The shapes of the dataset returned by from_generator depend on the shapes of the elements generated by the generator function. Each element must have the same nested structure and shapes, and the resulting dataset will have the same structure but with batch dimension added to each shape. For example, if the generator function returns a tuple of two tensors with shapes (1, 32, 32, 3) and (1, 10), respectively, the resulting dataset will have a nested structure of (TensorShape([None, 32, 32, 3]), TensorShape([None, 10])), where the None dimension represents the batch size.
Please start posting anonymously - your entry will be published after you log in or create a new account. This space is reserved only for answers. If you would like to engage in a discussion, please instead post a comment under the question or an answer that you would like to discuss
Asked: 2022-04-19 11:00:00 +0000
Seen: 12 times
Last updated: Feb 27 '23
Can the choropleth map incorporate various shapes for depicting different colors on the map?
How can the columns be transformed into a multi-level structure?
What is the proper way to structure computed land measurement using Excel?
Can the grid pattern be obtained by modifying the hollow star pattern?
How can the schema structure of Firestore be exported to a JSON file?
What CNN structure is appropriate for the classification of extremely small images?
Is it possible to have an unordered map consisting of a structure that has an expanding linked list?