Load and Preprocess Data
Import, manage, and store data for your deep learning projects with images.
What you learned: To import and prepare data for training
- Load data as an image datastore
imageDatastorefunction automatically labels the images based on folder names
- Preprocessing data is a common first step in the deep learning workflow to prepare raw data in a format that the network can accept
Ensure the imported network and the image data are the right size to produce a highly accurate model.
What you learned: To use the network for model predictions before retraining
- Import networks and network architectures from TensorFlow-Keras, TensorFlow 2, Caffe, and the ONNX (Open Neural Network Exchange) model format
- Export a trained Deep Learning Toolbox network to the ONNX model format
Modify an existing network to work with your data, so you can customize deep learning to perform your specific task.
What you learned: To prepare the model for a new task
- Transfer the learned features of a pretrained network to a new problem
- Transfer learning is faster and easier than training a new network
- Reduce training time and dataset size
- Perform deep learning without needing to learn how to create a whole new network
Test the Network
Verify how well the model works with new data and not just the data it learned during training.
What you learned: To test all images in the validation set and evaluate how well the network trained
- Classify the validation data and calculate the classification accuracy
- Try using pretrained network for other tasks
- Solve new classification problems on your image data with transfer learning or feature extraction