Changes in the CNTK book:
1. corrected the parameter list for the Delay command in NDL. 2. added the options for the rmprop gradient update type. 3. added the ConvertDBN command.
This commit is contained in:
Родитель
e773dc6264
Коммит
6bd6dbeb47
|
@ -159,3 +159,4 @@ $RECYCLE.BIN/
|
||||||
|
|
||||||
*.lyx~
|
*.lyx~
|
||||||
*.bak
|
*.bak
|
||||||
|
*.lyx#
|
||||||
|
|
Разница между файлами не показана из-за своего большого размера
Загрузить разницу
|
@ -115,8 +115,8 @@ Jie Gao, Avner May, Baolin Peng, Andreas Stolcke, Malcolm Slaney
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
||||||
\begin_layout Date
|
\begin_layout Date
|
||||||
MSR-TR-2014-112 (DRAFT v0.3: Dec.
|
MSR-TR-2014-112 (DRAFT v0.4: Jan.
|
||||||
11, 2014)
|
4, 2015)
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
||||||
\begin_layout Standard
|
\begin_layout Standard
|
||||||
|
|
|
@ -3265,7 +3265,7 @@ status open
|
||||||
|
|
||||||
\begin_layout Plain Layout
|
\begin_layout Plain Layout
|
||||||
|
|
||||||
Delay(m, [delayTime=1, defaultPastValue=0.1])
|
Delay(rows, [cols], m, [delayTime=1, defaultPastValue=0.1])
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
||||||
\end_inset
|
\end_inset
|
||||||
|
@ -3273,6 +3273,18 @@ Delay(m, [delayTime=1, defaultPastValue=0.1])
|
||||||
|
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
rows - the number of rows in the delay node (and in the input matrix).
|
||||||
|
This parameter is needed because under some loopy conditions the dimensions
|
||||||
|
cannot be automatically inferred from the input matrix.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
cols - the number of columns in the delay node (and in the input matrix).
|
||||||
|
This parameter is optional since it will be set based on the minibatch
|
||||||
|
size during training and testing.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
\begin_layout Itemize
|
\begin_layout Itemize
|
||||||
m - input matrix to be delayed.
|
m - input matrix to be delayed.
|
||||||
Each column is a sample.
|
Each column is a sample.
|
||||||
|
|
|
@ -1789,9 +1789,113 @@ gradUpdateType
|
||||||
: gradient update type.
|
: gradient update type.
|
||||||
Valid values are None (default, no special treatment to the gradient),
|
Valid values are None (default, no special treatment to the gradient),
|
||||||
AdaGrad, and RmsProp.
|
AdaGrad, and RmsProp.
|
||||||
|
When gradUpdateType equals to RmsProp, you can control the behavior of
|
||||||
|
the gradient update using following parameters:
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_deeper
|
||||||
|
\begin_layout Itemize
|
||||||
|
|
||||||
|
\emph on
|
||||||
|
rms_wgt_inc
|
||||||
|
\emph default
|
||||||
|
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
rms_wgt_inc
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
: multiplicative increment of the learning rate scale.
|
||||||
|
Default is 1.2.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
|
||||||
|
\emph on
|
||||||
|
rms_wgt_dec
|
||||||
|
\emph default
|
||||||
|
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
rms_wgt_dec
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
: multiplicative decrement of the learning rate scale.
|
||||||
|
Default is 0.75.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
|
||||||
|
\emph on
|
||||||
|
rms_wgt_max
|
||||||
|
\emph default
|
||||||
|
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
rms_wgt_max
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
: maximum learning rate scale allowed.
|
||||||
|
A value closer to 1 makes the learning rate adjustment more stable but
|
||||||
|
slower.
|
||||||
|
Default is 10.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
|
||||||
|
\emph on
|
||||||
|
rms_wgt_min
|
||||||
|
\emph default
|
||||||
|
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
rms_wgt_min
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
: minimum learning rate scale allowed.
|
||||||
|
A value closer to 1 makes the learning rate adjustment more stable but
|
||||||
|
slower.
|
||||||
|
Default is 0.1.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
|
||||||
|
\emph on
|
||||||
|
rms_gamma
|
||||||
|
\emph default
|
||||||
|
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
rms_gamma
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
: smoothing factor used to estimate the moving average of the variance.
|
||||||
|
The smaller the value, the quicker it forgets the past information.
|
||||||
|
Default is 0.99.
|
||||||
|
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
||||||
|
\end_deeper
|
||||||
\begin_layout Itemize
|
\begin_layout Itemize
|
||||||
|
|
||||||
\emph on
|
\emph on
|
||||||
|
@ -4379,6 +4483,60 @@ minibatchSize
|
||||||
– the minibatch size to use when creating the label mapping file.
|
– the minibatch size to use when creating the label mapping file.
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Section
|
||||||
|
ConvertDBN Command
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
ConvertDBN Command
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Standard
|
||||||
|
This command is used to convert a model generated by Microsoft's dbn.exe
|
||||||
|
tool to a CNTK model.
|
||||||
|
This command is useful when you want to compare the performance of these
|
||||||
|
two tools (dbn.exe only supports simple fully connected deep neural networks),
|
||||||
|
port existing models trained with dbn.exe to CNTK, or if you want to use
|
||||||
|
the RBM pre-training which is available in dbn.exe but not in CNTK right
|
||||||
|
now.
|
||||||
|
The related parameters are
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
modelPath
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
modelPath
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
– the full path of the generated CNTK model.
|
||||||
|
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\begin_layout Itemize
|
||||||
|
dbnModelPath
|
||||||
|
\begin_inset Index idx
|
||||||
|
status open
|
||||||
|
|
||||||
|
\begin_layout Plain Layout
|
||||||
|
dbnModelPath
|
||||||
|
\end_layout
|
||||||
|
|
||||||
|
\end_inset
|
||||||
|
|
||||||
|
– the full path of the model to be converted.
|
||||||
|
\end_layout
|
||||||
|
|
||||||
\begin_layout Section
|
\begin_layout Section
|
||||||
Additional Top-Level Configurations
|
Additional Top-Level Configurations
|
||||||
\end_layout
|
\end_layout
|
||||||
|
|
Загрузка…
Ссылка в новой задаче