Hands-On Convolutional Neural Networks with TensorFlow

 Calculating the number of operations

Now we’re interested in calculating the computational cost of a particular convolution layer. This step is important if you would like to understand how to implement efficient network structures, perhaps when speed is key like in mobile devices. Another reasons is to see how many multipliers are needed to implement a particular layer in hardware. The convolutional layers in modern CNN architectures can be responsible for up to 90% of all computation in the model!

These are the factors that impact the number of MACs (Multiply add accumulators)/operations:

• Convolution kernel size (F)
• Number of filters (M)
• Height and Width of the input feature map (H,W)
• Input batch size (B)
• Input depth size (channels) (C) ...