The ‘PyTorch for Deep Learning with Python Bootcamp’ course will teach you how to create state of the art neural networks for deep learning with Facebook’s PyTorch Deep Learning library. In this course, you will learn how to use NumPy to format data into arrays and classic machine learning theory principals.
This course focuses on balancing important theory concepts with practical hands-on exercises and projects that let you learn how to apply the concepts in the course to your own data sets. The course is usually available for INR 2,799 on Udemy but you can click on the link and get the ‘PyTorch for Deep Learning with Python Bootcamp’ for INR 499.
Who all can opt for this course?
- Python developers those are intermediate to advanced and wish to learn PyTorch’s deep learning capabilities
Course Highlights
| Key Highlights | Details |
|---|---|
| Registration Link | Apply Now! |
| Price | INR 499 ( |
| Duration | 17 Hours |
| Rating | 4.7/5 |
| Student Enrollment | 25,499 students |
| Instructor | Jose Portilla https://www.linkedin.com/in/joseportilla |
| Topics Covered | PyTorch Basics, NumPy, Pandas, Artificial Neural Networks, Deep Learning |
| Course Level | Intermediate |
| Total Student Reviews | 3,888 |
Learning Outcomes
- Learn how to format data into arrays using NumPy
- For data cleaning and manipulation, use pandas
- Study the basic concepts of machine learning theory
- Use the PyTorch Deep Learning Library to classify images
- Recurrent neural networks for sequence time series data should be used with PyTorch
- Build cutting-edge Deep Learning models that can handle tabular data
Course Content
| S.No. | Module (Duration) | Topics |
|---|---|---|
| 1. | Course Overview, Installs, and Setup (25 minutes) | COURSE OVERVIEW LECTURE – PLEASE DO NOT SKIP! |
| Installation and Environment Setup | ||
| 2. | COURSE OVERVIEW CONFIRMATION CHECK (00 seconds) | DID YOU WATCH THE COURSE OVERVIEW LECTURE? |
| 3. | Crash Course: NumPy (46 minutes) | Introduction to NumPy |
| NumPy Arrays | ||
| NumPy Arrays Part Two | ||
| Numpy Index Selection | ||
| NumPy Operations | ||
| Numpy Exercises | ||
| Numpy Exercises – Solutions | ||
| 4. | Crash Course: Pandas (01 hour 13 minutes) | Pandas Overview |
| Pandas Series | ||
| Pandas DataFrames – Part One | ||
| Pandas DataFrames – Part Two | ||
| GroupBy Operations | ||
| Pandas Operations | ||
| Data Input and Output | ||
| Pandas Exercises | ||
| Pandas Exercises – Solutions | ||
| 5. | PyTorch Basics (54 minutes) | PyTorch Basics Introduction |
| Tensor Basics | ||
| Tensor Basics – Part Two | ||
| Tensor Operations | ||
| Tensor Operations – Part Two | ||
| PyTorch Basics – Exercise | ||
| PyTorch Basics – Exercise Solutions | ||
| 6. | Machine Learning Concepts Overview (46 minutes) | What is Machine Learning? |
| Supervised Learning | ||
| Overfitting | ||
| Evaluating Performance – Classification Error Metrics | ||
| Evaluating Performance – Regression Error Metrics | ||
| Unsupervised Learning | ||
| 7. | ANN – Artificial Neural Networks (04 hours 44 minutes) | Introduction to ANN Section |
| Theory – Perceptron Model | ||
| Theory – Neural Network | ||
| Theory – Activation Functions | ||
| Multi-Class Classification | ||
| Theory – Cost Functions and Gradient Descent | ||
| Theory – BackPropagation | ||
| PyTorch Gradients | ||
| Linear Regression with PyTorch | ||
| Linear Regression with PyTorch – Part Two | ||
| DataSets with PyTorch | ||
| Basic Pytorch ANN – Part One | ||
| Basic PyTorch ANN – Part Two | ||
| Basic PyTorch ANN – Part Three | ||
| Introduction to Full ANN with PyTorch | ||
| Full ANN Code Along – Regression – Part One – Feature Engineering | ||
| Full ANN Code Along – Regression – Part 2 – Categorical and Continuous Features | ||
| Full ANN Code Along – Regression – Part Three – Tabular Model | ||
| Full ANN Code Along – Regression – Part Four – Training and Evaluation | ||
| Full ANN Code Along – Classification Example | ||
| ANN – Exercise Overview | ||
| ANN – Exercise Solutions | ||
| 8. | CNN – Convolutional Neural Networks (04 hours 21 minutes) | Introduction to CNNs |
| Understanding the MNIST data set | ||
| ANN with MNIST – Part One – Data | ||
| ANN with MNIST – Part Two – Creating the Network | ||
| ANN with MNIST – Part Three – Training | ||
| ANN with MNIST – Part Four – Evaluation | ||
| Image Filters and Kernels | ||
| Convolutional Layers | ||
| Pooling Layers | ||
| MNIST Data Revisited | ||
| MNIST with CNN – Code Along – Part One | ||
| MNIST with CNN – Code Along – Part Two | ||
| MNIST with CNN – Code Along – Part Three | ||
| CIFAR-10 DataSet with CNN – Code Along – Part One | ||
| CIFAR-10 DataSet with CNN – Code Along – Part Two | ||
| Loading Real Image Data – Part One | ||
| Loading Real Image Data – Part Two | ||
| CNN on Custom Images – Part One – Loading Data | ||
| CNN on Custom Images – Part Two – Training and Evaluating Model | ||
| CNN on Custom Images – Part Three – PreTrained Networks | ||
| CNN Exercise | ||
| CNN Exercise Solutions | ||
| 9. | Recurrent Neural Networks (02 hours 10 minutes) | Introduction to Recurrent Neural Networks |
| RNN Basic Theory | ||
| Vanishing Gradients | ||
| LSTMS and GRU | ||
| RNN Batches Theory | ||
| RNN – Creating Batches with Data | ||
| Basic RNN – Creating the LSTM Model | ||
| Basic RNN – Training and Forecasting | ||
| RNN on a Time Series – Part One | ||
| RNN on a Time Series – Part Two | ||
| RNN Exercise | ||
| RNN Exercise – Solutions | ||
| 10. | Using a GPU with PyTorch and CUDA (30 minutes) | Why do we need GPUs? |
| Using GPU for PyTorch | ||
| 11. | NLP with PyTorch (01 hour 08 minutes) | Introduction to NLP with PyTorch |
| Encoding Text Data | ||
| Generating Training Batches | ||
| Creating the LSTM Model | ||
| Training the LSTM Model | ||
| OUR MODEL FOR DOWNLOAD | ||
| Generating Predictions | ||
| 12. | BONUS SECTION: THANK YOU! (10 seconds) | BONUS LECTURE |
Resources Required
- Knowledge of Python’s fundamental concepts (data types, loops, and functions) is advised
- Able to perform simple derivative computations
- Your computer’s admin permissions (ability to download our files)
Featured Review
Christopher Berry (5/5) : You couldn’t fault this course. The author explains everything perfectly for someone who has never been exposed to neural networks before. All of his courses are excellent, I think I own 12 of them.
Pros
- Dian Wei (5/5) : Excellent course, a lot of details were provided which helps a lot.
- Prasanta Dutta (5/5) : Though it is not the perfect time to rate the course.
- David Morgan (5/5) : This was a very good course for me, coming to it with intermediate Python skills.
- Abdoul Nasser Ibrahim (5/5) : this is a great course and I am once again convinced that Jose Portilla is the best udemy instructor in pyton and data science.
Cons
- Pratikkumar Prajapati (1/5) : His answers are late (2 weeks per reply) and his replies are out of context.
- Nikhil Gupta (2/5) : For example, batch size in calculations is hard coded and so the code breaks if used for another problem.
- Nikhil Gupta (2/5) : Although there is a small section towards the end that shows what changes are needed to run on GPU, there are a lot of changes that need to be made to the code “templated” to get it working.
- Nikhil Gupta (2/5) : Pros: The course provides some templates that can be sort of used for other problems.
About the Author
The instructor of this course is Jose Portilla who is a Head of Data Science at Pierian Training. With 4.6 Instructor Rating and 1,023,193 Reviews on Udemy, he/she offers 60 Courses and has taught 3,294,076 Students so far.
- Jose Marcial Portilla holds degrees in mechanical engineering from Santa Clara University (BS and MS), and he has years of experience working as a qualified instructor and trainer for Python programming, machine learning, and data science
- He has written articles and received patents in a number of disciplines, including data science, materials science, and microfluidics
- He has acquired a set of abilities for data analysis throughout the course of his career, and he wants to combine both his teaching and data science knowledge to educate others the power of programming, how to analyse data, and how to display the data in attractive visualisations
- He currently serves as the Head of Data Science for Pierian Training, where he trains people at prestigious organisations like General Electric, Cigna, The New York Times, Credit Suisse, McKinsey, and others in data science and python programming on-site
- Please click the website link to learn more about the available training options
Comparison Table
| Parameters | PyTorch for Deep Learning with Python Bootcamp | Tensorflow 2.0: Deep Learning and Artificial Intelligence | Complete Tensorflow 2 and Keras Deep Learning Bootcamp |
|---|---|---|---|
| Offers | INR 499 ( | INR 455 ( | INR 455 ( |
| Duration | 17 hours | 23.5 hours | 19 hours |
| Rating | 4.7/5 | 4.7/5 | 4.7/5 |
| Student Enrollments | 25,499 | 43,012 | 43,659 |
| Instructors | Jose Portilla | Lazy Programmer Inc. | Jose Portilla |
| Register Here | Apply Now! | Apply Now! | Apply Now! |
Leave feedback about this