logo

Eduardo Avelar
  • E-learning ML/Data resources
    • ML/Data/Dev Books
    • Coursera courses
    • GCP Courses/Videos Analysis
    • GCP Skills Boost Updates
    • GCP ML/Data labs
    • Pages/Posts/Lectures
    • Platforms/Tools
    • Courses/Videos
  • Dev-ML Tools
    • Check for duplicated questions
    • Create html page with ML questions
    • VS Code ext to paste one line
    • Qwiklabs Quizzes to JSON
    • GCP Courses Builder
    • GCP Videos to Images
  • My Dev notes
    • apt install dev-essentials
    • Dev commands
    • Dev Troubleshooting Notes
    • Install Kubeflow Pipelines for Local Deployment
    • Kubeflow Pipelines v1 sdk v2 examples
    • My VS Code theme
  • ML Notes
    • ML Good practice
    • Nvidia ML
  • Google Cloud Skills Boost Courses
    • Google Cloud Big Data and Machine Learning Fundamentals
    • How Google Does Machine Learning
    • Launching into Machine Learning
    • TensorFlow on Google Cloud
    • Feature Engineering
    • Machine Learning in the Enterprise
      • Vertex Vizier Hyperparameter Tuning
        • Introduction
        • Vertex AI Vizier hyperparameter tuning
        • Lab intro: Vertex Vizier Hyperparameter Tuning
      • Prediction and Model Monitoring using Vertex AI
        • Introduction
        • Predictions using Vertex AI
        • Model management using Vertex AI
        • Lab intro: Vertex AI Model Monitoring
      • Vertex AI Pipelines
        • Introduction
        • Prediction using Vertex AI pipelines
        • Lab intro: Vertex AI Pipelines
      • Best Practices for Machine Learning Development
        • Introduction
        • Best practices for model deployment and serving
        • Best practices for model monitoring
        • Vertex AI pipeline best practices
        • Best practices for artifact organization
      • Series Summary
        • Series summary
      • Working dir
        • intro_to_vertex_pipelines.ipynb
    • Production Machine Learning Systems
      • Introduction to Advanced Machine Learning on Google Cloud
        • Advanced Machine Learning on Google Cloud
        • Welcome
      • Architecting Production ML Systems
        • Architecting ML systems
        • Data extraction, analysis, and preparation
        • Model training, evaluation, and validation
        • Trained model, prediction service, and performance monitoring
        • Training design decisions
        • Serving design decisions
        • Using Vertex AI
        • Lab introduction: Structured data prediction
      • Designing Adaptable ML Systems
        • Introduction
        • Adapting to data
        • Changing distributions
        • Lab: Adapting to data
        • Right and wrong decisions
        • System failure
        • Concept drift
        • Actions to mitigate concept drift
        • TensorFlow data validation
        • Components of TensorFlow data validation
        • Lab Introduction: Introduction to TensorFlow Data Validation
        • Lab Introduction: Advanced Visualizations with TensorFlow Data Validation
        • Mitigating training-serving skew through design
        • Lab Introduction: Serving ML Predictions in Batch and Real Time
        • Diagnosing a production model
      • Designing High-performance ML Systems
        • Training
        • Why distributed training is needed
        • Distributed training architectures
        • TensorFlow distributed training strategies
        • Mirrored strategy
        • Multi-worker mirrored strategy
        • TPU strategy
        • Parameter server strategy
        • Lab Introduction: Distributed Training with Keras
        • Lab Introduction: Distributed Training using GPUs on Cloud AI Platform
        • Training on large datasets with tf.data API
        • Lab Introduction: TPU-speed Data Pipelines
      • Building Hybrid ML Systems
        • Kubeflow
        • Optimizing TensorFlow for mobile
      • Summary
        • Course summary
      • Working dir
        • keras.ipynb
        • serving_ml_prediction.ipynb
        • tfdv_basic_spending.ipynb
        • babyweight/train_deploy.ipynb
    • Computer Vision Fundamentals with Google Cloud
      • Introduction to Computer Vision and Pre-built ML Models for Image Classification
        • What Is Computer Vision
        • Different Type of Computer Vision Problems
        • Computer Vision Use Cases
        • Vision API - Pre-built ML Models
      • Vertex AI and AutoML Vision on Vertex AI
        • What is Vertex AI and why does a unified platform matter?
        • Introduction to AutoML Vision on Vertex AI
        • How does Vertex AI help with the ML workflow, part 1 ?
        • How does Vertex AI help with the ML workflow, part 2 ?
        • Which vision product is right for you?
        • Lab Introduction - Identifying Damaged Car Parts with Vertex AI for AutoML Vision users
      • Custom Training with Linear, Neural Network and Deep Neural Network models
        • Introduction
        • Introduction to Linear Models
        • Reading the Data
        • Implementing Linear Models for Image Classification
        • Neural Networks and Deep Neural Networks for Image Classification
        • Deep Neural Networks with Dropout and Batch Normalization
      • Convolutional Neural Networks
        • Introduction
        • Convolutional Neural Networks
        • Understanding Convolutions
        • CNN Model Parameters
        • Working with Pooling Layers
        • Implementing CNNs on Vertex AI with pre-built TF container using Vertex Workbench
      • Dealing with Image Data
        • Introduction
        • Preprocessing the Image Data
        • Model Parameters and the Data Scarcity Problem
        • Data Augmentation
        • Transfer Learning
      • Summary
        • Summary
    • Natural Language Processing on Google Cloud
      • Course introduction
        • Course Introduction
      • NLP on Google Cloud
        • Introduction
        • What is NLP?
        • NLP history
        • NLP architecture
        • NLP APIs
        • NLP solutions
        • Summary
      • NLP with Vertex AI
        • Introduction
        • NLP options
        • Vertex AI
        • NLP with AutoML
        • NLP with custom training
        • NLP end-to-end workflow
        • Summary
      • Text representation
        • Introduction
        • Tokenization
        • One-hot encoding and bag-of-words
        • Word embeddings
        • Word2vec
        • Transfer learning and reusable embeddings
        • Summary
      • Advanced NLP models
        • Introduction
        • Encoder-decoder architecture
        • Attention mechanism
        • Transformer
        • BERT
        • Large language models
        • Lab introduction: Text Translation using Encoder-decoder Architecture
        • Summary
    • Recommendation Systems on Google Cloud
      • Recommendation Systems Overview
        • Types of Recommendation Systems
        • Content-Based or Collaborative
        • Recommendation System Pitfalls
      • Content-Based Recommendation Systems
        • Content-Based Recommendation Systems
        • Similarity Measures
        • Building a User Vector
        • Making Recommendations Using a User Vector
        • Making Recommendations for Many Users
        • Using Neural Networks for Content-Based Recommendation Systems
    • Machine Learning Operations (MLOps): Getting Started
      • Employing Machine Learning Operations
        • Machine learning (ML) practitioners’ pain points
        • The concept of devOps in ML
        • ML lifecycle
        • Automating the ML process
      • Vertex AI and MLOps on Vertex AI
        • What is vertex ai and why does a unified platform matter?
        • Introduction to mlops on vertex ai
        • How does vertex ai help with the mlops workflow, part 2?
  • Official GCP codes
    • Create machine learning models in BigQuery ML
  • GCP notes/resources
    • GCP notes
    • Machine Learning Cert guide
    • Notebooks To Do
    • Vertex AI MLOps
  • Official TF codes
    • Structured Data
      • Time series forecasting
    • Distributed training
      • Multi-worker training with Keras
  • Tensorflow Notebooks
    • TF Libraries & extensions
    • tfdv_basic.ipynb
    • Preprocessing Layers and tools
    • Scikit Learn anf TF
    • TensorFlow Developer Certificate
  • Feature Engineering Tools
  • DeepLearning.AI Courses
    • TensorFlow Dev Cert - original version
      • C1W1 Assignment: Housing Prices
      • C1W2: Implementing Callbacks in TensorFlow using the MNIST Dataset
      • C1W3: Improve MNIST with Convolutions
      • C1W4: Handling Complex Images - Happy or Sad Dataset
      • C2W1: Using CNN’s with the Cats vs Dogs Dataset
      • C2W2: Tackle Overfitting with Data Augmentation
      • C2W3: Transfer Learning
      • C2W4: Multi-class Classification
      • C3W1: Explore the BBC News archive
      • C3W2: Diving deeper into the BBC News archive
      • C3W3: Exploring Overfitting in NLP
      • C3W4: Predicting the next word
      • C4W1: Working with time series
      • C4W2: Predicting time series
      • C4W3: Using RNNs to predict time series
      • C4W4: Using real world data
    • TensorFlow Dev Cert - updated
      • C1W1 Assignment: Housing Prices
      • C1W2: Implementing Callbacks in TensorFlow using the MNIST Dataset
      • C1W3: Improve MNIST with Convolutions
      • C1W4: Handling Complex Images - Happy or Sad Dataset
      • C2W1: Using CNN’s with the Cats vs Dogs Dataset
      • C2W2: Tackle Overfitting with Data Augmentation
      • C2W3: Transfer Learning
      • C2W4: Multi-class Classification
      • C3W1: Explore the BBC News archive
      • C3W2: Diving deeper into the BBC News archive
      • C3W3: Exploring Overfitting in NLP
      • C3W4: Predicting the next word
      • C4W1: Working with time series
      • C4W2: Predicting time series
      • C4W3: Using RNNs to predict time series
      • C4W4: Using real world data

TensorFlow Dev Cert - updated

TensorFlow Dev Cert - updated#

This version of notebooks use methods from the last TF version and the way to resolve the problems based on the official TF documentation.

Content

  • C1W1 Assignment: Housing Prices
  • C1W2: Implementing Callbacks in TensorFlow using the MNIST Dataset
  • C1W3: Improve MNIST with Convolutions
  • C1W4: Handling Complex Images - Happy or Sad Dataset
  • C2W1: Using CNN’s with the Cats vs Dogs Dataset
  • C2W2: Tackle Overfitting with Data Augmentation
  • C2W3: Transfer Learning
  • C2W4: Multi-class Classification
  • C3W1: Explore the BBC News archive
  • C3W2: Diving deeper into the BBC News archive
  • C3W3: Exploring Overfitting in NLP
  • C3W4: Predicting the next word
  • C4W1: Working with time series
  • C4W2: Predicting time series
  • C4W3: Using RNNs to predict time series
  • C4W4: Using real world data

C4W4: Using real world data

C1W1 Assignment: Housing Prices