catkin friendly and "hacked" for using cpu version of region layer wi…

…th tiny yolov2.

The reason of the "hack" is extended in ganyc717#4. As a summary, the time expend in that layer was drastically increasing for some reason. Current version is stable and actually faster than GPU implementation in a MSI laptop with an i7.

CMakeLists.txt

@@ -1,4 +1,5 @@
 cmake_minimum_required(VERSION 2.8)
+project(darknet)
 set(CMAKE_CXX_FLAGS "-std=c++11 -O2 -DNDEBUG " )
 
 set(OPENCV ON)
@@ -28,4 +29,6 @@ include_directories(./darknet_cl/clBLAS)
 
 link_libraries(libpthread.so)
 
-add_executable(darknet ${DIR_LIB_SRC} ${DIR_EXAMPLE_SRC})
+catkin_package( INCLUDE_DIRS ./darknet_cl/include ./darknet_cl/clBLAS)
+
+add_library(darknet ${DIR_LIB_SRC} ${DIR_EXAMPLE_SRC})

darknet_cl/src/network.cpp

@@ -770,23 +770,44 @@ void forward_network_gpu(network *netp)
  if(net.truth){
  cl_push_array(net.truth_gpu, net.truth, net.truths*net.batch);
  }
-
+ system("clear");
  int i;
  for(i = 0; i < net.n; ++i){
+ auto t0 = std::chrono::system_clock::now();
  net.index = i;
  layer l = net.layers[i];
- if(l.delta_gpu.buffer && l.delta_gpu.size > 0){
- fill_gpu(l.outputs * l.batch, 0, l.delta_gpu, 1);
+ if (i == 15) {
+ if (l.delta) {
+ fill_cpu(l.outputs * l.batch, 0, l.delta, 1);
+ }
+ //copy net.input_gpu into net.input
+ cl_pull_array(net.input_gpu, net.input, l.inputs*l.batch);
+ l.forward(l, net);
+
+ net.input = l.output;
+ if (l.truth) {
+ net.truth = l.output;
+ }
  }
- l.forward_gpu(l, net);
- net.input_gpu = l.output_gpu;
- net.input = l.output;
- if(l.truth) {
- net.truth_gpu = l.output_gpu;
- net.truth = l.output;
+ else{
+ if (l.delta_gpu.buffer && l.delta_gpu.size > 0) {
+ fill_gpu(l.outputs * l.batch, 0, l.delta_gpu, 1);
+ }
+ l.forward_gpu(l, net);
+
+ net.input_gpu = l.output_gpu;
+ net.input = l.output;
+ if (l.truth) {
+ net.truth_gpu = l.output_gpu;
+ net.truth = l.output;
+ }
  }
+
+
+ auto t1 = std::chrono::system_clock::now();
+ std::cout << "Layer: " << i << " time: " << std::chrono::duration_cast<std::chrono::microseconds>(t1-t0).count() << std::endl;
  }
- pull_network_output(netp);
+ //pull_network_output(netp);
  calc_network_cost(netp);
 }
 

darknet_cl/src/region_layer.cpp

@@ -159,9 +159,9 @@ int entry_index(layer l, int batch, int location, int entry)
 void forward_region_layer(const layer l, network net)
 {
  int i,j,b,t,n;
- memcpy(l.output, net.input, l.outputs*l.batch*sizeof(float));
+ memcpy(l.output, net.input, l.inputs*l.batch*sizeof(float));
 
-#ifndef GPU
+//#ifndef GPU
  for (b = 0; b < l.batch; ++b){
  for(n = 0; n < l.n; ++n){
  int index = entry_index(l, b, n*l.w*l.h, 0);
@@ -184,7 +184,7 @@ void forward_region_layer(const layer l, network net)
  int index = entry_index(l, 0, 0, l.coords + !l.background);
  softmax_cpu(net.input + index, l.classes + l.background, l.batch*l.n, l.inputs/l.n, l.w*l.h, 1, l.w*l.h, 1, l.output + index);
  }
-#endif
+//#endif
 
  memset(l.delta, 0, l.outputs * l.batch * sizeof(float));
  if(!net.train) return;

package.xml

@@ -0,0 +1,45 @@
+<?xml version="1.0"?>
+<package>
+ <name>darknet</name>
+ <version>0.0.1</version>
+ <description>Cool lib with tools for 3d and 2d data processing</description>
+
+ <!-- One maintainer tag required, multiple allowed, one person per tag --> 
+ <!-- Example: -->
+ <!-- <maintainer email="[email protected]">Jane Doe</maintainer> -->
+ <maintainer email="[email protected]">Pablo Ramon Soria</maintainer>
+
+
+ <!-- One license tag required, multiple allowed, one license per tag -->
+ <!-- Commonly used license strings: -->
+ <!-- BSD, MIT, Boost Software License, GPLv2, GPLv3, LGPLv2.1, LGPLv3 -->
+ <license>MIT</license>
+
+
+ <!-- Url tags are optional, but multiple are allowed, one per tag -->
+ <!-- Optional attribute type can be: website, bugtracker, or repository -->
+ <!-- Example: -->
+ <!-- <url type="website">http:https://wiki.ros.org/uav_abstraction_layer</url> -->
+
+
+ <!-- The *_depend tags are used to specify dependencies -->
+ <!-- Dependencies can be catkin packages or system dependencies -->
+ <!-- Examples: -->
+ <!-- Use build_depend for packages you need at compile time: -->
+ <!-- <build_depend>message_generation</build_depend> -->
+ <!-- Use buildtool_depend for build tool packages: -->
+ <!-- <buildtool_depend>catkin</buildtool_depend> -->
+ <!-- Use run_depend for packages you need at runtime: -->
+ <!-- <run_depend>message_runtime</run_depend> -->
+ <!-- Use test_depend for packages you need only for testing: -->
+ <!-- <test_depend>gtest</test_depend> -->
+ <buildtool_depend>catkin</buildtool_depend>
+ <build_depend>roscpp</build_depend>
+ <run_depend>roscpp</run_depend>
+
+ <!-- The export tag contains other, unspecified, tags -->
+ <export>
+ <!-- Other tools can request additional information be placed here -->
+
+ </export>
+</package>