PyTorch Ultimate 2024- From Basics to Cutting-Edge

PyTorch Ultimate 2024: From Basics to Cutting-Edge, available at $89.99, has an average rating of 4.75, with 176 lectures, based on 483 reviews, and has 17952 subscribers.

You will learn about learn all relevant aspects of PyTorch from simple models to state-of-the-art models deploy your model on-premise and to Cloud Transformers Natural Language Processing (NLP), e.g. Word Embeddings, Zero-Shot Classification, Similarity Scores CNNs (Image-, Audio-Classification; Object Detection) Style Transfer Recurrent Neural Networks Autoencoders Generative Adversarial Networks Recommender Systems adapt top-notch algorithms like Transformers to custom datasets develop CNN models for image classification, object detection, Style Transfer develop RNN models, Autoencoders, Generative Adversarial Networks learn about new frameworks (e.g. PyTorch Lightning) and new models like OpenAI ChatGPT use Transfer Learning This course is ideal for individuals who are Python developers willing to learn one of the most interesting and in-demand techniques It is particularly useful for Python developers willing to learn one of the most interesting and in-demand techniques.

Enroll now: PyTorch Ultimate 2024: From Basics to Cutting-Edge

Summary

Title: PyTorch Ultimate 2024: From Basics to Cutting-Edge

Price: $89.99

Average Rating: 4.75

Number of Lectures: 176

Number of Published Lectures: 176

Number of Curriculum Items: 176

Number of Published Curriculum Objects: 176

Original Price: $199.99

Quality Status: approved

Status: Live

What You Will Learn

learn all relevant aspects of PyTorch from simple models to state-of-the-art models

deploy your model on-premise and to Cloud

Transformers

Natural Language Processing (NLP), e.g. Word Embeddings, Zero-Shot Classification, Similarity Scores

CNNs (Image-, Audio-Classification; Object Detection)

Style Transfer

Recurrent Neural Networks

Autoencoders

Generative Adversarial Networks

Recommender Systems

adapt top-notch algorithms like Transformers to custom datasets

develop CNN models for image classification, object detection, Style Transfer

develop RNN models, Autoencoders, Generative Adversarial Networks

learn about new frameworks (e.g. PyTorch Lightning) and new models like OpenAI ChatGPT

use Transfer Learning

Who Should Attend

Python developers willing to learn one of the most interesting and in-demand techniques

Target Audiences

Python developers willing to learn one of the most interesting and in-demand techniques

PyTorch is a Python framework developed by Facebook to develop and deploy Deep Learning models. It is one of the most popular Deep Learning frameworks nowadays.

In this course you will learn everything that is needed for developing and applying Deep Learning models to your own data. All relevant fields like Regression, Classification, CNNs, RNNs, GANs, NLP, Recommender Systems, and many more are covered. Furthermore, state of the art models and architectures  like Transformers, YOLOv7, or ChatGPT are presented.

It is important to me that you learn the underlying concepts as well as how to implement the techniques. You will be challenged to tackle problems on your own, before I present you my solution.

In my course I will teach you:

Introduction to Deep Learning

high level understanding

perceptrons

layers

activation functions

loss functions

optimizers

Tensor handling

creation and specific features of tensors

automatic gradient calculation (autograd)

Modeling introduction, incl.

Linear Regression from scratch

understanding PyTorch model training

Batches

Datasets and Dataloaders

Hyperparameter Tuning

saving and loading models

Classification models

multilabel classification

multiclass classification

Convolutional Neural Networks

CNN theory

develop an image classification model

layer dimension calculation

image transformations

Audio Classification with torchaudio and spectrograms

Object Detection

object detection theory

develop an object detection model

YOLO v7, YOLO v8

Faster RCNN

Style Transfer

Style transfer theory

developing your own style transfer model

Pretrained Models and Transfer Learning

Recurrent Neural Networks

Recurrent Neural Network theory

developing LSTM models

Recommender Systems with Matrix Factorization

Autoencoders

Transformers

Understand Transformers, including Vision Transformers (ViT)

adapt ViT to a custom dataset

Generative Adversarial Networks

Semi-Supervised Learning

Natural Language Processing (NLP)

Word Embeddings Introduction

Word Embeddings with Neural Networks

Developing a Sentiment Analysis Model based on One-Hot Encoding, and GloVe

Application of Pre-Trained NLP models

Model Debugging

Hooks

Model Deployment

deployment strategies

deployment to on-premise and cloud, specifically Google Cloud

Miscellanious Topics

ChatGPT

ResNet

Extreme Learning Machine (ELM)

Enroll right now to learn some of the coolest techniques and boost your career with your new skills.

Best regards,

Bert

Course Curriculum

Chapter 1: Course Overview & System Setup

Lecture 1: Course Overview

Lecture 2: PyTorch Introduction

Lecture 3: System Setup

Lecture 4: How to Get the Course Material

Lecture 5: Additional Information for Mac-Users

Lecture 6: Setting up the conda environment

Lecture 7: General Environment Setup Error Handling

Lecture 8: How to work with the course

Chapter 2: Machine Learning

Lecture 1: Artificial Intelligence (101)

Lecture 2: Machine Learning (101)

Lecture 3: Machine Learning Models (101)

Chapter 3: Deep Learning Introduction

Lecture 1: Deep Learning General Overview

Lecture 2: Deep Learning Modeling 101

Lecture 3: Performance

Lecture 4: From Perceptron to Neural Network

Lecture 5: Layer Types

Lecture 6: Activation Functions

Lecture 7: Loss Functions

Lecture 8: Optimizers

Chapter 4: Model Evaluation

Lecture 1: Underfitting Overfitting (101)

Lecture 2: Train Test Split (101)

Lecture 3: Resampling Techniques (101)

Chapter 5: Neural Network from Scratch (opt. but highly recommended)

Lecture 1: Section Overview

Lecture 2: NN from Scratch (101)

Lecture 3: Calculating the dot-product (Coding)

Lecture 4: NN from Scratch (Data Prep)

Lecture 5: NN from Scratch Modeling __init__ function

Lecture 6: NN from Scratch Modeling Helper Functions

Lecture 7: NN from Scratch Modeling forward function

Lecture 8: NN from Scratch Modeling backward function

Lecture 9: NN from Scratch Modeling optimizer function

Lecture 10: NN from Scratch Modeling train function

Lecture 11: NN from Scratch Model Training

Lecture 12: NN from Scratch Model Evaluation

Chapter 6: Tensors

Lecture 1: Section Overview

Lecture 2: From Tensors to Computational Graphs (101)

Lecture 3: Tensor (Coding)

Chapter 7: PyTorch Modeling Introduction

Lecture 1: Section Overview

Lecture 2: Linear Regression from Scratch (Coding, Model Training)

Lecture 3: Linear Regression from Scratch (Coding, Model Evaluation)

Lecture 4: Model Class (Coding)

Lecture 5: Exercise: Learning Rate and Number of Epochs

Lecture 6: Solution: Learning Rate and Number of Epochs

Lecture 7: Batches (101)

Lecture 8: Batches (Coding)

Lecture 9: Datasets and Dataloaders (101)

Lecture 10: Datasets and Dataloaders (Coding)

Lecture 11: Saving and Loading Models (101)

Lecture 12: Saving and Loading Models (Coding)

Lecture 13: Model Training (101)

Lecture 14: Hyperparameter Tuning (101)

Lecture 15: Hyperparameter Tuning (Coding)

Chapter 8: Classification Models

Lecture 1: Section Overview

Lecture 2: Classification Types (101)

Lecture 3: Confusion Matrix (101)

Lecture 4: ROC curve (101)

Lecture 5: Multi-Class 1: Data Prep

Lecture 6: Multi-Class 2: Dataset class (Exercise)

Lecture 7: Multi-Class 3: Dataset class (Solution)

Lecture 8: Multi-Class 4: Network Class (Exercise)

Lecture 9: Multi-Class 5: Network Class (Solution)

Lecture 10: Multi-Class 6: Loss, Optimizer, and Hyper Parameters

Lecture 11: Multi-Class 7: Training Loop

Lecture 12: Multi-Class 8: Model Evaluation

Lecture 13: Multi-Class 9: Naive Classifier

Lecture 14: Multi-Class 10: Summary

Lecture 15: Multi-Label (Exercise)

Lecture 16: Multi-Label (Solution)

Chapter 9: CNN: Image Classification

Lecture 1: Section Overview

Lecture 2: CNNs (101)

Lecture 3: CNN (Interactive)

Lecture 4: Image Preprocessing (101)

Lecture 5: Image Preprocessing (Coding)

Lecture 6: Binary Image Classification (101)

Lecture 7: Binary Image Classification (Coding)

Lecture 8: MultiClass Image Classification (Exercise)

Lecture 9: MultiClass Image Classification (Solution)

Lecture 10: Layer Calculations (101)

Lecture 11: Layer Calculations (Coding)

Chapter 10: CNN: Audio Classification

Lecture 1: Audio Classification (101)

Lecture 2: Audio Classification (Exercise)

Lecture 3: Audio Classification (Exploratory Data Analysis)

Lecture 4: Audio Classification (Data Prep-Solution)

Lecture 5: Audio Classification (Model-Solution)

Chapter 11: CNN: Object Detection

Lecture 1: Section Overview

Lecture 2: Accuracy Metrics (101)

Lecture 3: Object Detection (101)

Lecture 4: Object Detection with detecto (Coding)

Lecture 5: Training a Model on GPU for free (Coding)

Instructors

Bert Gollnick
Data Scientist

Rating Distribution

1 stars: 5 votes

2 stars: 2 votes

3 stars: 29 votes

4 stars: 115 votes

5 stars: 332 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!