What is the meaning of the “None” in model.summary of KERAS?

by

None means this dimension is variable.

The first dimension in a keras model is always the batch size. You don’t need fixed batch sizes, unless in very specific cases (for instance, when working with stateful=True LSTM layers).

That’s why this dimension is often ignored when you define your model. For instance, when you define input_shape=(100,200), actually you’re ignoring the batch size and defining the shape of “each sample”. Internally the shape will be (None, 100, 200), allowing a variable batch size, each sample in the batch having the shape (100,200).

The batch size will be then automatically defined in the fit or predict methods.

Other None dimensions:

Not only the batch dimension can be None, but many others as well.

For instance, in a 2D convolutional network, where the expected input is (batchSize, height, width, channels), you can have shapes like (None, None, None, 3), allowing variable image sizes.

In recurrent networks and in 1D convolutions, you can also make the length/timesteps dimension variable, with shapes like (None, None, featuresOrChannels)

More Related Contents:

  1. What are the differences between all these cross-entropy losses in Keras and TensorFlow?
  2. Choosing number of Steps per Epoch
  3. TensorFlow and person recognition in video stream
  4. Make a custom loss function in keras
  5. Keras not training on entire dataset
  6. Keras : How should I prepare input data for RNN?
  7. Deep-Learning Nan loss reasons
  8. How to apply gradient clipping in TensorFlow?
  9. How to Properly Combine TensorFlow’s Dataset API and Keras?
  10. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  11. Keras custom loss function: Accessing current input pattern
  12. Does model.compile() initialize all the weights and biases in Keras (tensorflow backend)?
  13. How can I use a pre-trained neural network with grayscale images?
  14. Using Gensim Fasttext model with LSTM nn in keras
  15. Tensorflow (.pb) format to Keras (.h5)
  16. How to know if underfitting or overfitting is occuring?
  17. Save and load model optimizer state
  18. Unknown initializer: GlorotUniform when loading Keras model
  19. Obtaining output of an Intermediate layer in TensorFlow/Keras
  20. tf.data with multiple inputs / outputs in Keras
  21. Keras split train test set when using ImageDataGenerator
  22. In Keras, what exactly am I configuring when I create a stateful `LSTM` layer with N `units`?
  23. ‘Tensor’ object has no attribute ‘lower’
  24. Confusion about keras Model: __call__ vs. call vs. predict methods
  25. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  26. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  27. What is the difference between keras and tf.keras?
  28. How is the Keras Conv1D input specified? I seem to be lacking a dimension
  29. Checkpointing keras model: TypeError: can’t pickle _thread.lock objects
  30. How to replace (or insert) intermediate layer in Keras model?

Leave a Comment