Full-Stack Deep Learning with Python (2024)
1h 45mAdvanced2024-02-06
Authors
Janani Ravi
Certified Google Cloud Architect and Data Engineer
Course details
If you seek a more in-depth understanding of deep learning and Python, this hands-on course can help you. In this course, certified Google cloud architect and data engineer Janani Ravi guides you through the intricacies of full-stack deep learning with Python. After a review of full stack deep learning, MLOps, and MLflow, dive into setting up your environment on Google Colab and running MLflow. Learn how to load and explore a dataset, as well as how to log metrics, parameters, and artifacts. Explore model training, evaluation, and hyperparameter tuning. Plus, go over model deployment and predictions.
Skills covered
Neural Networks and Deep LearningAdvancedPythonArtificial Intelligence (AI)Programming LanguagesOpen SourceSoftware Development
Concepts
Introduction
- Full-stack deep learning, MLOps, and MLflow
- Prerequisites
An Overview of Full-Stack Deep Learning
- Introducing full-stack deep learning
- Introducing MLOps
- Introducing MLflow
- Setting up the environment on Google Colab
- Running MLflow and using ngrok to access the MLflow UI
Model Training and Evaluation Using MLflow
- Loading and exploring the EMNIST dataset
- Logging metrics, parameters, and artifacts in MLflow
- Set up the dataset and data loader
- Configuring the image classification DNN model
- Training a model within an MLflow run
- Exploring parameters and metrics in MLflow
- Making predictions using MLflow artifacts
Model Training and Hyperparameter Tuning
- Preparing data for image classification using CNN
- Configuring and training the model using MLflow runs
- Visualizing charts, metrics, and parameters on MLflow
- Setting up the objective function for hyperparameter tuning
- Hyperparameter optimization with Hyperopt and MLflow
- Identifying the best model
- Registering a model with the MLflow registry
Model Deployment and Predictions
- Setting up MLflow on the local machine
- Workaround to get model artifacts on the local machine
- Deploying and serving the model locally
Conclusion
- Summary and next steps