Mercurial > ift6266

changeset 327:4306796d60a8

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Rajout de la capacite de faire decroitre le taux d'apprentissage si demande
author SylvainPL <sylvain.pannetier.lebeuf@umontreal.ca>
date Sun, 11 Apr 2010 19:52:28 -0400
parents b762ac18a2d7
children c61b72d07676
files deep/stacked_dae/v_sylvain/nist_sda.py
diffstat 1 files changed, 14 insertions(+), 9 deletions(-) [+]
line wrap: on
line diff
--- a/deep/stacked_dae/v_sylvain/nist_sda.py	Fri Apr 09 15:50:11 2010 -0400
+++ b/deep/stacked_dae/v_sylvain/nist_sda.py	Sun Apr 11 19:52:28 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)
@@ -116,24 +121,24 @@
     if finetune_choice == 0:
         print('\n\n\tfinetune with NIST\n\n')
         optimizer.reload_parameters('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('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('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('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:
@@ -141,23 +146,23 @@
         print('\n\n\tfinetune with NIST\n\n')
         sys.stdout.flush()
         optimizer.reload_parameters('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('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('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()