type of recurrent neural network (RNN) architecture that is similar to LSTM (Long Short-Term Memory).Like LSTM, GRU is designed to model sequential data by allowing information to be selectively remembe

paper: https://owainevans.github.io/reversal_curse.pdfblog with interactions with the authors: Paper: LLMs trained on “A is B” fail to learn “B is A” — LessWrongThis is a linkpost for https://owainevans.github.io/reversal_curse.pdfThis post is the copy of

​AI image generation is the most recent AI capability blowing people’s minds (mine included). The ability to create striking visuals from text descriptions has a magical quality to it and points clearly to a shift in how humans create art.

For beginners, the most daunting aspect of deep learning algorithms is perhaps Back-Propagations (BP) which require derivations of some highly complex mathematical expressions.Luckily when actually implementing BP, we do not have to rely on smmary symbolic

efficientaccurate。

Paper:TorchSparse: Efficient Point Cloud Inference EngineNotation:Mappingto get output position set:when down-sampling, since we want to sample as manysparse input sites as possible, we slack the SSC i/o mapping condition to p < s*...

Review:2D sparsity in DNNsSparsity in Deep Learning_EverNoob的博客-优快云博客==> the above mentioned 2Dsparsity is decidedly different from the 3D sparsity situation, in that we manually created the structured sparsity to cut down memory footprint, whil.

Definitionsource：http://arxiv.org/abs/1708.02002v2AFocal Lossfunction addresses class imbalance during training in tasks like object detection. Focal loss applies a modulating term to the cross entropy loss in order to focus learning on hard miscla...

Cross Entropyhttps://en.wikipedia.org/wiki/Cross_entropyCross Entropy Losshttps://towardsdatascience.com/cross-entropy-loss-function-f38c4ec8643eA Gentle Introduction to Cross-Entropy for Machine Learning

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric SpacePointNet++[arXiv version][Code and Data (GitHub)]AbstractFew prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. Howeve.

Non-maximum Suppression (NMS)A technique to filter the predictions of object detectors.https://towardsdatascience.com/non-maximum-suppression-nms-93ce178e177cTypical Object detection pipeline has onecomponentfor generating proposals for classificat..

Selective Search Explained | Papers With CodeSelective Searchis a region proposal algorithm for object detection tasks. It starts by over-segmenting the image based on intensity of the pixels using a graph-based segmentation method by Felzenszwalb and ..

Intro videohttps://www.youtube.com/watch?v=vr5rs_cTKCs(short summary)https://towardsdatascience.com/object-detection-explained-r-cnn-a6c813937a7613.8. Region-based CNNs (R-CNNs) — Dive into Deep Learning 0.17.5 documentationVariants:https://t..

RoI is a technique/layer introduced in Fast-RCNN paper:https://arxiv.org/abs/1504.08083here is an easy to read intro:Understanding Region of Interest (RoI Pooling) - Blog by Kemal Erdem==> in short, RoI projection shrinks RoI after CNNpre-proces..

PointNetPaper Highlights Figure 1.Applications of PointNet.We propose a novel deep net architecture that consumes raw point cloud (set of points) without voxelization or rendering. It is a unified architecture that learns both global and local po...

for basics on point cloud, see:(3D Imaging) Point Cloud_EverNoob的博客-优快云博客Moving Point Cloud Processing: PointRNNhttps://arxiv.org/abs/1910.08287In this paper, we introduce a Point Recurrent Neural Network (PointRNN) for moving point cloud process

SOTA* Overview*[Submitted on 31 Jan 2021]Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkshttps://arxiv.org/abs/2102.00554The growing energy and performance costs of deep learning have driven th.

https://en.wikipedia.org/wiki/Point_cloudApoint cloudis a set of datapointsinspace. The points may represent a3D shapeor object. Each pointpositionhas its set ofCartesian coordinates(X, Y, Z).[1]Point clouds are generally produced by3D scan...

Introhttps://en.wikipedia.org/wiki/Physics-informed_neural_networksPhysics-informed neural networks(PINNs) are a type of universal function approximators that can embed the knowledge of any physical laws that govern a given data-set in the learning p.

Understanding the backward pass through Batch Normalization LayerFlair of Machine LearningPosted on February 12, 2016(for intro and howit possibly could work, see: Batch Normalization_EverNoob的博客-优快云博客)(for a concise mathematical solution, see: B.

Wiki Introhttps://en.wikipedia.org/wiki/Batch_normalization==> this wiki article is techinical enough for further reference on related concepts and deeper looksBatch normalization(also known asbatch norm) is a method used to makeartificial neu...

ByAhmed Fawzy GadTo evaluate object detection models like R-CNN andYOLO, themean average precision (mAP)is used. The mAP compares the ground-truth bounding box to the detected box and returns a score. The higher the score, the more accurate the model...

tutorial: from BrilliantMy Favorite Algorithm: Linear Time Median FindingThanks to random internet strangers, you can also read this post in:RussianFinding the median in a list seems like a trivial problem, but doing so in linear time turns out to b.

Definitionhttps://en.wikipedia.org/wiki/Grayscale#Converting_colour_to_grayscalehttps://en.wikipedia.org/wiki/Grayscale#Converting_colour_to_grayscaleIndigital photography,computer-generated imagery, andcolorimetry, agrayscaleimageis one in which t...

1. alignSize()+ n - 1 ensures the >= sz condition, while(n) & (-1 * n) get rid of the sign, andas n = 1 << N,sz + n - 1 ensures a sz' divisible by n is included in the range and & n will get rid of remainder bits.2. sobel/

Resources:https://en.wikipedia.org/wiki/Epipolar_geometryhttps://en.wikipedia.org/wiki/Epipolar_geometryEpipolar geometryhttps://homepages.inf.ed.ac.uk/rbf/CVonline/LOCAL_COPIES/OWENS/LECT10/node3.htmla more light-hearted intro:Introduction to Epipolar G

Summary:双线性插值(Bilinear Interpolation) - 马语者 - 博客园Intro:一篇文章为你讲透双线性插值 - 知乎双线性插值(Bilinear Interpolation)：双线性插值是用原图像中4(2*2)个点计算新图像中1个点，效果略逊于双三次插值，速度比双三次插值快，属于一种平衡美，在很多框架中属于默认算法。1. Nearest Interpolation最近邻法不需要计算只需要寻找原图中对应的点，所以最近邻法速度最快，但是会破坏原图像中.

Basic Intro:Wikipediahttps://en.wikipedia.org/wiki/Semi-global_matchingpaper:https://core.ac.uk/reader/11134866?utm_source=linkoutSemi-global matchingFrom Wikipedia, the free encyclopediaSemi-global matching(SGM) is acomputer visionalgorithm...

from: ​​​​​​What Is int8 Quantization and Why Is It Popular for Deep Neural Networks? - MATLAB & SimulinkWhat Is int8 Quantization and Why Is It Popular for Deep Neural Networks?By Ram Cherukuri, MathWorksDeep learning deployment on the edge for

4-bit introduction paper:https://papers.nips.cc/paper/2020/file/13b919438259814cd5be8cb45877d577-Paper.pdf4-bit CNN paper:https://arxiv.org/pdf/2009.06488.pdfshort news articles:https://medium.com/swlh/4-bit-deep-learning-d1614c0883e3https://towa..

the format names describe the storage scheme exactly, NCHW is consecutive in image (HW) then channel, while NHWC is consecutive is point-expansion (C) then image.example:“TensorFlow performance and advance topics”explanation:gpu - How much faster .

Computer Architecture: Dataflow/Systolic Arrayshttps://en.wikipedia.org/wiki/Systolic_arrayKung, H.T. and Leiserson, C.E. Algorithms for VLSI processor arrays. Chapter in Introduction to VLSI systems by C. Mead and L. Conway. Addison-Wesley, Reading, M

InterfacefromOpenCV: Geometric Image Transformations◆warpAffine()void cv::warpAffine ( InputArray src, OutputArray dst, InputArray M, Size dsize, int flags=INTER_LINEAR, int...

from:Coppersmith–Winograd algorithm - HandWikiInlinear algebra, theCoppersmith–Winograd algorithm, named after Don Coppersmith andShmuel Winograd, was the asymptotically fastest knownmatrix multiplication algorithmfrom 1990 until 2010. It can multi...

Morphologyhttps://en.wikipedia.org/wiki/Mathematical_morphologyDilationhttps://en.wikipedia.org/wiki/Dilation_(morphology)Dilated Convolution Example​​​​​​https://towardsdatascience.com/understanding-2d-dilated-convolution-operation-with-examples

basic intro：https://blog.youkuaiyun.com/qq_38410730/article/details/81667885博客园，弗兰克的猫背包合集【动态规划】01背包问题【动态规划】01背包问题【续】【动态规划】完全背包问题【动态规划】多重背包问题【动态规划】一次搞定三种背包问题 //summaryanother good summary:https://zhuanlan.zhihu.com/p/93857890?utm_source=wec...

fromhttps://www.cxyxiaowu.com/2869.html作者：李威题目描述给定一个字符串 s，找到 s 中最长的回文子串。你可以假设 s 的最大长度为 1000。示例1：输入:"babad"输出:"bab"注意:"aba"也是一个有效答案。示例2：输入:"cbbd"输出:"bb"方法一：暴力匹配 （Brute Force）根据回文子串的定义，枚举所有长度大于等于2的子串，依次判断它们是否是回文。在具体实现时，可以只针...