batch size for LSTM

0
votes

I've been trying to set up an LSTM model but I'm a bit confused about batch_size. I'm using the Keras module in Tensorflow.

I have 50,000 samples, each has 200 time steps and each time step has three features. So I've shaped my training data as (50000, 200, 3).

I set up my model with four LSTM layers, each having 100 units. For the first layer I specified the input shape as (200, 3). The first three layers have return_sequences=True, the last one doesn't. Then I do some softmax classification.

When I call model.fit with batch_size='some_number' do Tensorflow/Keras take care of feeding the model with batches of the specified size? Do I have to reshape my data somehow in advance? What happens if the number of samples is not evenly divisible by 'some_number'?

Thanks for your help!

1
pythontensorflowkeraslstm
Welcome, to improve your experience on Stack Overflow please read how to ask an On Topic question, and the Question Check list and the perfect question and how to create a Minimal, Complete, and Verifiable example and if not already done, take the tour. – Bsquare ℬℬ

1 Answers

2
votes

If you provide your data as numpy arrays to model.fit() then yes, Keras will take care of feeding the model with the batch size you specified. If your dataset size is not divisible by the batch size, Keras will have the final batch be smaller and equal to dataset_size mod batch_size.