Mercurial > ift6266

changeset 306:a78dbbc61f37

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Meilleure souplesse d'execution, un parametre hard-coade est maintenant plus propre
author SylvainPL <sylvain.pannetier.lebeuf@umontreal.ca>
date Wed, 31 Mar 2010 21:02:27 -0400
parents fe5d428c2acc
children ed0443f7aad4
files deep/stacked_dae/v_sylvain/nist_sda_retrieve.py
diffstat 1 files changed, 14 insertions(+), 8 deletions(-) [+]
line wrap: on
line diff
--- a/deep/stacked_dae/v_sylvain/nist_sda_retrieve.py	Wed Mar 31 21:00:59 2010 -0400
+++ b/deep/stacked_dae/v_sylvain/nist_sda_retrieve.py	Wed Mar 31 21:02:27 2010 -0400
@@ -84,8 +84,14 @@
 ##        print('\n\tpretraining with P07')
 ##        optimizer.pretrain(datasets.nist_P07(min_file=0,max_file=nb_file)) 
     print ('Retrieve pre-train done earlier')
+    
+    if state['pretrain_choice'] == 0:
+        PATH=PATH_NIST
+    elif state['pretrain_choice'] == 1:
+        PATH=PATH_P07
         
     sys.stdout.flush()
+    channel.save()
     
     #Set some of the parameters used for the finetuning
     if state.has_key('finetune_set'):
@@ -107,24 +113,24 @@
     
     if finetune_choice == 0:
         print('\n\n\tfinetune with NIST\n\n')
-        optimizer.reload_parameters('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_all(),datasets.nist_P07(min_file=nb_file),max_finetune_epoch_NIST,ind_test=1)
         channel.save()
     if finetune_choice == 1:
         print('\n\n\tfinetune with P07\n\n')
-        optimizer.reload_parameters('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_P07(min_file=nb_file),datasets.nist_all(),max_finetune_epoch_P07,ind_test=0)
         channel.save()
     if finetune_choice == 2:
         print('\n\n\tfinetune with NIST followed by P07\n\n')
-        optimizer.reload_parameters('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_all(),datasets.nist_P07(min_file=nb_file),max_finetune_epoch_NIST,ind_test=21)
         optimizer.finetune(datasets.nist_P07(min_file=nb_file),datasets.nist_all(),max_finetune_epoch_P07,ind_test=20)
         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('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_all(),datasets.nist_P07(min_file=nb_file),max_finetune_epoch_NIST,ind_test=1,special=1)
         
         
@@ -132,23 +138,23 @@
         print('\nSERIE OF 3 DIFFERENT FINETUNINGS')
         print('\n\n\tfinetune with NIST\n\n')
         sys.stdout.flush()
-        optimizer.reload_parameters('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_all(),datasets.nist_P07(min_file=nb_file),max_finetune_epoch_NIST,ind_test=1)
         channel.save()
         print('\n\n\tfinetune with P07\n\n')
         sys.stdout.flush()
-        optimizer.reload_parameters('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_P07(min_file=nb_file),datasets.nist_all(),max_finetune_epoch_P07,ind_test=0)
         channel.save()
         print('\n\n\tfinetune with NIST (done earlier) followed by P07 (written here)\n\n')
         sys.stdout.flush()
-        optimizer.reload_parameters('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_finetune_NIST.txt')
+        optimizer.reload_parameters('params_finetune_NIST.txt')
         optimizer.finetune(datasets.nist_P07(min_file=nb_file),datasets.nist_all(),max_finetune_epoch_P07,ind_test=20)
         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('/u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/ift6266h10_db/pannetis_finetuningSDA/1/params_pretrain.txt')
+        optimizer.reload_parameters(PATH+'params_pretrain.txt')
         optimizer.finetune(datasets.nist_all(),datasets.nist_P07(min_file=nb_file),max_finetune_epoch_NIST,ind_test=1,special=1)
         channel.save()