Image_dataset_from_directory
image_dataset_from_directory is a Keras utility function that creates an image dataset from files organized in class-specific subdirectories.
Deep Learning with R, Third Edition
image_dataset_from_directory is a Keras utility that constructs an image-input dataset by reading class-organized image files from a directory hierarchy.
- How it is used
- Builds image input pipelines from files on disk for Keras training, validation, testing, and image generation.
- How deep it goes
- Explains directory indexing, decoding, resizing, shuffling, batching, and dataset output without detailing implementation internals.
- Examples
- Uses class-organized train, validation, and test folders plus the unlabeled Oxford Flowers image collection.
- What you can do after
- Apply it via Keras to produce batched image tensors and labels ready for model fitting.
Read how Deep Learning with R, Third Edition explains image_dataset_from_directory →
Deep Learning with Python, Third Edition
A Keras utility function that builds a dataset from image files organized in class-specific subdirectories.
- How it is used
- Builds image datasets from directory-organized files for classification, generation, and model training.
- How deep it goes
- Explains directory indexing, decoding, resizing, shuffling, batching, and Dataset iteration without detailing the utility’s implementation.
- Examples
- Uses class-split image directories, 180×180 classification batches, and 128×128 aspect-preserving Oxford Flowers batches.
- What you can do after
- Apply it via Keras to create batched image datasets and pass them directly to model.fit() or model.evaluate().
Read how Deep Learning with Python, Third Edition explains image_dataset_from_directory →
Related concepts
- TensorFlow Datasetproduces · TensorFlow Dataset is an iterable abstraction for representing, transforming, batching, and supplying sequences of data elements to machine-learning models.
- Oxford Flowers datasetused by · The Oxford Flowers dataset is an image dataset containing 8,189 images categorized into 102 flower species.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.