Autoplay
Autocomplete
Previous Lesson
Complete and Continue
Machine Learning with Hugging Face Bootcamp: Zero to Mastery
Introduction
Machine Learning with Hugging Face Bootcamp: Zero to Mastery (1:48)
Exercise: Meet Your Classmates and Instructor
Understanding Your Video Player
Course Resources
Set Your Learning Streak Goal
Course Overview
Overview (5:02)
Project 0 - Introduction to Text Classification
Introduction to Text Classification (5:43)
What We're Going To Build! (7:21)
Project 0 - Let's Get Started!
Getting Setup: Adding Hugging Face Tokens to Google Colab (5:52)
Getting Setup: Importing Necessary Libraries to Google Colab (9:35)
Downloading a Text Classification Dataset from Hugging Face Datasets (16:00)
Project 0 - Preparing Text Data & Evaluation Metric
Preparing Text Data for Use with a Model - Part 1: Turning Our Labels into Numbers (12:48)
Preparing Text Data for Use with a Model - Part 2: Creating Train and Test Sets (6:18)
Preparing Text Data for Use with a Model - Part 3: Getting a Tokenizer (12:53)
Preparing Text Data for Use with a Model - Part 4: Exploring Our Tokenizer (10:26)
Preparing Text Data for Use with a Model - Part 5: Creating a Function to Tokenize Our Data (17:57)
Setting Up an Evaluation Metric (to measure how well our model performs) (8:53)
Let's Have Some Fun (+ More Resources)
Project 0 - Model Training
Introduction to Transfer Learning (a powerful technique to get good results quickly) (7:10)
Model Training - Part 1: Setting Up a Pretrained Model from the Hugging Face Hub (12:19)
Model Training - Part 2: Counting the Parameters in Our Model (12:27)
Model Training - Part 3: Creating a Folder to Save Our Model (3:53)
Model Training - Part 4: Setting Up Our Training Arguments with TrainingArguments (14:59)
Model Training - Part 5: Setting Up an Instance of Trainer with Hugging Face Transformers (5:05)
Model Training - Part 6: Training Our Model and Fixing Errors Along the Way (13:34)
Model Training - Part 7: Inspecting Our Models Loss Curves (14:39)
Model Training - Part 8: Uploading Our Model to the Hugging Face Hub (8:01)
Unlimited Updates
Project 0 - Making Predictions
Making Predictions on the Test Data with Our Trained Model (5:58)
Turning Our Predictions into Prediction Probabilities with PyTorch (12:48)
Sorting Our Model's Predictions by Their Probability (5:10)
Project 0 - Performing Inference
Performing Inference - Part 1: Discussing Our Options (9:40)
Performing Inference - Part 2: Using a Transformers Pipeline (one sample at a time) (10:01)
Performing Inference - Part 3: Using a Transformers Pipeline on Multiple Samples at a Time (Batching) (6:38)
Performing Inference - Part 4: Running Speed Tests to Compare One at a Time vs. Batched Predictions (10:33)
Performing Inference - Part 5: Performing Inference with PyTorch (12:06)
OPTIONAL - Putting It All Together: from Data Loading, to Model Training, to making Predictions on Custom Data (34:28)
Implement a New Life System
Project 0 - Launching Our Model!
Turning Our Model into a Demo - Part 1: Gradio Overview (3:47)
Turning Our Model into a Demo - Part 2: Building a Function to Map Inputs to Outputs (7:07)
Turning Our Model into a Demo - Part 3: Getting Our Gradio Demo Running Locally (6:46)
Making Our Demo Publicly Accessible - Part 1: Introduction to Hugging Face Spaces and Creating a Demos Directory (8:01)
Making Our Demo Publicly Accessible - Part 2: Creating an App File (12:14)
Making Our Demo Publicly Accessible - Part 3: Creating a README File (7:07)
Making Our Demo Publicly Accessible - Part 4: Making a Requirements File (3:33)
Making Our Demo Publicly Accessible - Part 5: Uploading Our Demo to Hugging Face Spaces and Making it Publicly Available (18:43)
Summary Exercises and Extensions (5:55)
Course Check-In
Project 1 - Building a Custom Object Detection Model with Hugging Face Transformers
Project 1 Overview and Resources
Introduction (10:03)
Setting Up Google Colab with Hugging Face Tokens (5:51)
Installing Necessary Dependencies (3:43)
Getting an Object Detection Dataset (7:37)
Inspecting the Features of Our Dataset (6:23)
Creating a Colour Palette to Visualize Our Classes (9:35)
Creating a Helper Function to Halve Our Image Sizes (4:24)
Creating a Helper Function to Halve Our Box Sizes (6:01)
Testing our Helper Functions (4:33)
Outlining the Steps to Draw Boxes on an Image (6:26)
Plotting Bounding Boxes on a Single Image Step by Step (19:04)
Different Bounding Box Formats (8:17)
Project 1 - Getting and Object Detection Model and Image Preprocessor
Getting an Object Detection Model (6:15)
Transfer Learning Overview (6:08)
Downloading our Model from the Hugging Face Hub and Trying it Out (9:26)
Inspecting the Layers of Our Model (6:53)
Counting the Number of Parameters in Our Model (10:54)
Creating a Function to Build Our Custom Model (13:15)
Passing a Single Image Sample Through Our Model - Part 1 (15:47)
OPTIONAL: Data Preprocessor Model Workflow (8:46)
Loading Our Models Image Preprocessor and Customizing it for Our Use Case (20:10)
Exercise: Imposter Syndrome (2:55)
Project 1 - Getting Hands-on with Different Bounding Box Formats
Bounding Box Formats 101
Discussing the Format Our Model Expects Our Annotations In (COCO) (6:17)
Creating Dataclasses to Hold the COCO Format (9:54)
Creating a Function to Turn Our Annotations into COCO Format (12:05)
Preprocessing a Single Image Sample and COCO Formatted Annotations (7:26)
Post Processing a Single Output (12:02)
Plotting a Single Post Processed Sample onto an Image (12:44)
Project 1 - OPTIONAL: Reproducing our Model's Post Processed Outputs by Hand
OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand - Part 1: Overview (10:44)
OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand - Part 2: Replicating Scores by Hand (28:32)
OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand - Part 3: Replicating Labels by Hand (12:32)
OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand - Part 4: Replicating Boxes by Hand Overview (10:23)
OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand - Part 5: Replicating Boxes by Hand Implementation (17:41)
OPTIONAL: Reproducing Our Models Post Processed Outputs by Hand - Part 6: Plotting Our Manual Post Processed Outputs on an Image (6:44)
Project 1 - Preparing our Data for Training our Object Detection Model
Preparing Our Data at Scale - Part 1: Concept Overview (9:21)
Preparing Our Data at Scale - Part 2: Creating Train Validation and Test Splits (12:13)
Preparing Our Data at Scale - Part 3: Preprocessing Multiple Samples at a Time Overview (8:16)
Preparing our Data at Scale - Part 4: Making a Function to Preprocess Multiple Samples at a Time (21:37)
Preparing our Data at Scale - Part 5: Applying Our Preprocessing Function to Our Datasets (9:37)
Preparing Our Data at Scale - Part 6: Creating a Data Collation Function (12:20)
Project 1 - Training a Custom Object Detection Model for Trashify
Training a Custom Model - Part 1: Overview (7:42)
Training a Custom Model - Part 2: Creating a Model and Folder to Save Our Model to (4:11)
Training a Custom Model - Part 3: Creating TrainingArguments for Our Model Overview (12:53)
Training a Custom Model - Part 4: Creating our First TrainingArguments (11:11)
Training a Custom Model - Part 5: Finishing Off the TrainingArguments (12:39)
Training a Custom Model - Part 6: OPTIONAL - Creating a Custom Optimizer for Different Learning Rates (16:05)
Training a Custom Model - Part 7: Creating an Evaluation Function for Our Model Overview (13:09)
Training a Custom Model - Part 8: Creating an Evaluation Function for Our Model Targets Processing (22:49)
Training a Custom Model - Part 9: Creating an Evaluation Function for Our Model Predictions Processing (13:52)
Training a Custom Model - Part 10: Training Our Model with Trainer (12:53)
Training a Custom Model - Part 11: Plotting Our Models Loss Curves (8:35)
Project 1 - Evaluating our Trained Object Detection Model
Evaluating Our Model on the Test Dataset (11:13)
Making Predictions on Test Data and Visualizing Them (24:20)
Plotting Our Models Predictions vs. the Ground Truth Images (12:00)
Trying Our Model on Images from the Wild (9:49)
Uploading Our Trained Model to the Hugging Face Hub (10:46)
Project 1 - Bringing Trashify to Life: Turning our Custom Model into a Shareable Demo
Turning Our Model into a Demo - Part 1: Gradio and Hugging Face Spaces Overview (10:10)
Turning Our Model into a Demo - Part 2: Creating an App File Overview (7:10)
Turning Our Model into a Demo - Part 3: Building the Main Function of Our App File (27:32)
Turning Our Model into a Demo - Part 4: Finishing Off Our App File and Testing Our Demo (9:56)
Turning Our Model into a Demo - Part 5: Creating a Readme and Requirements File (3:31)
Turning Our Model into a Demo - Part 6: Getting Example Images for Our Demo (8:19)
Turning Our Model into a Demo - Part 7: Uploading Our Demo to the Hugging Face Hub (17:18)
Turning Our Model into a Demo - Part 8: Embedding Our Demo into Our Notebook (3:44)
Summary, Extensions and Extra-Curriculum (6:15)
Project 2 - Fully Fine-tuning a Small Language Model (SLM) with Hugging Face Transformers
Overview and Introduction to Small Language Models (SLMs) + Resources (10:32)
What We're Going to Cover (8:39)
Setting Up Google Colab with Hugging Face Tokens (5:52)
Getting Our Google Colab Instance Ready for Coding (6:18)
Summary: Extensions and Extra Curriculum (9:56)
Project 2 - Setting up a Small Language Model and Getting a Dataset
Setting Up Our Base Model and Inspecting the Tokenizer (14:07)
How to Convert Input and Output Tokens to Text (10:31)
Counting the Parameters in Our Model and Comparing it to the Teacher Model (12:07)
Downloading a Text Dataset for Our Model (14:24)
Project 2 - Preparing a text dataset for language model fine-tuning
Formatting Our Dataset Ready to Be Used with a Language Model (12:17)
Splitting Our Dataset into Train and Test Sets (5:01)
Project 2 - Testing our Small Language Model (before fine-tuning)
Using Our Base Model with a Hugging Face Pipeline (16:05)
Attempt 0: Trying the Base Model Pipeline with One of Our Own Samples (8:59)
Attempt 1: Trying the Base Model Pipeline with One of Our Own Samples and an Instruction Prompt (15:20)
Project 2 - Fine-Tuning Our Model On Custom Data
Fine-Tuning Our Model - Part 1: Discussing the Ingredients We Need for Fine-Tuning (5:09)
Fine-Tuning Our Model - Part 2: Setting Up Our SFTConfig with Hyperparameters for Model Training (17:53)
Fine-Tuning Our Model - Part 3: Setting Up Our SFTTrainer and Fine-Tuning Our Model and Fixing Errors Along the Way (15:21)
Fine-Tuning Our Model - Part 4: Plotting Our Models Loss Curves (5:54)
Fine-Tuning Our Model - Part 5: Saving Our Best Model to File (4:42)
Project 2 - Loading Our Fine-Tuned Model and Making Predictions
Loading In Our Best Model from File and Preparing to Make Predictions (5:08)
Making Predictions on Test Samples with Our Loaded Fine-tuned Model (5:28)
Project 2 - Evaluating Our Fine-Tuned Small Language Model
Comparing Our Fine-Tuned Model's Predictions to the Test Labels (7:45)
Writing a Helper Function to Make Predictions on Any Sample and Inspecting the Results (9:57)
Project 2 - Uploading Our Model to the Hugging Face Hub
Discussing what Uploading Our Model to the Hugging Face Hub Looks Like (5:49)
Creating a Hugging Face Hub Model Repo to Store Our Model (3:41)
Creating a README Model Card for Our Fine Tuned Model (6:04)
Uploading Our Fine-Tuned Model to the Hugging Face Hub (6:14)
Project 2 - Turning Our Fine-Tuned Model Into a Shareable Demo
Turning Our Model into a Demo - Part 1: Discussing the Required Components (6:13)
Turning Our Model into a Demo - Part 2: Building an app.py File to Launch Our Demo (18:09)
Turning Our Model into a Demo - Part 3: Creating Requirements and README Files for Our Demo (4:11)
Turning Our Model into a Demo - Part 4: Uploading Our Demo to the Hugging Face Hub and Publishing it (13:05)
Turning Our Model into a Demo - Part 5: Embedding Our Demo Right within Google Colab (4:31)
Where To Go From Here?
Thank You! (1:17)
Review This Course!
Become An Alumni
Learning Guideline
ZTM Events Every Month
LinkedIn Endorsements
Writing a Helper Function to Make Predictions on Any Sample and Inspecting the Results
This lecture is available exclusively for ZTM Academy members.
If you're already a member,
you'll need to login
.
Join ZTM To Unlock All Lectures