Why the mini-batch size are always set as 218 or 512, with the train-data size can't be evenly divisible by the input size?

fchollet / deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

MIT License

18.59k stars 8.63k forks source link

Open danli349 opened 2 years ago

danli349 commented 2 years ago

Why the mini-batch size are always set as 218 or 512, with the train-data size can't be evenly divisible by the input size? Thanks