How to get the required FLOPs for my neural network

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.

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

Hi, 
I am Ankit Tiwari
I have Some Information below~>

• FLOPS: Abbreviation for floating-point operations per second, which means the number of floating-point operations per second, which is understood as the calculation speed. ... The height, width, and number of channels of the input feature map
• If you're using Keras, you could just use the patch in this pull request: github.com/.../6203 Then just call print_summary() and you'll see both the flops per layer and the total.