News for hackers. Stuff that matters.
Re:Why is so much memory needed for deep neural networks? by syntaxing on Thursday March 23, 2017 @08:17AM (#13939092)
This question might be a bit off topic but does anyone know of a calculator or library (I primarily use Tensorflow and Keras) to calculate the GPU memory footprint of the network? I only have a 1050Ti and I fit my networks in the memory by manually adjusting different parameters. It would be nice to know how much room I have left to expand my network.
Re:Why is so much memory needed for deep neural networks? by Q6T46nT668w6i3m on Thursday March 23, 2017 @09:15AM (#13939430)
model.summary() in Keras will provide you the number of parameters. You can use this with the shape of your data to measure the memory cost.
Re:Why is so much memory needed for deep neural networks? by syntaxing on Thursday March 23, 2017 @11:52AM (#13940857)
Thanks! Can you explain how I can calculate the memory cost with the shape of my data assuming a batch size of 1 and a input data shape of (10,20,3)?