potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 15:53:03 +04:00
Code Packages Releases Wiki Activity

Merge remote-tracking branch 'origin/2.4' into merge-2.4

Browse Source 
Conflicts:
	cmake/OpenCVDetectPython.cmake
	cmake/OpenCVModule.cmake
	modules/core/src/gpumat.cpp
	modules/cudaimgproc/test/test_hough.cpp
	modules/gpu/CMakeLists.txt
	modules/gpu/src/cuda/generalized_hough.cu
	modules/gpu/src/generalized_hough.cpp
	modules/python/CMakeLists.txt
This commit is contained in:
Roman Donchenko
2014-01-27 15:28:14 +04:00
parent 06acf7090c d093cb54d5
commit bbc35d609d
40 changed files with 247 additions and 141 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/ml/doc/neural_networks.rst
+3
View File
@@ -240,6 +240,7 @@ This method applies the specified training algorithm to computing/adjusting the
The RPROP training algorithm is parallelized with the TBB library.
If you are using the default ``cvANN_MLP::SIGMOID_SYM`` activation function then the output should be in the range [-1,1], instead of [0,1], for optimal results.
CvANN_MLP::predict
------------------
@@ -257,6 +258,8 @@ Predicts responses for input samples.
The method returns a dummy value which should be ignored.
If you are using the default ``cvANN_MLP::SIGMOID_SYM`` activation function with the default parameter values fparam1=0 and fparam2=0 then the function used is y = 1.7159*tanh(2/3 * x), so the output will range from [-1.7159, 1.7159], instead of [0,1].
CvANN_MLP::get_layer_count
--------------------------
Returns the number of layers in the MLP.