Discover and read the best of Twitter Threads about #100DaysOfMLCode

Most recents (24)


"roc_auc_score" is defined as the area under the ROC curve, which is the curve having False Positive Rate on the x-axis and True Positive Rate on the y-axis at all classification thresholds.

#DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python
Read 17 tweets
Following tips may boost model performance across different network structures with up to 5% (mAP or mean Average Precision) without increasing computational costs in any way.

#computervision #pytorch #deeplearning #deeplearningai #100daysofmlcode #neuralnetworks #AI
Visually Coherent Image Mix-up for Object Detection. This has already been proven to be successful in lessening adversarial fears in network classification after testing it on COCO 2017 and PASCAL datasets with YOLOv3 models.
#computervision #pytorch
Read 13 tweets
Types of magic commands

Line magics - starts with % character. Rest of the line is its argument passed without parentheses or quotes.

Cell magics - %% - can operate on multiple lines below their call.
#DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist
Read 21 tweets

GauGAN2 combines segmentation mapping, inpainting and text-to-image generation in a single model

#Computervision #AI #ArtificialIntelligence #TensorFlow #PyTorch #DeepLearning #DataScience #MachineLearning #100DaysOfMLCode #Python #DataScientist #Statistics #Mathematics

Unlike GauGAN1 the GauGAN2 can translate natural language descriptions into landscape images. Typing a phrase like “sunset at a beach” generates the scene

#Computervision #AI #ArtificialIntelligence #TensorFlow #PyTorch #DeepLearning #DataScience #MachineLearning #Math
Read 7 tweets
Image interpolation occurs when you resize or distort your image from one pixel grid to another.


#computervision #IMAGE #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #programming #Math #Stat #dataviz #DataAnalytics #AI #ArtificialIntelligence #data
Image interpolation works in two directions, and tries to achieve a best approximation of a pixel's intensity based on the values at surrounding pixels.


#computervision #IMAGE #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python #programming #Math #Stat
Image resizing is necessary when you need to increase or decrease the total number of pixels, whereas remapping can occur when you are correcting for lens distortion or rotating an image.

#computervision #DataScience #MachineLearning #DeepLearning #100DaysOfMLCode #Python
Read 8 tweets
20 GitHub Repos that Helps You to Win Hacktoberfest

A thread 🧵 👇
1. Free Programming Books

In this repository, you can contribute by sharing free e-books books 📚

Discover free programming books from different languages, contribute your favourite ones if missing, making it more valuable.…
2. 📒 App Ideas Collection

A collection of ideas to make a beginner life lot easier, make it more valuable by adding more ideas into it.…
Read 22 tweets
Hey Reader, I hope you are having a good day and will have a great life from now on.

Realized that I messed up the thread for day 4 so gonna tweet that again.
Day 4 of #100DaysOfCode

1) List Comprehension:
is a useful way to create lists when elements obey simple rule.
e.g cubes = [i**3 for i in range(10)]
With conditional
cubes = [i**3 for i in range(10) if i%2==0]
2) String Formatting:
Syntax: 'some string {0} {1} {2}'.format(value1,value2,value3)
msg = "{0} is my friend,{0} is my best friend. His nickname is {1} {2}".format('Bob','Tony','-hehe')
format can have any data that needs to be printed out.
Read 7 tweets
Day 3 of #100DaysOfCode
Motivation, Don't Repeat Yourself.

1)Defining a function
def function_name(parameters_if_any):
"""indentation identifies the code block of a function"""
return data_if_any
Parameters: are variables in function definition.
Arguments: are the values put into parameters when functions are called.
Calling a function: function_name(arguments_if_any)
These are the codes written to perform useful tasks. Some modules are already part of standard library and others need to be

-To import an existing module e.g. math
import math #imports whole math module
Read 15 tweets
Sunday Morning Reading Thread ☕️

- Self-Supervised Learning: The Dark Matter of Intelligence 🧠
- SEER ⚙️
- Multimodal Neurons 👁️📚
- Do Transformer Modifications Transfer? ⚔️
- Ultra Data-Efficient GAN 🤯

Quote from each below: 👇
Self-Supervised Learning: The Dark Matter of Intelligence 🧠

"As babies, we learn how the world works largely by observation. We form generalized predictive models about objects in the world by learning concepts such as object permanence and gravity"…
Self-Supervised Pretraining of Visual Features in the Wild ⚙️

"a RegNetY with 1.3B parameters trained on 1B random images with 512 GPUs achieves 84.2% top-1 accuracy, surpassing the best self-supervised pretrained model by 1%"
Read 7 tweets
Bringing back AI Weekly Update! 🎉
Here is a preview/curation for March 8th (#27):

- Multimodal Neurons
- SSL: The Dark Matter of Intelligence
- SEER (x2)
- Generative Adversarial Transformers
- Ultra Data-Efficient GAN Training

Links Below: 👇
Multimodal Neurons…
Wikipedia Image-Text Dataset…
Read 21 tweets

SQL(stands for Structured Query Language)is the popular query language to manage databases. So, here is a collection of the most asked SQL interview questions to help you prepare

Please Like & Retweet

🧵A Thread 🧵

#SQL #Coding
What is Database?

A database is an organized collection of data, stored and retrieved digitally from a remote or local computer system. Databases can be vast and complex, and such databases are developed using fixed design and modeling approaches.

#100DaysOfCode #SQL #Coding
What is DBMS?

DBMS stands for Database Management System. DBMS is a system software responsible for the creation, retrieval, updating, and management of the database.

#100DaysOfCode #SQL #Coding
Read 24 tweets
👋 CNN get easier to understand if you consider how we solve word puzzles (An illustrative thread) 👇🏾

#100DaysOfMLCode Image
Neural Networks came back into limelight when Prof. Yan Lecun introduced a mathematical operation, called convolution, in one of the layers of a digit recognition model. For NNs, it just turned the world upside down
Most of the AI Applications that we see today are based on convolutional neural networks (CNN).
Read 12 tweets
Don't know where and how to start with ML?

#100daysOfMLCode #100daysOfCode

🧵This is my journey so far👇
1️⃣ I started with ML during my master's degree.

I decided to try to build a model of my guitar amplifier.

I started with this course:…
2️⃣ After I finished it I started playing around with Keras and scikit-learn to build a model of my guitar amplifier.

It took 72 hours of recording, 250+ hours of training, and 6 months of experimenting to conclude - ML algorithms like NN won't produce anything useful.
Read 12 tweets
☁️ AWS is a great choice for a startup

Here are some reasons why

#100daysOfCode #100daysOfMLCode #AWS

1️⃣ Free tier

Most of the services offer free tier for first 12 months since registration.

There are enough free resources per month that you're able to build MVP for almost free.
2️⃣ Designed for scalability

All of their services are designed with scalability in mind.

You can scale your startup business without limits.
Read 8 tweets
Don't know how to land your first tech job?

It's not easy but it's possible

🧵This is how I did it👇

#100daysOfCode #100daysOfMLCode
It was starting my master's at university in electrical engineering.

For some reason, I decided to try to get a job as a software engineer to increase my income.

I knew how to program in Matlab & C. It was enough to pass exams but not enough to build a project from scratch.
I decided to learn the basics of Javascript, PHP, and Laravel.

I built a couple of small and simple projects (e.g. web page for my band with Laravel).

I searched for open positions in my town. I didn't meet more than 25% of the requirements for any of them.
Read 8 tweets
🤷‍♂️You've learned basics of Python and you don't know what to do next?

How to go from "hello world" to real applications?

🧵 This one is for you👇

#100daysOfCode #100DaysOfMLCode #Python
1️⃣ Build expense tracker CLI app.

Each expense should have following attributes:
* title (string)
* amount (float)
* created_at (date)
* tags (list of strings)

Store expenses in TXT file.

Cover: Add expense, list expenses, get expense, edit expense, delete expense
2️⃣ Add database

Instead to storing/reading in/from TXT file start using SQLite.

Write script to copy all of the existing expenses from TXT file to database.

Don't use ORM at this point.
Read 14 tweets
Python is a great choice for the main backend programming language in a startup

Here are some reasons why

#100daysOfCode #100daysOfMLCode #Python #Startup

1️⃣ Easy to write & easy to read

It reads and writes almost like the English language. You need a small amount of code to get a job done. You'll probably rewrite it at least 3 times.
2️⃣ 1st class citizen on cloud platforms

You don't want to deal with physical servers in a startup. You just want to run your app. Python has cloud SDK libraries, it runs on serverless platforms, it's used in ML services, a lot of examples in cloud docs are using Python.
Read 7 tweets
One Of The Most Common Misconceptions People Starting Out With Machine Learning Have Is,

You Need An Expensive Laptop With A Good GPU To Train Machine Learning Models.

Lets Break Down This Misconception And Why It Is False👇🧵

#100DaysOfMLCode #MachineLearning #CodeNewbie #AI
Introducing Google Colab.

Now What Is @GoogleColab?

This Is What Their Documentation Says :

"Colab allows anybody to write and execute arbitrary python code through the browser, and is especially well suited to machine learning, data analysis and education."

In Simple Words,

Google Colab Let's You Write Python Code In the Browser And Executes It On Their Cloud CPU, GPU or TPU.

How Does This Help Us In Any Way?

Read 6 tweets
Want to become a Data Scientist? Here are some great resources that you should watch in order;Statistics & Linear Algebra Not Included 🧵
#100DaysOfCode #100DaysOfMLCode #DataScience #AI #MachineLearning #ArtificialIntelligence #ML #Coding #Coders #PyTorch #Tensorflow #Developer
Part 1 of Microsoft's Intro to Python Series:
Gets you up and running in python and introduces you to the basics of setting up your development environment.…
Continuation of the series above.…
Read 17 tweets
📌Do you wonder why so many AI projects fail in the real world?

Every AI developer should read this!


#AI #DeepLearning #100DaysOfCode #100DaysOfMLCode #Python #javascript
We all imagine AI developer as a geek solving math equations all day. The funny thing is AI developers imagine exactly the same. We just want to be left alone with our models and develop in peace, but the real world doesn't work this way.
Business needs change often and we need to embrace it if we want it or not

The change in business needs means we have to change the goal of our algorithms to maximize the value we generate in the company. To give you an example imagine a company producing cookies
Read 16 tweets
Every AI developer starting to work in the real world should read this!


#AI #DeepLearning #100DaysOfCode #100DaysOfMLCode #Python #javascript
We all imagine AI developer as a geek solving math equations all day. The funny thing is AI developers imagine exactly the same. We just want to be left alone with our models and develop in peace, but the real world doesn't work this way.
Business needs change often and we need to embrace it if we want it or not

The change in business needs means we have to change the goal of our algorithms to maximize the value we generate in the company. To give you an example imagine a company producing cookies
Read 15 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!