About

Applications

Houdini Unreal Engine Unity 3D Nuke Maya Blender ZBrush Python Mixed Reality Machine Learning Graphic Design Extras

Site created with Notion, Super & Cluster

Notes

ML Python

Amazon EC2 Instance

Computer Vision

Classification

Hardware & Driver Setup

NVIDIA CUDA Toolkit

Installation

Install NVIDIA CUDA Toolkit: https://developer.nvidia.com/cuda-toolkit

Temp CUDA Toolkit Install directory


C:\Users\<username>\AppData\Local\Temp\CUDA

The install process adds the CUDA_PATH, CUDA_PATH_V<version#>, and other System Variables to the Environment Variables, including the specified bin directory to the Path System Variable.
Install also confirms the following are installed:

Nsight for Visual Studio 2019
Nsight Monitor

GPU Confirmation

Once installed, build the included deviceQuery_vs2019.sln in VS, and run the resulting deviceQuery.exe via CMD to confirm GPU recognition. The following output confirms GPU recognition.

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v11.2\bin\win64\Debug>deviceQuery.exe
deviceQuery.exe Starting...

CUDA Device Query (Runtime API) version (CUDART static linking)

Detected 1 CUDA Capable device(s)

Device 0: "Quadro RTX 6000"
CUDA Driver Version / Runtime Version          11.2 / 11.2
CUDA Capability Major/Minor version number:    7.5
Total amount of global memory:                 24576 MBytes (25769803776 bytes)
(72) Multiprocessors, ( 64) CUDA Cores/MP:     4608 CUDA Cores
GPU Max Clock rate:                            1770 MHz (1.77 GHz)
Memory Clock rate:                             7001 Mhz
Memory Bus Width:                              384-bit
L2 Cache Size:                                 6291456 bytes
Maximum Texture Dimension Size (x,y,z)         1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers  1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers  2D=(32768, 32768), 2048 layers
Total amount of constant memory:               65536 bytes
Total amount of shared memory per block:       49152 bytes
Total shared memory per multiprocessor:        65536 bytes
Total number of registers available per block: 65536
Warp size:                                     32
Maximum number of threads per multiprocessor:  1024
Maximum number of threads per block:           1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size    (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch:                          2147483647 bytes
Texture alignment:                             512 bytes
Concurrent copy and kernel execution:          Yes with 6 copy engine(s)
Run time limit on kernels:                     Yes
Integrated GPU sharing Host Memory:            No
Support host page-locked memory mapping:       Yes
Alignment requirement for Surfaces:            Yes
Device has ECC support:                        Enabled
CUDA Device Driver Mode (TCC or WDDM):         WDDM (Windows Display Driver Model)
Device supports Unified Addressing (UVA):      Yes
Device supports Managed Memory:                Yes
Device supports Compute Preemption:            Yes
Supports Cooperative Kernel Launch:            Yes
Supports MultiDevice Co-op Kernel Launch:      No
Device PCI Domain ID / Bus ID / location ID:   0 / 33 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >

deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 11.2, CUDA Runtime Version = 11.2, NumDevs = 1
Result = PASS

Resources

UCI ML Repo

archive.ics.uci.edu

Google Colaboratory

colab.research.google.com

TensorBoard

www.tensorflow.org

AWS Documentation

docs.aws.amazon.com

Deep (TensorFlow) Playground

playground.tensorflow.org

MNIST Dataset

yann.lecun.com

Image Kernels

setosa.io

OpenAI

openai.com

CIFAR-10 Dataset

www.cs.toronto.edu

Kubernetes (K8)

kubernetes.io

Kubeflow

www.kubeflow.org

Google Dev Pathways

developers.google.com

An Introduction to Statistical Learning

www.statlearning.com

YOLO: Real-Time Object Detection

pjreddie.com

move.ai

www.move.ai

respeecher

www.respeecher.com

Modules

nltk (Natural Language Toolkit)

www.nltk.org

Library for working with natural language data, as in use with Natural Language Processing

Keras

keras.io

Python deep-learning framework and TF module.

Spark

spark.apache.org

Engine for big data processing

Hadoop

hadoop.apache.org

Open-source library for big data management

TensorFlow

www.tensorflow.org

TensorFlow 3D

ai.googleblog.com

Open source framework for 3D object detection, semantic segmentation, and instance segmentation models.

gensim

pypi.org

Framework for vector space modelling; document indexing.

OpenCV

opencv.org

Open Source Computer Vision (OpenCV); library for real-time computer vision (images/videos).

OpenAI Gym

gym.openai.com

Reinforcement learning toolkit.

TFX

www.tensorflow.org

Production scale ML platform and framework.

Acronyms

Abbreviation	Definition
PCA	Principal Component Analysis
NCE	Noise Contrastive Estimation
CBOW	Continuous Bag of Words
ELU	Exponential Linear Unit
CNN	Convolutional Neural Network
RNN	Recurrent Neural Network
LSTM	Long Short Term Memory
VQA	Visual Question Answering
IID	Independent & Identically Distributed
SGD	Stochastic Gradient Descent
AMI	Amazon Machine Image
EC2	Elastic Compute Cloud
DAG	Directed Acyclic Graph
HDFS	Hadoop Distributed File System
RDD	Resilient Distributed Dataset
MAE	Mean Absolute Error
RMSE	Root Mean Squared Error
MSE	Mean Squared Error
RELU	Rectified Linear Unit
NN	Neural Network
TF	Term Frequency
IDF	Inverse Document Frequency
NLP	Natural Language Processing
EDA	Exploratory Data Analysis
CRD	Custom Resource Definition
ROI	Region of Interest
MIL	Multiple Instance Learning

On This Page

Notes
Hardware & Driver Setup
NVIDIA CUDA Toolkit
Installation
GPU Confirmation
Resources
Modules
Acronyms

Machine Learning

Notes

Notes

Hardware & Driver Setup

NVIDIA CUDA Toolkit

Installation

GPU Confirmation

Resources

Resources

Modules

Libraries

Acronyms

Acronyms