👨🏻💻 With support for more than 200 different mathematical operations, PyTorch is one of the most powerful open source and computational libraries based on Python for machine learning. You don't need to look for different sources to learn this popular library, but the website of this library covers more than what you need.💯
2️⃣ Here, I will teach you how to learn PyTorch from scratch in 4 steps. 👌🏼
1️⃣Text tutorial: If you don't know anything about Python, you should start learning from here. ⬅️Topics: tensors, datasets and DataLoader, model building, optimization loop, saving, loading and using the model.
2️⃣Video training: This section is very useful for those who prefer video content. ⬅️Topics: introduction, tensor construction and model construction with pytorch.
4️⃣Coding: This step is vital! Your theoretical knowledge is worthless without coding! The Keras website is full of sample code that is great for getting started.
The course is regularly supplemented with practical problems and slides. The author Xavier Bresson is a professor at the National University of Singapore.
🔺The best GitHub repositories for learning Python ✅Learn Python for Data Science in 2024
👨🏻💻 In the latest data science report 2024 , Python is still the top programming language for data science with 56.7% . Here I have put a list of the best Python repositories for data science , which will improve your coding skills and guide you on the path to data science mastery.💯
1️⃣Learn Python 3 repo 🖥 A collection of Jupyter notebooks for learning Python. 🐱GitHub repo link
2️⃣The Algorithms repo 🖥 All algorithms implemented in Python for training. 🐱GitHub repo link
3️⃣Awesome Python repo 🖥 A list of great Python frameworks, libraries, software, and resources. 🐱GitHub repo link
4️⃣100 Days of ML repo 🖥 Learning algorithms and building neural networks without any programming experience. 🐱GitHub repo link
5️⃣Cosmic Python book repo 🖥 A book on Python's functional architectural patterns for managing complexity. 🐱GitHub repo link
6️⃣A Byte of Python book repo 🖥 If you do not learn Python programming, start with this book. 🐱GitHub repo link
7️⃣Python Machine Learning book repo 🖥 Python Machine Learning book code repository. 🐱GitHub repo link
8️⃣Repo of interactive interview challenges 🖥 120+ interactive Python coding interview challenges. 🐱GitHub repo link
9️⃣Repo of coding problems 🖥 Solutions for various coding/algorithmic problems. 🐱GitHub repo link
1️⃣Python Basics repo 🖥 A list of 300 Python interview questions + answer sheet. 🐱GitHub repo link
1️⃣Python programming exercises repo 🖥 100+ challenging Python programming exercises. 🐱GitHub repo link 〰️〰️〰️〰️〰️〰️〰️〰️〰️〰️〰️ 😠 More likes 💦➡️ more posts ✈️http://t.me/codeprogrammer✅
In 1989, Yann LeCun and his team trained a LeNet 1 CNN, which was able to detect handwriting.
They published a video showing how this model can read the numbers that were written manually on a piece of paper, and then the model gives the numbers electronically.
The Convolution Neural Network CNN algorithm is considered one of the algorithms that has influenced the world and we find it nowadays in many fields.
In general, everything that can be predicted from an image or video is a CNN. Many researchers relied on this algorithm and derived many of the most famous models from it (ResNet, DenseNet, MobileNet, SqueezeNet, VGG)
There are many models that come under the name CNN 〰️〰️〰️〰️〰️〰️〰️〰️〰️〰️〰️ 😠 More likes 💦➡️ more posts ✈️http://t.me/codeprogrammer✅
🟢 Yaoliang Yu, a professor at the School of Computer Science at the University of Waterloo, Canada, has published several free data science courses. These courses include machine learning, data science optimization, linear algebra and deep learning.
✅ The resources of each course include textbooks, assignments, articles and projects during the course.
🔖Guide to free data science courses at the University of Waterloo:
📌PyTorch Sentiment Analysis - analysis of the emotional component of the text
This repository contains different implementations of text analysis in PyTorch: 🔄 using a “bag of words” 🟰 using a recurrent neural network (RNN) ♾ via convolutional neural network (CNN) 🔍 with the help of fashionable transformers
🖥deepface - Python library for facial recognition and more
- pip install deepface
⏩ deepface is a lightweight Python library that allows you to find faces and analyze various attributes from photographs: age, gender, emotions. It incorporates the best of the VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, ArcFace, Dlib, SFace and GhostFaceNet models.
⏩ This is how you can compare the similarity of 2 faces, the result is in the image:
from deepface import DeepFace result = DeepFace.verify(img1_path = "img1.jpg", img2_path = "img2.jpg")
Featuretools is a Python library for automated feature development, i.e. defining variables from the data set for training the ML model. Featuretools excels at converting temporal and relational datasets into feature matrices for machine learning.
🌟Step-by-step implementation of the Transformer architecture
This laptop describes in as much detail as possible each step of implementing a transformer from scratch, with the necessary theoretical minimum For complete enlightenment, you can combine it with video 3b1b