tomrunia/uva_dlc_cnn_architecture.md

Last active October 26, 2017 19:43

Star (0) You must be signed in to star a gist
Fork (0) You must be signed in to fork a gist

Learn more about clone URLs
Clone this repository at <script src="https://gist.github.com/tomrunia/ae96f44eafa8398d3bd07d29db39dd6a.js"></script>
Save tomrunia/ae96f44eafa8398d3bd07d29db39dd6a to your computer and use it in GitHub Desktop.

Download ZIP

Raw

uva_dlc_cnn_architecture.md

Block	Elements	Kernel Size	Filter depth	Output depth	Stride	Misc. Info
	`Convolution`	`[5, 5]`	`3`	`64`	`[1, 1]`
`conv1`	`ReLU`	`-`	`-`	`-`	`-`
	`Max-pool`	`[3, 3]`	`-`	`-`	`[2, 2]`

	`Convolution`	`[5, 5]`	`64`	`64`	`[1, 1]`
`conv2`	`ReLU`	`-`	`-`	`-`	`-`
	`Max-pool`	`[3, 3]`	`-`	`-`	`[2, 2]`

`flatten`	`Flatten`

`fc1`	`Multiplication`	`[dim(conv2), 384]`	`-`	`-`	`-`
	`ReLU`	`-`	`-`	`-`	`-`

`fc2`	`Multiplication`	`[384, 192]`	`-`	`-`	`-`
	`ReLU`	`-`	`-`	`-`	`-`

`fc3`	`Multiplication`	`[192, 10]`	`-`	`-`	`-`
	`Softmax`	`-`	`-`	`-`	`-`

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment