OpenGenus IQ: Learn Algorithms, DL, System Design (Page 154)

PyTorch vs TensorFlow

We have compared PyTorch and TensorFlow on the basis of various metrics to help you determine the framework you should go forward with. In short, TensorFlow gives you more control and high computational efficiency while PyTorch gives you the simplicity to develop applications.

Machine Learning (ML)

Install and use NNVM Compiler

NNVM compiler is a graph compiler for the TVM Stack that takes in models in NNVM Intermediate Representation format and compiles them for various backends such as LLVM, METAL, CUDA and others. We have presented how to install and build NNVM from source and how to use it with the configurations

Machine Learning (ML)

NNVM Intermediate Representation

NNVM is a reusable graph Intermediate Representation stack for deep learning systems. It provides useful API to construct, represent and transform computation graphs to get most high-level optimization needed in deep learning. NNVM is a part of TVM stack for deep learning and has a compiler as well

Machine Learning (ML)

Run a ResNet34 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a ResNet34 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Run a ResNet18 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a ResNet18 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Run a ResNet101 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a ResNet101 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Run a ResNet152 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a ResNet152 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Run a ResNet50 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a ResNet50 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Run a VGG16 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a VGG16 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Run a VGG19 model in ONNX format on TVM Stack with LLVM backend

In this guide, we will run a VGG19 model in ONNX format on the TVM Stack with LLVM backend. You do not need any specialized equipment like GPU and TPU to follow this guide. A simple CPU is enough.

Machine Learning (ML)

Install TVM and NNVM from source

In this guide, we will walk you through the process of installing TVM and NNVM compiler from source along with all its dependencies such as HalideIR, DMLC-CORE, DLPACK and COMPILER-RT. Once installed, you can enjoy compiling models in any frameworks on any backend of your choice.

Machine Learning (ML)

TVM: A Deep Learning Compiler Stack

TVM is an open source deep learning compiler stack for CPUs, GPUs, and specialized accelerators that takes in models in various frameworks like TensorFlow, Keras, ONNX and others and deploys them on various backends like LLVM, CUDA, METAL and OpenCL. It gives comparably better performance than other

game theory

Traveler's dilemma

In game theory, the traveler's dilemma (abbreviated TD) is a type of non-zero-sum game in which two players attempt to maximize their own payoff, without any concern for the other player's payoff. We have presented the code and applications for Traveler's dilemma in O(1) time complexity.

Software Engineering

Git: git remote add command

git remote add command is a basic git command which add a remote repository as an origin of your local repository. The basic idea is that the remote repository is the final working repository which is considered by everyone and your local repository is your local copy holding your changes

git

Git: git commit command

git commit is a basic git command which saves the staged changes made to your local repository. We have explored how we can skip the add command and the information provided by the commit command of Git

git

Git diff command

Git diff command show changes between the working tree and the index or a tree, changes between the index and a tree, changes between two trees, changes between two blob objects, or changes between two files on disk.

git

Git add command: track a new file

In this article, we learnt how to track a new file in a project using Git. In the process, we explored the git add command to add a new file to tracking, touch command to create a new file and git status command on two different occasions to explore the status of the content tracked by Git.

git

Git Status command: File stages in Git

In this article, we have explored the various stages that a file assumes in Git. In the process, we came across tracked and untracked files and committed, modified and staged files and the significance of each stage in relation to git status.

git

Git: git status command

In this article, we have explored the git status command which gives us information regarding our current branch, remote repository, changes that have been staged for commit and changes that have not been staged for commit. In the process, we have explored the clear command as well.

git

Git: Initialize a Git repository

In this article, we have explored the procedure to initializing a new Git repository. In the process, we have explored the cd (change directory) command, git init command, cd .git command and ls command to explore the hidden files in the .git folder.

git

Git is a Map and SHA1 hash

Git is exactly a map data structure or more precisely a persistent map which maps blobs to hashes. We have demonstrated how Git is simply a hash map and with this view, its working is simplified.

git

Git is an Onion

Git version control is like an onion and has 4 layers namely a Distributed Revision Control System, a Revision Control System, a Simple Content Tracker and a Persistent Map. We have demonstrated its working based on the layers

bitwise operation

Algorithm to detect whether two numbers have opposite signs using bitwise operators

We present a bitwise algorithm to detect whether two numbers have opposite signs. This is important as using comparision based operations is slow and nearly all hardware support optimizations for bitwise operations

Algorithms

Maximize sum of consecutive differences in a circular array

Given an array A with values a1, a2, a3, a4, an Now, arrange all elements of array A such that sum of absolute differences of consecutive elements is maximum, i.e consider after an arrangement the array is b1, b2, b3, b4,..., bn then maximize |b1-b2| + |b2-b3| + |b3-b4| + .. + |bn-1-bn| + |bn-b1|

control statement

switch case control statement

A switch statement allows a variable to be tested for equality against a list of values. Each value is called a case, and the variable being switched on is checked for each case.if variable and case value are matched, then matched case will be executed.