Convolution is a very important mathematical operation in artificial neural networks(ANN’s). Convolutional neural networks (CNN’s) can be used to learn features as well as classify data with the help of image frames. There are many types of CNN’s. One class of CNN’s are depth wise separable convolutional neural networks.
These type of CNN’s are widely used because of the following two reasons –
- They have lesser number of parameters to adjust as compared to the standard CNN’s, which reduces overfitting
- They are computationally cheaper because of fewer computations which makes them suitable for mobile vision applications
This article explains the architecture and operations used by depth wise separable convolutional networks and derives its efficiency over simple convolution neural networks.
Understanding Normal Convolution operation
Suppose there is an input data of size Df x Df x M, where Df x Df can be the image size and M is the number of channels (3 for an RGB image). Suppose there are N filters/kernels of size Dk x Dk x M. If a normal convolution operation is done, then, the output size will be Dp x Dp x N.
The number of multiplications in 1 convolution operation = size of filter = Dk x Dk x M
Since there are N filters and each filter slides vertically and horizontally Dp times,
the total number of multiplications become N x Dp x Dp x (Multiplications per convolution)
So for normal convolution operation
Total no of multiplications = N x Dp2 x Dk2 x M
Depth-Wise Separable Convolutions
Now look at depth-wise separable convolutions. This process is broken down into 2 operations –
- Depth-wise convolutions
- Point-wise convolutions
- DEPTH WISE CONVOLUTION
In depth-wise operation, convolution is applied to a single channel at a time unlike standard CNN’s in which it is done for all the M channels. So here the filters/kernels will be of size Dk x Dk x 1. Given there are M channels in the input data, then M such filters are required. Output will be of size Dp x Dp x M.
Cost of this operation:
A single convolution operation require Dk x Dk multiplications.
Since the filter are slided by Dp x Dp times across all the M channels,
the total number of multiplications is equal to M x Dp x Dp x Dk x Dk
So for depth wise convolution operation
Total no of multiplications = M x Dk2 x Dp2
- POINT WISE CONVOLUTION
In point-wise operation, a 1×1 convolution operation is applied on the M channels. So the filter size for this operation will be 1 x 1 x M. Say we use N such filters, the output size becomes Dp x Dp x N.
Cost of this operation:
A single convolution operation require 1 x M multiplications.
Since the filter is being slided by Dp x Dp times,
the total number of multiplications is equal to M x Dp x Dp x (no. of filters)
So for point wise convolution operation
Total no of multiplications = M x Dp2 x N
Therefore, for overall operation:
Total multiplications = Depth wise conv. multiplications + Point wise conv. multiplications
Total multiplications = M * Dk2 * Dp2 + M * Dp2 * N = M * Dp2 * (Dk2 + n)
So for depth wise separable convolution operation
Total no of multiplications = M x Dp2 x (Dk2 + N)
Comparison between the complexities of these types of convolution operations
Type of Convolution
N x Dp2 x Dg2 x M
Depth wise separable
M x Dp2 x (Dk2 + N)
Complexity of depth wise separable convolutions -------------------------------------------------- = RATIO ( R ) Complexity of standard convolution
Ratio(R) = 1/N + 1/Dk2
As an example, consider N = 100 and Dk = 512. Then the ratio R = 0.010004
This means that the depth wise separable convolution network, in this example, performs 100 times lesser multiplications as compared to a standard constitutional neural network.
This implies that we can deploy faster convolution neural network models without losing much of the accuracy.My Personal Notes arrow_drop_up
- Multiple Labels Using Convolutional Neural Networks
- Dropout in Neural Networks
- Recurrent Neural Networks Explanation
- Activation functions in Neural Networks
- Artificial Neural Networks and its Applications
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Neural Network Advances
- ANN - Self Organizing Neural Network (SONN)
- Introduction to Recurrent Neural Network
- Deep Neural Network With L - Layers
- Introduction to Convolution Neural Network
- Implementation of neural network from scratch using NumPy
- Difference between Neural Network And Fuzzy Logic
- A single neuron neural network in Python
- ANN - Self Organizing Neural Network (SONN) Learning Algorithm
- ANN - Implementation of Self Organizing Neural Network (SONN) from Scratch
- Implementing Artificial Neural Network training process in Python
- Deep Neural net with forward and back propagation from scratch - Python
- Implementation of Artificial Neural Network for OR Logic Gate with 2-bit Binary Input
- Implementation of Artificial Neural Network for AND Logic Gate with 2-bit Binary Input
If you like GeeksforGeeks and would like to contribute, you can also write an article using contribute.geeksforgeeks.org or mail your article to email@example.com. See your article appearing on the GeeksforGeeks main page and help other Geeks.
Please Improve this article if you find anything incorrect by clicking on the "Improve Article" button below.
Improved By : MeghnaNatraj