|
364
|
1 '''
|
|
|
2 These are parameters used by nist_sda.py. They'll end up as globals in there.
|
|
|
3
|
|
|
4 Rename this file to config.py and configure as needed.
|
|
|
5 DON'T add the renamed file to the repository, as others might use it
|
|
|
6 without realizing it, with dire consequences.
|
|
|
7 '''
|
|
|
8
|
|
|
9 # Set this to True when you want to run cluster tests, ie. you want
|
|
|
10 # to run on the cluster, many jobs, but want to reduce the training
|
|
|
11 # set size and the number of epochs, so you know everything runs
|
|
|
12 # fine on the cluster.
|
|
|
13 # Set this PRIOR to inserting your test jobs in the DB.
|
|
|
14 TEST_CONFIG = False
|
|
|
15
|
|
|
16 NIST_ALL_LOCATION = '/data/lisa/data/nist/by_class/all'
|
|
|
17 NIST_ALL_TRAIN_SIZE = 649081
|
|
|
18 # valid et test =82587 82587
|
|
|
19
|
|
|
20 # change "sandbox" when you're ready
|
|
|
21 JOBDB = 'postgres://ift6266h10@gershwin/ift6266h10_db/rifaisal_csda'
|
|
|
22 EXPERIMENT_PATH = "ift6266.deep.convolutional_dae.salah_exp.nist_csda.jobman_entrypoint"
|
|
|
23
|
|
|
24 ##Pour lancer des travaux sur le cluster: (il faut etre ou se trouve les fichiers)
|
|
|
25 ##python nist_sda.py jobman_insert
|
|
|
26 ##dbidispatch --condor --repeat_jobs=2 jobman sql 'postgres://ift6266h10@gershwin/ift6266h10_db/pannetis_finetuningSDA0' . #C'est le path dans config.py
|
|
|
27
|
|
|
28 # reduce training set to that many examples
|
|
|
29 REDUCE_TRAIN_TO = None
|
|
|
30 # that's a max, it usually doesn't get to that point
|
|
|
31 MAX_FINETUNING_EPOCHS = 1000
|
|
|
32 # number of minibatches before taking means for valid error etc.
|
|
|
33 REDUCE_EVERY = 100
|
|
|
34 #Set the finetune dataset
|
|
|
35 FINETUNE_SET=1
|
|
|
36 #Set the pretrain dataset used. 0: NIST, 1:P07
|
|
|
37 PRETRAIN_CHOICE=1
|
|
|
38
|
|
|
39
|
|
|
40 if TEST_CONFIG:
|
|
|
41 REDUCE_TRAIN_TO = 1000
|
|
|
42 MAX_FINETUNING_EPOCHS = 2
|
|
|
43 REDUCE_EVERY = 10
|
|
|
44
|
|
|
45
|
|
|
46 # This is to configure insertion of jobs on the cluster.
|
|
|
47 # Possible values the hyperparameters can take. These are then
|
|
|
48 # combined with produit_cartesien_jobs so we get a list of all
|
|
|
49 # possible combinations, each one resulting in a job inserted
|
|
|
50 # in the jobman DB.
|
|
|
51
|
|
|
52
|
|
|
53 JOB_VALS = {'pretraining_lr': [0.01],#, 0.001],#, 0.0001],
|
|
|
54 'pretraining_epochs_per_layer': [10],
|
|
|
55 'kernels' : [[[52,5,5], [32,3,3]], [[52,7,7], [52,3,3]]],
|
|
|
56 'mlp_size' : [[1000],[500]],
|
|
|
57 'imgshp' : [[32,32]],
|
|
|
58 'max_pool_layers' : [[[2,2],[2,2]]],
|
|
|
59 'corruption_levels': [[0.2,0.1]],
|
|
|
60 'minibatch_size': [100],
|
|
|
61 'max_finetuning_epochs':[MAX_FINETUNING_EPOCHS],
|
|
|
62 'max_finetuning_epochs_P07':[1000],
|
|
|
63 'finetuning_lr':[0.1,0.01], #0.001 was very bad, so we leave it out
|
|
|
64 'num_hidden_layers':[2],
|
|
|
65 'finetune_set':[1],
|
|
|
66 'pretrain_choice':[1]
|
|
|
67 }
|
|
|
68
|
|
|
69 DEFAULT_HP_NIST = {'pretraining_lr': 0.01,
|
|
|
70 'pretraining_epochs_per_layer': 1,
|
|
|
71 'kernels' : [[4,5,5], [2,3,3]],
|
|
|
72 'mlp_size' : [10],
|
|
|
73 'imgshp' : [32,32],
|
|
|
74 'max_pool_layers' : [[2,2],[2,2]],
|
|
|
75 'corruption_levels': [0.1,0.2],
|
|
|
76 'minibatch_size': 20,
|
|
|
77 'max_finetuning_epochs':MAX_FINETUNING_EPOCHS,
|
|
|
78 'max_finetuning_epochs_P07':1000,
|
|
|
79 'finetuning_lr':0.1, #0.001 was very bad, so we leave it out
|
|
|
80 'num_hidden_layers':2,
|
|
|
81 'finetune_set':1,
|
|
|
82 'pretrain_choice':1,
|
|
|
83 #'reduce_train_to':1000,
|
|
|
84 }
|
|
|
85
|
|
|
86
|
|
|
87
|
|
|
88 ##[pannetis@ceylon test]$ python nist_sda.py test_jobman_entrypoint
|
|
|
89 ##WARNING: untracked file /u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/TMP_DBI/configobj.py
|
|
|
90 ##WARNING: untracked file /u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/TMP_DBI/utils.py
|
|
|
91 ##WARNING: untracked file /u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/config.py
|
|
|
92 ##WARNING: untracked file /u/pannetis/IFT6266/ift6266/deep/stacked_dae/v_sylvain/config2.py
|
|
|
93 ##Creating optimizer with state, DD{'reduce_train_to': 11000, 'pretraining_epochs_per_layer': 2, 'hidden_layers_sizes': 300, 'num_hidden_layers': 2, 'corruption_levels': 0.20000000000000001, 'finetuning_lr': 0.10000000000000001, 'pretrain_choice': 0, 'max_finetuning_epochs': 2, 'version_pylearn': '08b37147dec1', 'finetune_set': -1, 'pretraining_lr': 0.10000000000000001, 'version_ift6266': 'a6b6b1140de9', 'version_theano': 'fb6c3a06cb65', 'minibatch_size': 20}
|
|
|
94 ##SdaSgdOptimizer, max_minibatches = 11000
|
|
|
95 ##C##n_outs 62
|
|
|
96 ##pretrain_lr 0.1
|
|
|
97 ##finetune_lr 0.1
|
|
|
98 ##----
|
|
|
99 ##
|
|
|
100 ##pretraining with NIST
|
|
|
101 ##
|
|
|
102 ##STARTING PRETRAINING, time = 2010-03-29 15:07:43.945981
|
|
|
103 ##Pre-training layer 0, epoch 0, cost 113.562562494
|
|
|
104 ##Pre-training layer 0, epoch 1, cost 113.410032944
|
|
|
105 ##Pre-training layer 1, epoch 0, cost 98.4539954687
|
|
|
106 ##Pre-training layer 1, epoch 1, cost 97.8658966686
|
|
|
107 ##Pretraining took 9.011333 minutes
|
|
|
108 ##
|
|
|
109 ##SERIE OF 3 DIFFERENT FINETUNINGS
|
|
|
110 ##
|
|
|
111 ##
|
|
|
112 ##finetune with NIST
|
|
|
113 ##
|
|
|
114 ##
|
|
|
115 ##STARTING FINETUNING, time = 2010-03-29 15:16:46.512235
|
|
|
116 ##epoch 1, minibatch 4999, validation error on P07 : 29.511250 %
|
|
|
117 ## epoch 1, minibatch 4999, test error on dataset NIST (train data) of best model 40.408509 %
|
|
|
118 ## epoch 1, minibatch 4999, test error on dataset P07 of best model 96.700000 %
|
|
|
119 ##epoch 1, minibatch 9999, validation error on P07 : 25.560000 %
|
|
|
120 ## epoch 1, minibatch 9999, test error on dataset NIST (train data) of best model 34.778969 %
|
|
|
121 ## epoch 1, minibatch 9999, test error on dataset P07 of best model 97.037500 %
|
|
|
122 ##
|
|
|
123 ##Optimization complete with best validation score of 25.560000 %,with test performance 34.778969 % on dataset NIST
|
|
|
124 ##The test score on the P07 dataset is 97.037500
|
|
|
125 ##The finetuning ran for 3.281833 minutes
|
|
|
126 ##
|
|
|
127 ##
|
|
|
128 ##finetune with P07
|
|
|
129 ##
|
|
|
130 ##
|
|
|
131 ##STARTING FINETUNING, time = 2010-03-29 15:20:06.346009
|
|
|
132 ##epoch 1, minibatch 4999, validation error on NIST : 65.226250 %
|
|
|
133 ## epoch 1, minibatch 4999, test error on dataset P07 (train data) of best model 84.465000 %
|
|
|
134 ## epoch 1, minibatch 4999, test error on dataset NIST of best model 65.965237 %
|
|
|
135 ##epoch 1, minibatch 9999, validation error on NIST : 58.745000 %
|
|
|
136 ## epoch 1, minibatch 9999, test error on dataset P07 (train data) of best model 80.405000 %
|
|
|
137 ## epoch 1, minibatch 9999, test error on dataset NIST of best model 61.341923 %
|
|
|
138 ##
|
|
|
139 ##Optimization complete with best validation score of 58.745000 %,with test performance 80.405000 % on dataset P07
|
|
|
140 ##The test score on the NIST dataset is 61.341923
|
|
|
141 ##The finetuning ran for 3.299500 minutes
|
|
|
142 ##
|
|
|
143 ##
|
|
|
144 ##finetune with NIST (done earlier) followed by P07 (written here)
|
|
|
145 ##
|
|
|
146 ##
|
|
|
147 ##STARTING FINETUNING, time = 2010-03-29 15:23:27.947374
|
|
|
148 ##epoch 1, minibatch 4999, validation error on NIST : 83.975000 %
|
|
|
149 ## epoch 1, minibatch 4999, test error on dataset P07 (train data) of best model 83.872500 %
|
|
|
150 ## epoch 1, minibatch 4999, test error on dataset NIST of best model 43.170010 %
|
|
|
151 ##epoch 1, minibatch 9999, validation error on NIST : 79.775000 %
|
|
|
152 ## epoch 1, minibatch 9999, test error on dataset P07 (train data) of best model 80.971250 %
|
|
|
153 ## epoch 1, minibatch 9999, test error on dataset NIST of best model 49.017468 %
|
|
|
154 ##
|
|
|
155 ##Optimization complete with best validation score of 79.775000 %,with test performance 80.971250 % on dataset P07
|
|
|
156 ##The test score on the NIST dataset is 49.017468
|
|
|
157 ##The finetuning ran for 2.851500 minutes
|
|
|
158 ##
|
|
|
159 ##
|
|
|
160 ##finetune with NIST only on the logistic regression on top.
|
|
|
161 ## All hidden units output are input of the logistic regression
|
|
|
162 ##
|
|
|
163 ##
|
|
|
164 ##STARTING FINETUNING, time = 2010-03-29 15:26:21.430557
|
|
|
165 ##epoch 1, minibatch 4999, validation error on P07 : 95.223750 %
|
|
|
166 ## epoch 1, minibatch 4999, test error on dataset NIST (train data) of best model 93.268765 %
|
|
|
167 ## epoch 1, minibatch 4999, test error on dataset P07 of best model 96.535000 %
|
|
|
168 ##epoch 1, minibatch 9999, validation error on P07 : 95.223750 %
|
|
|
169 ##
|
|
|
170 ##Optimization complete with best validation score of 95.223750 %,with test performance 93.268765 % on dataset NIST
|
|
|
171 ##The test score on the P07 dataset is 96.535000
|
|
|
172 ##The finetuning ran for 2.013167 minutes
|
|
|
173 ##Closing remaining open files: /u/pannetis/IFT6266/test/series.h5... done
|
|
|
174 ##[pannetis@ceylon test]$
|
|
|
175
|
|
|
176
|
|
|
177
|
