PLearn 0.1
|
00001 // -*- C++ -*- 00002 00003 // SequentialValidation.h 00004 // 00005 // Copyright (C) 2003 Rejean Ducharme, Yoshua Bengio 00006 // Copyright (C) 2003 Pascal Vincent 00007 // 00008 // Redistribution and use in source and binary forms, with or without 00009 // modification, are permitted provided that the following conditions are met: 00010 // 00011 // 1. Redistributions of source code must retain the above copyright 00012 // notice, this list of conditions and the following disclaimer. 00013 // 00014 // 2. Redistributions in binary form must reproduce the above copyright 00015 // notice, this list of conditions and the following disclaimer in the 00016 // documentation and/or other materials provided with the distribution. 00017 // 00018 // 3. The name of the authors may not be used to endorse or promote 00019 // products derived from this software without specific prior written 00020 // permission. 00021 // 00022 // THIS SOFTWARE IS PROVIDED BY THE AUTHORS ``AS IS'' AND ANY EXPRESS OR 00023 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 00024 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN 00025 // NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 00026 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED 00027 // TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR 00028 // PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF 00029 // LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING 00030 // NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS 00031 // SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 00032 // 00033 // This file is part of the PLearn library. For more information on the PLearn 00034 // library, go to the PLearn Web site at www.plearn.org 00035 00036 00037 00038 #ifndef SEQUENTIAL_VALIDATION 00039 #define SEQUENTIAL_VALIDATION 00040 00041 #include <plearn/base/PP.h> 00042 #include <plearn/base/Object.h> 00043 #include <plearn/vmat/VMat.h> 00044 #include <plearn/math/VecStatsCollector.h> 00045 #include <plearn/io/PPath.h> 00046 #include <plearn_learners/testers/PTester.h> // for using class StatSpec 00047 #include <plearn_learners/generic/StatefulLearner.h> 00048 00049 namespace PLearn { 00050 using namespace std; 00051 00052 00053 class SequentialValidation: public Object 00054 { 00055 typedef Object inherited; 00056 00057 protected: 00058 //##### Data members required for simulation ############################ 00059 00061 PP<VecStatsCollector> train_stats; 00062 00064 PP<VecStatsCollector> accessory_train_stats; 00065 00067 PP<VecStatsCollector> test_stats; 00068 00070 PP<VecStatsCollector> sequence_stats; 00071 00073 PP<VecStatsCollector> timewise_stats; 00074 00075 // Contains pointers to train_stats and test_stats 00076 TVec< PP<VecStatsCollector> > stcol; 00077 00079 TVec<StatSpec> statspecs; 00080 00082 TVec<StatSpec> timewise_statspecs; 00083 00085 VMat global_stats_vm; 00086 00088 VMat split_stats_vm; 00089 00091 VMat timewise_stats_vm; 00092 00094 Vec input, target; 00095 Vec dummy_output; 00096 Vec dummy_costs; 00097 Vec output; 00098 Vec costs; 00099 00100 public: 00101 00102 // ********************* 00103 // * public options * 00104 // ********************* 00105 00107 int init_train_size; 00108 00118 int warmup_size; 00119 00122 int train_step; 00123 00125 int last_test_time; 00126 00128 VMat dataset; 00129 00131 PP<StatefulLearner> learner; 00132 00136 TVec< PP<StatefulLearner> > accessory_learners; 00137 00139 TVec<string> statnames; 00140 00142 TVec<string> timewise_statnames; 00143 00145 PPath expdir; 00146 00147 bool report_stats; 00148 bool save_final_model; 00149 bool save_initial_model; 00150 bool save_initial_seqval; 00151 bool save_data_sets; 00152 bool save_test_outputs; 00153 bool save_test_costs; 00154 bool save_stat_collectors; 00155 bool provide_learner_expdir; /* =true */ 00156 00160 bool save_sequence_stats; 00161 00167 bool report_memory_usage; 00168 00178 TVec< pair<string,string> > measure_after_train; 00179 00182 TVec< pair<string,string> > measure_after_test; 00183 00184 private: 00185 00187 void build_(); 00188 00189 protected: 00190 00192 static void declareOptions(OptionList& ol); 00193 00195 virtual void reportStats(const Vec& global_result); 00196 00198 virtual void reportMemoryUsage(int t); 00199 00203 virtual bool shouldTrain(int t); 00204 00207 virtual VMat trainVMat(int t); 00208 00211 virtual VMat testVMat(int t); 00212 00214 virtual int maxTimeStep() const; 00215 00218 virtual void measureOptions(const TVec< pair<string,string> >& options, 00219 PPath where_to_save); 00220 00221 public: 00222 00224 SequentialValidation(); 00225 00227 virtual void build(); 00228 00229 virtual void setExperimentDirectory(const PPath& _expdir); 00230 00232 virtual void run(); 00233 00235 virtual void warmupModel(int warmup_size); 00236 00239 virtual void setTestStartTime(int test_start_time, bool call_build = true); 00240 00242 virtual void createStatCollectors(); 00243 00245 virtual void createStatSpecs(); 00246 00248 virtual void createStatVMats(); 00249 00251 virtual void trainLearners(VMat training_set); 00252 00255 virtual void testLearners(VMat test_set); 00256 00259 void makeDeepCopyFromShallowCopy(CopiesMap& copies); 00260 00261 PLEARN_DECLARE_OBJECT(SequentialValidation); 00262 }; 00263 00265 DECLARE_OBJECT_PTR(SequentialValidation); 00266 00267 } // end of namespace PLearn 00268 00269 #endif 00270 00271 00272 /* 00273 Local Variables: 00274 mode:c++ 00275 c-basic-offset:4 00276 c-file-style:"stroustrup" 00277 c-file-offsets:((innamespace . 0)(inline-open . 0)) 00278 indent-tabs-mode:nil 00279 fill-column:79 00280 End: 00281 */ 00282 // vim: filetype=cpp:expandtab:shiftwidth=4:tabstop=8:softtabstop=4:encoding=utf-8:textwidth=79 :