Posts

Goals I am recently working on a computer vision task and need a large volume data to be downloaded and processed. However, it takes too much time working in a single thread. So, working in parrallel way in a HPC system would be a better choice. Understand the multiprocessing, subprocess, threading package in python The workflow for a MPI work Transfer to HPC Multiprocessing package: Process-based parallelism Pool object: parallelizing execution and distributing data (data parallelism) Basic example:...

Introduction Transformers have been tremendously successful in natural language processing tasks and other domains. Many variants have been suggested. Descriptions of transformers are usually graphical, verbal, partial, or incremental. No pseudocode has ever been published for any variant.

Mout a disk using gparted to format the disk to ext4 file system: sudo apt-get install gparted -> sudo gparted -> format the disk mount the disk to mountpoint, eg: sudo mount /dev/sda2 ~/HDD Permanently mounting: cat /etc/fstab to get UUID -> here change the ownership of the folder ~/HDD: sudo chown xxy ~/ vim cheatsheet Docker 1 2 3 4 5 1. build with `Dockerfile`: sudo docker build -t xxy ....

Here I would introduce how to use jupyter hub in HPC Introduction JupyterHub is the best way to serve Jupyter notebook for multiple users. Because jupyterhub manages a separate Jupyter encironment for each user, it can be used in a class of students, a corporate data scientific research group. It is a multi-user Hub that spawns, manages, and proxies multiple instances of the sinfle0user Jupyter notebook server. It offers distributions for different use cases....

1 2 3 4 5 X Error of failed request: GLXBadContext Major opcode of failed request: 152 (GLX) Minor opcode of failed request: 6 (X_GLXIsDirect) Serial number of failed request: 39 Current serial number in output stream: 38 Reproduce: on compute canada, with singularity, installed mesa-utils, libgl1-mesa-glx. 1 2 3 4 python from vedo import Plotter v = Plotter() v.show() Solution: use --nv args in singularity shell command. Experience: the mesa requires nvidia graphical card to run correctly....

what is pytorch lightning PyTorch Lightning is the deep learning framework with “batteries included” for professional AI researchers and machine learning engineers who need maximal flexibility while super-charging performance at scale. quick start Your browser does not support the video tag. summary steps: lightning module forward func configure optimizers def training_step def validation_step remove .cuda() backward and step as hook init lightning module init trainer add other functions as call back explanation about dataloader and sampler LightningDataModule was designed as a way of decoupling data-related hooks from the LightningDataModule, so you can develop dataset agonostic models....

Preface To understand the basics of the graph neural network, it can’t circumvent the topic of “Spectral-GNN”. Today, I’d like to deeply explore what the spectral GNN is and how does it works. Table of contents Theory part Basic theory 1 <The Emerging Field of Signal Processing on Graphs> challenges a “classical” signal $f(t)$ has a concept of “translate to the right by 3” to get $f(t-3)$. But for graph signal, it is not clear to say “translate by 3”....

Pedestrain trajectory Questions: 1. only pedestrain relation considered? hoe about environment 2. what is the general framework for pedestrain trajectory prediction. SGCN: Sparse Graph Convolution Network for Pedestrain Trajectory Prediction (CVPR2021) SGCN framework superfulous interactions: dense interaction -> one pedestrain is related to all other pedestrains while in fact it is not sparse undirected -> equal interactions for a pair of pedestrains spatial GCN -> sparse directed -> not all pedestrains + not equal interaction temporal GCN -> motion tendency Disentangled Multi-Relational Graph Convolutional Network for Pedestrian Trajectory Prediction (AAAI2021) Use CNN to generalize complex interpersonal relations a graph representation: node as pedestrian, edges correspond to distance challeges only simple social relationship like collision avoidance is aggregated modelling social norms is not suitable for determining the end-points of pedestrians in the last frame (over-avoidance) contributions disentangled multi-scale aggregation to clearly distinguish between relevant pedestrians multi-relational GCN to extract sophisticated social interaction in a scene....

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection From Point Clouds 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds Multi-Instance Point Cloud Registration by Efficient Correspondence Clustering Contrastive Boundary Learning for Point Cloud Segmentation Lepard: Learning Partial Point Cloud Matching in Rigid and Deformable Scenes CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding Density-Preserving Deep Point Cloud Compression Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients Neural Points: Point Cloud Representation With Neural Fields for Arbitrary Upsampling Not All Points Are Equal: Learning Highly Efficient Point-Based Detectors for 3D LiDAR Point Clouds Equivariant Point Cloud Analysis via Learning Orientations for Message Passing Point Cloud Pre-Training With Natural 3D Structures A Unified Query-Based Paradigm for Point Cloud Understanding REGTR: End-to-End Point Cloud Correspondences With Transformers 3DeformRS: Certifying Spatial Deformations on Point Clouds IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception Surface Reconstruction From Point Clouds by Learning Predictive Context Priors Point2Cyl: Reverse Engineering 3D Objects From Point Clouds to Extrusion Cylinders RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior Deterministic Point Cloud Registration via Novel Transformation Decomposition Surface Representation for Point Clouds 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection An MIL-Derived Transformer for Weakly Supervised Point Cloud Segmentation Why Discard if You Can Recycle?...

1 Jure Leskovec, Stanford CS224W: Machine Learning with Graphs, http://cs224w.stanford.edu Why graphs relations of entities Similar data points arbitrary sizes, no spatial index, no reference order representation learning Map nodes to d-dimensional embeddings-> similar nodes in the network are embedded close together Applications of Graph ML different tasks: Node classification Link prediction: knowledge graph completion Graph classification: molecule property prediction Clustering Graph generation Graph evolution: physical simulation Examples: node-level: Protein folding Recommender system: recommend related pins to users by edge level classification subgraph-level: traffic prediction: nodes: road segments, edges: connectivity between nodes-> predict time arrival etc graph-level: drug discovery: nodes: atoms, edges: chemical bonds....