From the course: Full-Stack Deep Learning with Python

Unlock this course with a free trial

Join today to access over 24,500 courses taught by industry experts.

Configuring the image classification DNN model

Configuring the image classification DNN model - Python Tutorial

From the course: Full-Stack Deep Learning with Python

Start my 1-month free trial Buy for my team

Configuring the image classification DNN model

“

- [Instructor] Let's set up the MLflow experiment to track our dense neural network training. I'm going to call mlflow.create_experiment. The name of the experiment is emnist_letters_prediction_using_dnn. And I'm going to set that experiment as the active experiment for this notebook. So any runs we create will be created within this emnist_letters_prediction_using_dnn experiment. Next, I'm going to import some Pytorch-related libraries and classes that we'll need to set up our neural network. We're going to be using a dense neural network for image classification. The size of the input fed into this dense network will be 28 by 28, that is 784, and the size of the output will be 26 since each image can be classified into one of 26 categories. The output will be a probability score for each class or category, and the category with the highest probability will be the predicted label of the model. We are now ready to set…

Contents