From the course: Full-Stack Deep Learning with Python
Join today to access over 24,400 courses taught by industry experts.
Summary and next steps - Python Tutorial
From the course: Full-Stack Deep Learning with Python
Summary and next steps
- [Instructor] This demo brings us to the very end of this course. Let's quickly review what we've covered so far. We started off with an overview of full-stack deep learning, and we saw that this covers the complete lifecycle of a deep learning model, from prototyping to production. we understood the role of MLOps in full-stack deep learning, and we were introduced to the MLflow tool that streamlines and automates the machine learning lifecycle. We then got hands-on with MLflow and saw how we could track logs and metrics using MLflow experiments and runs. We trained two different image classification models against neural network and a convolutional neural network, and we trained them to classify images from the EMNIST dataset. We performed hyperparameter tuning on our convolutional neural network using the Hyperopt Python library, which integrates very well with MLflow. And finally, we used MLflow serving to deploy…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
