🌟
Advanced Concepts
Term | Description |
🔷 Padding | Adding additional border(s) to the image before convolution |
🌠 Strided Convolution | Convolving by s steps |
🏐 Convolutions Over Volume | Applying convs on n-dimensional input (such as an RGB image) |
Adding an additional one border or more to the image so the image is
n+2 x n+2 and after convolution we end up with n x n image which is the original size of the imagep = number of added bordersFor convention: it is filled by 0
For better understanding let's say that we have two concepts:
It means no padding so:
n x n * f x f ➡ n-f+1 x n-f+1Pad so that output size is the same as the input size.
So we want that 🧐:
n+2p-f+1 = nHence:
p = (f-1)/2For convention f is chosen to be odd 👩🚀
Another approach of convolutions, we calculate the output by applying filter on regions by some value
s.
For an
n x n image and f x f filter, with p padding and stride s; the output image size can be calculated by the following formula
To apply convolution operation on an RGB image; for example on 10x10 px RGB image, technically the image's dimension is 10x10x3 so we can apply for example a 3x3x3 filter or fxfx3 🤳
Filters can be applied on a special color channel 🎨
Layer | Description |
💫 Convolution CONV | Filters to extract features |
🌀 Pooling POOL | A technique to reduce size of representation and to speed up the computations |
⭕ Fully Connected FC | Standard single neural network layer (one dimensional) |
👩🏫 Usually when people report number of layers in an NN they just report the number of layers that have weights and paramsConvention:CONV1+POOL1=LAYER1
- Better performance since they decrease the parameters that will be tuned 💫
Last modified 2yr ago