Commit 36ca411f authored by David Peter's avatar David Peter
Browse files

Redraw multi-exit arch

parent 01dcaeb0
No preview for this file type
......@@ -13,7 +13,7 @@ For the following experiments in this section, we select one of the models from
\label{fig:multiex_model}
\end{figure}
There will be 5 exits in total, one exit after every of the first four \glspl{mbc} named exit 1 to exit 4 respectively and another exit at the final output named exit 5. A single exit consists of multiple layers depending on the exit topology according to Table~\ref{tab:exit_topology}. The first layer is either an ordinary convolution or a depthwise separable convolution. Then there is an additional pointwise convolution followed by global average pooling and either one, two or three fully connected layers. Convolutional layers use batch norm and \gls{relu} activations. Linear layers also use batch norm and \gls{relu} activations, except for the last linear layer where no batch norm and no activation function is used.
There will be 5 exits in total, one exit after every of the first four \glspl{mbc} named exit 1 to exit 4 respectively and another exit at the final output named exit 5. Exit 1 to exit 4 consist of multiple layers depending on the exit topology according to Table~\ref{tab:exit_topology}. The first layer of every exit is either an ordinary convolution or a depthwise separable convolution. Then there is an additional pointwise convolution followed by global average pooling and either one, two or three fully connected layers. Convolutional layers use batch norm and \gls{relu} activations. Linear layers also use batch norm and \gls{relu} activations, except for the last linear layer where no batch norm and no activation function is used.
\begin{table}
\begin{center}
......
results/plots/multiex_model.png

51.4 KB | W: | H:

results/plots/multiex_model.png

77.3 KB | W: | H:

results/plots/multiex_model.png
results/plots/multiex_model.png
results/plots/multiex_model.png
results/plots/multiex_model.png
  • 2-up
  • Swipe
  • Onion skin
#!/bin/bash
model_path="/Users/david/Git/kws-nas/models/pless_td/pless_sweep_td_SincConv_wm1_f60_3/"
plot_script="/Users/david/Git/kws-nas/src/plot_net.py"
plot_script="/Users/david/Git/kws-nas/src/plot_net_multi_exit.py"
net_cfg="${model_path}/learned_net/net.config"
python $plot_script -i $net_cfg -o . -n multiex_model.png -d 1,16000
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment