projects
/
dagnn.git
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
f1e78b9
)
Cosmetics.
author
Francois Fleuret
<francois@fleuret.org>
Fri, 13 Jan 2017 22:14:08 +0000
(23:14 +0100)
committer
Francois Fleuret
<francois@fleuret.org>
Fri, 13 Jan 2017 22:14:08 +0000
(23:14 +0100)
README.md
patch
|
blob
|
history
diff --git
a/README.md
b/README.md
index
f370b71
..
436aa63
100644
(file)
--- a/
README.md
+++ b/
README.md
@@
-65,13
+65,13
@@
input, since it is the input to the module a, and its output will is a
table composed of two tensors, corresponding to the outputs of d and e
respectively.
table composed of two tensors, corresponding to the outputs of d and e
respectively.
-#
Usage
#
+#
#Usage#
#
-##
nn.DAG()
##
+##
#nn.DAG()#
##
Create a new empty DAG, which inherits from nn.Container.
Create a new empty DAG, which inherits from nn.Container.
-##
nn.DAG:connect([module1 [, module2 [, ...]]])
##
+##
#nn.DAG:connect([module1 [, module2 [, ...]]])#
##
Add new nodes corresponding to the modules passed as arguments if they
are not already existing. Add edges between every two nodes
Add new nodes corresponding to the modules passed as arguments if they
are not already existing. Add edges between every two nodes
@@
-80,21
+80,21
@@
corresponding to a pair of successive modules in the arguments.
Calling it with n > 2 arguments is strictly equivalent to calling it
n-1 times on the pairs of successive arguments.
Calling it with n > 2 arguments is strictly equivalent to calling it
n-1 times on the pairs of successive arguments.
-##
nn.DAG:setInput(i)
##
+##
#nn.DAG:setInput(i)#
##
Defines the content and structure of the input. The argument should be
either a module, or a (nested) table of module. The input to the DAG
should be a (nested) table of inputs with the corresponding structure.
Defines the content and structure of the input. The argument should be
either a module, or a (nested) table of module. The input to the DAG
should be a (nested) table of inputs with the corresponding structure.
-##
nn.DAG:setOutput(o)
##
+##
#nn.DAG:setOutput(o)#
##
Similar to DAG:setInput().
Similar to DAG:setInput().
-##
nn.DAG:print()
##
+##
#nn.DAG:print()#
##
Prints the list of nodes.
Prints the list of nodes.
-##
nn.DAG:saveDot(filename)
##
+##
#nn.DAG:saveDot(filename)#
##
Save a dot file to be used by the Graphviz set of tools for graph
visualization. This dot file can than be used for instance to produce
Save a dot file to be used by the Graphviz set of tools for graph
visualization. This dot file can than be used for instance to produce
@@
-104,15
+104,15
@@
a pdf file with
dot graph.dot -T pdf -o graph.pdf
```
dot graph.dot -T pdf -o graph.pdf
```
-##
nn.DAG:updateOutput(input)
##
+##
#nn.DAG:updateOutput(input)#
##
See the torch documentation.
See the torch documentation.
-##
nn.DAG:updateGradInput(input, gradOutput)
##
+##
#nn.DAG:updateGradInput(input, gradOutput)#
##
See the torch documentation.
See the torch documentation.
-##
nn.DAG:accGradParameters(input, gradOutput, scale)
##
+##
#nn.DAG:accGradParameters(input, gradOutput, scale)#
##
See the torch documentation.
See the torch documentation.