This discussion has been locked.

You can no longer post new replies to this discussion. If you have a question you can start a new discussion

How to get the required FLOPs for my neural network

fset89 over 6 years ago

I want to estimate the memory bandwidth of my neural network. In order to do this, I need to know the FLOPS required for an inference. Does this number depend on the library that I am using (e.g. ComputeLibrary, OpenBLAS)? In this case, how can I estimate it?

Top replies

Julie John over 5 years ago +1

This link might help you https://stats.stackexchange.com/questions/291843/how-to-understand-calculate-flops-of-the-neural-network-model If you still don't understand click here to get more information...
Robert Duffy over 4 years ago in reply to Julie John +1

If you're using Keras, you could just use the patch in this pull request: https://github.com/fchollet/keras/pull/6203 Then just call print_summary() and you'll see both the flops per layer and the total...

Parents

0 Robert Duffy over 4 years ago in reply to Julie John

If you're using Keras, you could just use the patch in this pull request: https://github.com/fchollet/keras/pull/6203

Then just call print_summary() and you'll see both the flops per layer and the total.

Even if not using Keras, it may be worth it to recreate your nets in Keras just so you can get the flops counts. find more at SLC
Cancel
Vote up +1 Vote down

Cancel

Reply

0 Robert Duffy over 4 years ago in reply to Julie John

If you're using Keras, you could just use the patch in this pull request: https://github.com/fchollet/keras/pull/6203

Then just call print_summary() and you'll see both the flops per layer and the total.

Even if not using Keras, it may be worth it to recreate your nets in Keras just so you can get the flops counts. find more at SLC
Cancel
Vote up +1 Vote down

Cancel

Children

No data