Convolutional Network terminologies
- Patch / kernel : size of the small image tile
- Stride : The number of pixels we will be shifting each time we move the filter.
Stride of 1 makes the output the same size as input. The stride of two makes the output roughly half the size of the input
- Valid Padding : If we do not go off the edge
- Same Padding : If the output map size is exactly the same as input. For the extra rows or columns they are padded with the zeroes in c this case
- Depth = semantic representation of the complexity i.e more depth = more complex learning. Increase the depth layer after layer in case of ConvNets
Finding the stride, depth with valid and same padding