# How to compute number of weights of CNN?

How can we compute number of weights considering a convolutional neural network that is used to classify images into two classes :

• INPUT: 100x100 gray-scale images.
• LAYER 1: Convolutional layer with 60 7x7 convolutional filters (stride=1, valid padding).
• LAYER 2: Convolutional layer with 100 5x5 convolutional filters (stride=1, valid padding).
• LAYER 3: A max pooling layer that down-samples Layer 2 by a factor of 4 (e.g., from 500x500 to 250x250)
• LAYER 4: Dense layer with 250 units
• LAYER 5: Dense layer with 200 units
• LAYER 6: Single output unit

Assume the existence of biases in each layer. Moreover, pooling layer has a weight (similar to AlexNet)

How many weights does this network have?

# Keras Code

import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Conv2D, MaxPooling2D

model = Sequential()

# Layer 1

# Layer 2

# Layer 3

# Layer 4

# Layer 5

model.summary()

• Dec 14 '19 at 19:44
• @pasabaporaqui I am facing problems with lasgane , theano so i prefer solve this question theoretically rather than with code , if fix this would be nice . AMD GPU's aren't supported I think . Dec 14 '19 at 21:03

Calculating parameter number in a CNN is very straightforward.

CNN is composed of different filters which is essentially a 3d tensor. CNN weights are shared meaning they are used multiple times and reused in different locations. Each layer have n tensors each with dimension w * h * c where w = width, h = height, c = channels (the input channel size), therefore getting param_no = w * h * c * n. There is also a bias for each output channel, so param_no_bias = n. At the end the parameter number is calculated with: n * w * h * c + n. See more about this in hear: Article

The pooling layer does not have a weight, it only has hyperparameters. You may have confused the two. There are hyperparameters for the stride, the factor and etc. These are predefined and not trainable.

For a keras API, @pasabaporaqui has mentioned https://stackoverflow.com/a/35827171/4886927 which definitely works.