PyTorch for Deep Learning Bootcamp
-
IntroductionPyTorch for Deep Learning Bootcamp Zero to Mastery0sCourse Welcome and What Is Deep Learning0sExercise: Meet Your Classmates + InstructorFree Course Book + Code Resources + Asking Questions + Getting HelpMachine Learning + Python MonthlyZTM Plugin + Understanding Your Video PlayerSet Your Learning Streak Goal
-
PyTorch FundamentalsWhy Use Machine Learning or Deep Learning0sThe Number 1 Rule of Machine Learning and What Is Deep Learning Good For0sMachine Learning vs. Deep Learning0sAnatomy of Neural Networks0sDifferent Types of Learning Paradigms0sWhat Can Deep Learning Be Used For0sWhat Is and Why PyTorch0sWhat Are Tensors0sWhat We Are Going To Cover With PyTorch0sHow To and How Not To Approach This Course0sImportant Resources For This Course0sGetting Setup to Write PyTorch Code0sIntroduction to PyTorch Tensors0sCreating Random Tensors in PyTorch0sCreating Tensors With Zeros and Ones in PyTorch0sCreating a Tensor Range and Tensors Like Other Tensors0sDealing With Tensor Data Types0sGetting Tensor Attributes0sManipulating Tensors (Tensor Operations)0sMatrix Multiplication (Part 1)0sMatrix Multiplication (Part 2): The Two Main Rules of Matrix Multiplication0sMatrix Multiplication (Part 3): Dealing With Tensor Shape Errors0sFinding the Min Max Mean and Sum of Tensors (Tensor Aggregation)0sFinding The Positional Min and Max of Tensors0sReshaping, Viewing and Stacking Tensors0sSqueezing, Unsqueezing and Permuting Tensors0sSelecting Data From Tensors (Indexing)0sPyTorch Tensors and NumPy0sPyTorch Reproducibility (Taking the Random Out of Random)0sDifferent Ways of Accessing a GPU in PyTorch0sSetting up Device-Agnostic Code and Putting Tensors On and Off the GPU0sPyTorch Fundamentals: Exercises and Extra-Curriculum0s
-
PyTorch WorkflowIntroduction and Where You Can Get Help0sGetting Setup and What We Are Covering0sCreating a Simple Dataset Using the Linear Regression Formula0sSplitting Our Data Into Training and Test Sets0sBuilding a function to Visualize Our Data0sCreating Our First PyTorch Model for Linear Regression0sBreaking Down What’s Happening in Our PyTorch Linear regression Model0sDiscussing Some of the Most Important PyTorch Model Building Classes0sChecking Out the Internals of Our PyTorch Model0sMaking Predictions With Our Random Model Using Inference Mode0sTraining a Model Intuition (The Things We Need)0sSetting Up an Optimizer and a Loss Function0sPyTorch Training Loop Steps and Intuition0sWriting Code for a PyTorch Training Loop0sReviewing the Steps in a Training Loop Step by Step0sRunning Our Training Loop Epoch by Epoch and Seeing What Happens0sWriting Testing Loop Code and Discussing What’s Happening Step by Step0sReviewing What Happens in a Testing Loop Step by Step0sWriting Code to Save a PyTorch Model0sWriting Code to Load a PyTorch Model0sSetting Up to Practice Everything We Have Done Using Device Agnostic code0sPutting Everything Together (Part 1): Data0sPutting Everything Together (Part 2): Building a Model0sPutting Everything Together (Part 3): Training a Model0sPutting Everything Together (Part 4): Making Predictions With a Trained Model0sPutting Everything Together (Part 5): Saving and Loading a Trained Model0sExercise: Imposter Syndrome0sPyTorch Workflow: Exercises and Extra-Curriculum
-
PyTorch Neural Network ClassificationIntroduction to Machine Learning Classification With PyTorch0sClassification Problem Example: Input and Output Shapes0sTypical Architecture of a Classification Neural Network (Overview)0sMaking a Toy Classification Dataset0sTurning Our Data into Tensors and Making a Training and Test Split0sLaying Out Steps for Modelling and Setting Up Device-Agnostic Code0sCoding a Small Neural Network to Handle Our Classification Data0sMaking Our Neural Network Visual0sRecreating and Exploring the Insides of Our Model Using nn.Sequential0sLoss Function Optimizer and Evaluation Function for Our Classification Network0sGoing from Model Logits to Prediction Probabilities to Prediction Labels0sCoding a Training and Testing Optimization Loop for Our Classification Model0sWriting Code to Download a Helper Function to Visualize Our Models Predictions0sDiscussing Options to Improve a Model0sCreating a New Model with More Layers and Hidden Units0sWriting Training and Testing Code to See if Our Upgraded Model Performs Better0sCreating a Straight Line Dataset to See if Our Model is Learning Anything0sBuilding and Training a Model to Fit on Straight Line Data0sEvaluating Our Models Predictions on Straight Line Data0sIntroducing the Missing Piece for Our Classification Model Non-Linearity0sBuilding Our First Neural Network with Non-Linearity0sWriting Training and Testing Code for Our First Non-Linear Model0sMaking Predictions with and Evaluating Our First Non-Linear Model0sReplicating Non-Linear Activation Functions with Pure PyTorch0sPutting It All Together (Part 1): Building a Multiclass Dataset0sCreating a Multi-Class Classification Model with PyTorch0sSetting Up a Loss Function and Optimizer for Our Multi-Class Model0sLogits to Prediction Probabilities to Prediction Labels with a Multi-Class Model0sTraining a Multi-Class Classification Model and Troubleshooting Code on the Fly0sMaking Predictions with and Evaluating Our Multi-Class Classification Model0sDiscussing a Few More Classification Metrics0sPyTorch Classification: Exercises and Extra-Curriculum0s
-
PyTorch Computer VisionWhat Is a Computer Vision Problem and What We Are Going to Cover0sComputer Vision Input and Output Shapes0sWhat Is a Convolutional Neural Network (CNN)0sDiscussing and Importing the Base Computer Vision Libraries in PyTorch0sGetting a Computer Vision Dataset and Checking Out Its- Input and Output Shapes0sVisualizing Random Samples of Data0sDataLoader Overview Understanding Mini-Batches0sTurning Our Datasets Into DataLoaders0sModel 0: Creating a Baseline Model with Two Linear Layers0sCreating a Loss Function: an Optimizer for Model 00sCreating a Function to Time Our Modelling Code0sWriting Training and Testing Loops for Our Batched Data0sWriting an Evaluation Function to Get Our Models Results0sSetup Device-Agnostic Code for Running Experiments on the GPU0sModel 1: Creating a Model with Non-Linear Functions0sMode 1: Creating a Loss Function and Optimizer0sTuring Our Training Loop into a Function0sTuring Our Testing Loop into a Function0sTraining and Testing Model 1 with Our Training and Testing Functions0sGetting a Results Dictionary for Model 10sModel 2: Convolutional Neural Networks High Level Overview0sModel 2: Coding Our First Convolutional Neural Network with PyTorch0sModel 2: Breaking Down Conv2D Step by Step0sModel 2: Breaking Down MaxPool2D Step by Step0sMode 2: Using a Trick to Find the Input and Output Shapes of Each of Our Layers0sModel 2: Setting Up a Loss Function and Optimizer0sModel 2: Training Our First CNN and Evaluating Its Results0sComparing the Results of Our Modelling Experiments0sMaking Predictions on Random Test Samples with the Best Trained Model0sPlotting Our Best Model Predictions on Random Test Samples and Evaluating Them0sMaking Predictions and Importing Libraries to Plot a Confusion Matrix0sEvaluating Our Best Models Predictions with a Confusion Matrix0sSaving and Loading Our Best Performing Model0sRecapping What We Have Covered Plus Exercises and Extra-Curriculum0s
-
PyTorch Custom DatasetWhat Is a Custom Dataset and What We Are Going to Cover0sImporting PyTorch and Setting Up Device Agnostic Code0sDownloading a Custom Dataset of Pizza, Steak and Sushi Images0sBecoming One With the Data (Part 1): Exploring the Data Format0sBecoming One With the Data (Part 2): Visualizing a Random Image0sBecoming One With the Data (Part 3): Visualizing a Random Image with Matplotlib0sTransforming Data (Part 1): Turning Images Into Tensors0sTransforming Data (Part 2): Visualizing Transformed Images0sLoading All of Our Images and Turning Them Into Tensors With ImageFolder0sVisualizing a Loaded Image From the Train Dataset0sTurning Our Image Datasets into PyTorch Dataloaders0sCreating a Custom Dataset Class in PyTorch High Level Overview0sCreating a Helper Function to Get Class Names From a Directory0sWriting a PyTorch Custom Dataset Class from Scratch to Load Our Images0sCompare Our Custom Dataset Class. to the Original Imagefolder Class0sWriting a Helper Function to Visualize Random Images from Our Custom Dataset0sTurning Our Custom Datasets Into DataLoaders0sExploring State of the Art Data Augmentation With Torchvision Transforms0sBuilding a Baseline Model (Part 1): Loading and Transforming Data0sBuilding a Baseline Model (Part 2): Replicating Tiny VGG from Scratch0sBuilding a Baseline Model (Part 3):Doing a Forward Pass to Test Our Model Shapes0sUsing the Torchinfo Package to Get a Summary of Our Model0sCreating Training and Testing loop Functions0sCreating a Train Function to Train and Evaluate Our Models0sTraining and Evaluating Model 0 With Our Training Functions0sPlotting the Loss Curves of Model 00sThe Balance Between Overfitting and Underfitting and How to Deal With Each0sCreating Augmented Training Datasets and DataLoaders for Model 10sConstructing and Training Model 10sPlotting the Loss Curves of Model 10sPlotting the Loss Curves of All of Our Models Against Each Other0sPredicting on Custom Data (Part 1): Downloading an Image0sPredicting on Custom Data (Part 2): Loading In a Custom Image With PyTorch0sPredicting on Custom Data (Part3):Getting Our Custom Image Into the Right Format0sPredicting on Custom Data (Part4):Turning Our Models Raw Outputs Into Prediction0sPredicting on Custom Data (Part 5): Putting It All Together0sSummary of What We Have Covered Plus Exercises and Extra-Curriculum0s
-
PyTorch Going ModularWhat Is Going Modular and What We Are Going to Cover0sGoing Modular Notebook (Part 1): Running It End to End0sDownloading a Dataset0sWriting the Outline for Our First Python Script to Setup the Data0sCreating a Python Script to Create Our PyTorch DataLoaders0sTurning Our Model Building Code into a Python Script0sTurning Our Model Training Code into a Python Script0sTurning Our Utility Function to Save a Model into a Python Script0sCreating a Training Script to Train Our Model in One Line of Code0sGoing Modular: Summary, Exercises and Extra-Curriculum0s
-
PyTorch Transfer LearningIntroduction: What is Transfer Learning and Why Use It0sWhere Can You Find Pretrained Models and What We Are Going to Cover0sInstalling the Latest Versions of Torch and Torchvision0sDownloading Our Previously Written Code from Going Modular0sDownloading Pizza, Steak, Sushi Image Data from Github0sTurning Our Data into DataLoaders with Manually Created Transforms0sTurning Our Data into DataLoaders with Automatic Created Transforms0sWhich Pretrained Model Should You Use0sSetting Up a Pretrained Model with Torchvision0sDifferent Kinds of Transfer Learning0sGetting a Summary of the Different Layers of Our Model0sFreezing the Base Layers of Our Model and Updating the Classifier Head0sTraining Our First Transfer Learning Feature Extractor Model0sPlotting the Loss curves of Our Transfer Learning Model0sOutlining the Steps to Make Predictions on the Test Images0sCreating a Function Predict On and Plot Images0sMaking and Plotting Predictions on Test Images0sMaking a Prediction on a Custom Image0sMain Takeaways, Exercises and Extra- Curriculum0s
-
PyTorch Experiment TrackingWhat Is Experiment Tracking and Why Track Experiments0sGetting Setup by Importing Torch Libraries and Going Modular Code0sCreating a Function to Download Data0sTurning Our Data into DataLoaders Using Manual Transforms0sTurning Our Data into DataLoaders Using Automatic Transforms0sPreparing a Pretrained Model for Our Own Problem0sSetting Up a Way to Track a Single Model Experiment with TensorBoard0sTraining a Single Model and Saving the Results to TensorBoard0sExploring Our Single Models Results with TensorBoard0sCreating a Function to Create SummaryWriter Instances0sAdapting Our Train Function to Be Able to Track Multiple Experiments0sWhat Experiments Should You Try0sDiscussing the Experiments We Are Going to Try0sDownloading Datasets for Our Modelling Experiments0sTurning Our Datasets into DataLoaders Ready for Experimentation0sCreating Functions to Prepare Our Feature Extractor Models0sCoding Out the Steps to Run a Series of Modelling Experiments0sRunning Eight Different Modelling Experiments in 5 Minutes0sViewing Our Modelling Experiments in TensorBoard0sLoading the Best Model and Making Predictions on Random Images from the Test Set0sMaking a Prediction on Our Own Custom Image with the Best Model0sMain Takeaways, Exercises and Extra- Curriculum0s
-
PyTorch Paper ReplicatingWhat Is a Machine Learning Research Paper?0sWhy Replicate a Machine Learning Research Paper?0sWhere Can You Find Machine Learning Research Papers and Code?0sWhat We Are Going to Cover0sGetting Setup for Coding in Google Colab0sDownloading Data for Food Vision Mini0sTurning Our Food Vision Mini Images into PyTorch DataLoaders0sVisualizing a Single Image0sReplicating a Vision Transformer – High Level Overview0sBreaking Down Figure 1 of the ViT Paper0sBreaking Down the Four Equations Overview and a Trick for Reading Papers0sBreaking Down Equation 10sBreaking Down Equation 2 and 30sBreaking Down Equation 40sBreaking Down Table 10sCalculating the Input and Output Shape of the Embedding Layer by Hand0sTurning a Single Image into Patches (Part 1: Patching the Top Row)0sTurning a Single Image into Patches (Part 2: Patching the Entire Image)0sCreating Patch Embeddings with a Convolutional Layer0sExploring the Outputs of Our Convolutional Patch Embedding Layer0sFlattening Our Convolutional Feature Maps into a Sequence of Patch Embeddings0sVisualizing a Single Sequence Vector of Patch Embeddings0sCreating the Patch Embedding Layer with PyTorch0sCreating the Class Token Embedding0sCreating the Class Token Embedding – Less Birds0sCreating the Position Embedding0sEquation 1: Putting it All Together0sEquation 2: Multihead Attention Overview0sEquation 2: Layernorm Overview0sTurning Equation 2 into Code0sChecking the Inputs and Outputs of Equation0sEquation 3: Replication Overview0sTurning Equation 3 into Code0sTransformer Encoder Overview0sCombining equation 2 and 3 to Create the Transformer Encoder0sCreating a Transformer Encoder Layer with In-Built PyTorch Layer0sBringing Our Own Vision Transformer to Life – Part 1: Gathering the Pieces0sBringing Our Own Vision Transformer to Life – Part 2: The Forward Method0sGetting a Visual Summary of Our Custom Vision Transformer0sCreating a Loss Function and Optimizer from the ViT Paper0sTraining our Custom ViT on Food Vision Mini0sDiscussing what Our Training Setup Is Missing0sPlotting a Loss Curve for Our ViT Model0sGetting a Pretrained Vision Transformer from Torchvision and Setting it Up0sPreparing Data to Be Used with a Pretrained ViT0sTraining a Pretrained ViT Feature Extractor Model for Food Vision Mini0sSaving Our Pretrained ViT Model to File and Inspecting Its Size0sDiscussing the Trade-Offs Between Using a Larger Model for Deployments0sMaking Predictions on a Custom Image with Our Pretrained ViT0sPyTorch Paper Replicating: Main Takeaways, Exercises and Extra-Curriculum0s
-
PyTorch Model DeploymentWhat is Machine Learning Model Deployment – Why Deploy a Machine Learning Model0sThree Questions to Ask for Machine Learning Model Deployment0sWhere Is My Model Going to Go?0sHow Is My Model Going to Function?0sSome Tools and Places to Deploy Machine Learning Models0sWhat We Are Going to Cover0sGetting Setup to Code0sDownloading a Dataset for Food Vision Mini0sOutlining Our Food Vision Mini Deployment Goals and Modelling Experiments0sCreating an EffNetB2 Feature Extractor Model0sCreate a Function to Make an EffNetB2 Feature Extractor Model and Transforms0sCreating DataLoaders for EffNetB20sTraining Our EffNetB2 Feature Extractor and Inspecting the Loss Curves0sSaving Our EffNetB2 Model to File0sGetting the Size of Our EffNetB2 Model in Megabytes0sCollecting Important Statistics and Performance Metrics for Our EffNetB2 Model0sCreating a Vision Transformer Feature Extractor Model0sCreating DataLoaders for Our ViT Feature Extractor Model0sTraining Our ViT Feature Extractor Model and Inspecting Its Loss Curves0sSaving Our ViT Feature Extractor and Inspecting Its Size0sCollecting Stats About Our-ViT Feature Extractor0sOutlining the Steps for Making and Timing Predictions for Our Models0sCreating a Function to Make and Time Predictions with Our Models0sMaking and Timing Predictions with EffNetB20sMaking and Timing Predictions with ViT0sComparing EffNetB2 and ViT Model Statistics0sVisualizing the Performance vs Speed Trade-off0sGradio Overview and Installation0sGradio Function Outline0sCreating a Predict Function to Map Our Food Vision Mini Inputs to Outputs0sCreating a List of Examples to Pass to Our Gradio Demo0sBringing Food Vision Mini to Life in a Live Web Application0sGetting Ready to Deploy Our App Hugging Face Spaces Overview0sOutlining the File Structure of Our Deployed App0sCreating a Food Vision Mini Demo Directory to House Our App Files0sCreating an Examples Directory with Example Food Vision Mini Images0sWriting Code to Move Our Saved EffNetB2 Model File0sTurning Our EffNetB2 Model Creation Function Into a Python Script0sTurning Our Food Vision Mini Demo App Into a Python Script0sCreating a Requirements File for Our Food Vision Mini App0sDownloading Our Food Vision Mini App Files from Google Colab0sUploading Our Food Vision Mini App to Hugging Face Spaces Programmatically0sRunning Food Vision Mini on Hugging Face Spaces and Trying it Out0sFood Vision Big Project Outline0sPreparing an EffNetB2 Feature Extractor Model for Food Vision Big0sDownloading the Food 101 Dataset0sCreating a Function to Split Our Food 101 Dataset into Smaller Portions0sTurning Our Food 101 Datasets into DataLoaders0sTraining Food Vision Big: Our Biggest Model Yet!0sOutlining the File Structure for Our Food Vision Big0sDownloading an Example Image and Moving Our Food Vision Big Model File0sSaving Food 101 Class Names to a Text File and Reading them Back In0sTurning Our EffNetB2 Feature Extractor Creation Function into a Python Script0sCreating an App Script for Our Food Vision Big Model Gradio Demo0sZipping and Downloading Our Food Vision Big App Files0sDeploying Food Vision Big to Hugging Face Spaces0sPyTorch Mode Deployment: Main Takeaways, Extra-Curriculum and Exercises0s
-
Introduction to PyTorch 2.0 and torch.compileIntroduction to PyTorch 2.00sWhat We Are Going to Cover and PyTorch 2 Reference Materials0sGetting Started with PyTorch 2 in Google Colab0sPyTorch 2.0 – 30 Second Intro0sGetting Setup for PyTorch 20sGetting Info from Our GPUs and Seeing if They’re Capable of Using PyTorch 20sSetting the Default Device in PyTorch 20sDiscussing the Experiments We Are Going to Run for PyTorch 20sCreating a Function to Setup Our Model and Transforms0sDiscussing How to Get Better Relative Speedups for Training Models0sSetting the Batch Size and Data Size Programmatically0sGetting More Potential Speedups with TensorFloat-320sDownloading the CIFAR10 Dataset0sCreating Training and Test DataLoaders0sPreparing Training and Testing Loops with Timing Steps for PyTorch 2.0 timing0sExperiment 1 – Single Run without torch.compile0sExperiment 2 – Single Run with torch.compile0sComparing the Results of Experiment 1 and 20sSaving the Results of Experiment 1 and 20sPreparing Functions for Experiment 3 and 40sExperiment 3 – Training a Non-Compiled Model for Multiple Runs0sExperiment 4 – Training a Compiled Model for Multiple Runs0sComparing the Results of Experiment 3 and 40sPotential Extensions and Resources to Learn More0s
-
Where To Go From Here?
What is PyTorch and why should I learn it?
PyTorch is a machine learning and deep learning framework written in Python.
PyTorch enables you to craft new and use existing state-of-the-art deep learning algorithms like neural networks powering much of today’s Artificial Intelligence (AI) applications.
Plus it’s so hot right now, so there’s lots of jobs available!
PyTorch is used by companies like:
-
Tesla to build the computer vision systems for their self-driving cars
-
Meta to power the curation and understanding systems for their content timelines
-
Apple to create computationally enhanced photography.
Want to know what’s even cooler?
Much of the latest machine learning research is done and published using PyTorch code so knowing how it works means you’ll be at the cutting edge of this highly in-demand field.
And you’ll be learning PyTorch in good company.
Graduates of Zero To Mastery are now working at Google, Tesla, Amazon, Apple, IBM, Uber, Meta, Shopify + other top tech companies at the forefront of machine learning and deep learning.
This can be you.
By enrolling today, you’ll also get to join our exclusive live online community classroom to learn alongside thousands of students, alumni, mentors, TAs and Instructors.
Most importantly, you will be learning PyTorch from a professional machine learning engineer, with real-world experience, and who is one of the best teachers around!
What will this PyTorch course be like?
This PyTorch course is very hands-on and project based. You won’t just be staring at your screen. We’ll leave that for other PyTorch tutorials and courses.
In this course you’ll actually be:
-
Running experiments
-
Completing exercises to test your skills
-
Building real-world deep learning models and projects to mimic real life scenarios
By the end of it all, you’ll have the skillset needed to identify and develop modern deep learning solutions that Big Tech companies encounter.
Fair warning: this course is very comprehensive. But don’t be intimidated, Daniel will teach you everything from scratch and step-by-step!
Here’s what you’ll learn in this PyTorch course:
1. PyTorch Fundamentals — We start with the barebone fundamentals, so even if you’re a beginner you’ll get up to speed.
In machine learning, data gets represented as a tensor (a collection of numbers). Learning how to craft tensors with PyTorch is paramount to building machine learning algorithms. In PyTorch Fundamentals we cover the PyTorch tensor datatype in-depth.
2. PyTorch Workflow — Okay, you’ve got the fundamentals down, and you’ve made some tensors to represent data, but what now?
With PyTorch Workflow you’ll learn the steps to go from data -> tensors -> trained neural network model. You’ll see and use these steps wherever you encounter PyTorch code as well as for the rest of the course.
3. PyTorch Neural Network Classification — Classification is one of the most common machine learning problems.
-
Is something one thing or another?
-
Is an email spam or not spam?
-
Is credit card transaction fraud or not fraud?
With PyTorch Neural Network Classification you’ll learn how to code a neural network classification model using PyTorch so that you can classify things and answer these questions.
4. PyTorch Computer Vision — Neural networks have changed the game of computer vision forever. And now PyTorch drives many of the latest advancements in computer vision algorithms.
For example, Tesla use PyTorch to build the computer vision algorithms for their self-driving software.
With PyTorch Computer Vision you’ll build a PyTorch neural network capable of seeing patterns in images of and classifying them into different categories.
5. PyTorch Custom Datasets — The magic of machine learning is building algorithms to find patterns in your own custom data. There are plenty of existing datasets out there, but how do you load your own custom dataset into PyTorch?
This is exactly what you’ll learn with the PyTorch Custom Datasets section of this course.
You’ll learn how to load an image dataset for FoodVision Mini: a PyTorch computer vision model capable of classifying images of pizza, steak and sushi (am I making you hungry to learn yet?!).
We’ll be building upon FoodVision Mini for the rest of the course.
6. PyTorch Going Modular — The whole point of PyTorch is to be able to write Pythonic machine learning code.
There are two main tools for writing machine learning code with Python:
-
A Jupyter/Google Colab notebook (great for experimenting)
-
Python scripts (great for reproducibility and modularity)
In the PyTorch Going Modular section of this course, you’ll learn how to take your most useful Jupyter/Google Colab Notebook code and turn it reusable Python scripts. This is often how you’ll find PyTorch code shared in the wild.
7. PyTorch Transfer Learning — What if you could take what one model has learned and leverage it for your own problems? That’s what PyTorch Transfer Learning covers.
You’ll learn about the power of transfer learning and how it enables you to take a machine learning model trained on millions of images, modify it slightly, and enhance the performance of FoodVision Mini, saving you time and resources.
8. PyTorch Experiment Tracking — Now we’re going to start cooking with heat by starting Part 1 of our Milestone Project of the course!
At this point you’ll have built plenty of PyTorch models. But how do you keep track of which model performs the best?
That’s where PyTorch Experiment Tracking comes in.
Following the machine learning practitioner’s motto of experiment, experiment, experiment! you’ll setup a system to keep track of various FoodVision Mini experiment results and then compare them to find the best.
9. PyTorch Paper Replicating — The field of machine learning advances quickly. New research papers get published every day. Being able to read and understand these papers takes time and practice.
So that’s what PyTorch Paper Replicating covers. You’ll learn how to go through a machine learning research paper and replicate it with PyTorch code.
At this point you’ll also undertake Part 2 of our Milestone Project, where you’ll replicate the groundbreaking Vision Transformer architecture!
10. PyTorch Model Deployment — By this stage your FoodVision model will be performing quite well. But up until now, you’ve been the only one with access to it.
How do you get your PyTorch models in the hands of others?
That’s what PyTorch Model Deployment covers. In Part 3 of your Milestone Project, you’ll learn how to take the best performing FoodVision Mini model and deploy it to the web so other people can access it and try it out with their own food images.
What’s the bottom line?
Machine learning’s growth and adoption is exploding, and deep learning is how you take your machine learning knowledge to the next level. More and more job openings are looking for this specialized knowledge.
Companies like Tesla, Microsoft, OpenAI, Meta (Facebook + Instagram), Airbnb and many others are currently powered by PyTorch.
And this is the most comprehensive online bootcamp to learn PyTorch and kickstart your career as a Deep Learning Engineer.
So why wait? Advance your career and earn a higher salary by mastering PyTorch and adding deep learning to your toolkit?
What's included
- 52 hours on-demand video
- 7 articles
- Access on mobile and TV
- Certificate of completion