# HG changeset patch
# User SylvainPL <sylvain.pannetier.lebeuf@umontreal.ca>
# Date 1271029955 14400
# Node ID c61b72d07676cdce0a66b30b35590c2440d02a85
# Parent  4306796d60a8d4aa4660f755aebfc8988c1a5f04
Rajout de la capacite de faire decroitre le taux d'apprentissage si demande

diff -r 4306796d60a8 -r c61b72d07676 deep/stacked_dae/v_sylvain/nist_sda_retrieve.py
--- a/deep/stacked_dae/v_sylvain/nist_sda_retrieve.py	Sun Apr 11 19:52:28 2010 -0400
+++ b/deep/stacked_dae/v_sylvain/nist_sda_retrieve.py	Sun Apr 11 19:52:35 2010 -0400
@@ -50,6 +50,11 @@
         rtt = state['reduce_train_to']
     elif REDUCE_TRAIN_TO:
         rtt = REDUCE_TRAIN_TO
+        
+    if state.has_key('decrease_lr'):
+        decrease_lr = state['decrease_lr']
+    else :
+        decrease_lr = 0
  
     n_ins = 32*32
     n_outs = 62 # 10 digits, 26*2 (lower, capitals)
@@ -124,48 +129,48 @@
     if finetune_choice == 0:
         print('\n\n\tfinetune with NIST\n\n')
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1)
+        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1,decrease=decrease_lr)
         channel.save()
     if finetune_choice == 1:
         print('\n\n\tfinetune with P07\n\n')
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_P07(),datasets.nist_all(),max_finetune_epoch_P07,ind_test=0)
+        optimizer.finetune(datasets.nist_P07(),datasets.nist_all(),max_finetune_epoch_P07,ind_test=0,decrease=decrease_lr)
         channel.save()
     if finetune_choice == 2:
         print('\n\n\tfinetune with P07 followed by NIST\n\n')
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_P07(),datasets.nist_all(),max_finetune_epoch_P07,ind_test=20)
-        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=21)
+        optimizer.finetune(datasets.nist_P07(),datasets.nist_all(),max_finetune_epoch_P07,ind_test=20,decrease=decrease_lr)
+        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=21,decrease=decrease_lr)
         channel.save()
     if finetune_choice == 3:
         print('\n\n\tfinetune with NIST only on the logistic regression on top (but validation on P07).\n\
         All hidden units output are input of the logistic regression\n\n')
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1,special=1)
+        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1,special=1,decrease=decrease_lr)
         
         
     if finetune_choice==-1:
-        print('\nSERIE OF 3 DIFFERENT FINETUNINGS')
+        print('\nSERIE OF 4 DIFFERENT FINETUNINGS')
         print('\n\n\tfinetune with NIST\n\n')
         sys.stdout.flush()
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1)
+        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1,decrease=decrease_lr)
         channel.save()
         print('\n\n\tfinetune with P07\n\n')
         sys.stdout.flush()
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_P07(),datasets.nist_all(),max_finetune_epoch_P07,ind_test=0)
+        optimizer.finetune(datasets.nist_P07(),datasets.nist_all(),max_finetune_epoch_P07,ind_test=0,decrease=decrease_lr)
         channel.save()
         print('\n\n\tfinetune with P07 (done earlier) followed by NIST (written here)\n\n')
         sys.stdout.flush()
         optimizer.reload_parameters('params_finetune_P07.txt')
-        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=21)
+        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=21,decrease=decrease_lr)
         channel.save()
         print('\n\n\tfinetune with NIST only on the logistic regression on top.\n\
         All hidden units output are input of the logistic regression\n\n')
         sys.stdout.flush()
         optimizer.reload_parameters(PATH+'params_pretrain.txt')
-        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1,special=1)
+        optimizer.finetune(datasets.nist_all(),datasets.nist_P07(),max_finetune_epoch_NIST,ind_test=1,special=1,decrease=decrease_lr)
         channel.save()
     
     channel.save()