I understand that while training the neural network you found that minibatch size which was initially set to 16 was later decreased to 9.
Please check whether the dataset being used has the total number of samples divisible by 16. This would ensure that all samples are used and the minibatch size is not adjusting automatically to accommodate remaining samples. The minibatch size is also dependent on the available memory. Try looking for any inconsistencies in data preprocessing or the network architecture.
You may try using Mini-Batch datastore for reading data in batches.
Please refer to the following:
Hope this helps!!
