From the course: Full-Stack Deep Learning with Python

Unlock this course with a free trial

Join today to access over 24,400 courses taught by industry experts.

Deploying and serving the model locally

Deploying and serving the model locally - Python Tutorial

From the course: Full-Stack Deep Learning with Python

Deploying and serving the model locally

- [Instructor] Before we deploy and serve the model using MLflow, let's load the model in from the best model folder as a Python function and use it for predictions right here in this Jupyter Notebook. I'm going to install PyTorch Lightning because I'm going to set up a data set and a data loader for the test data. Let's quickly import the libraries that we need to work with PyTorch Torch, NumPy, matplotlib, pandas, and so on, and also the dataset and the data loader. I have the CSV file of the test data in my local machine in the current working directory, so I'm going to use Pandas to read in this data. Once we have the test data, I'm going to shuffle it by using the sample function in Pandas. We now have the test data in the form of a data frame. I create a dataset to represent this test data. This is the same emnist dataset that we've seen in earlier demos. I'm just setting this up in this notebook. Next, I…

Contents