# HG changeset patch # User SylvainPL # Date 1268789049 14400 # Node ID 6d49cf134a400fce264fafdd13db7c28121f0fb6 # Parent 1bf046c0c84aef2293be171f639789730dd649bc ajout de fonctionnalite pour different finetune dataset diff -r 1bf046c0c84a -r 6d49cf134a40 deep/stacked_dae/v_sylvain/nist_sda.py --- a/deep/stacked_dae/v_sylvain/nist_sda.py Tue Mar 16 20:19:13 2010 -0400 +++ b/deep/stacked_dae/v_sylvain/nist_sda.py Tue Mar 16 21:24:09 2010 -0400 @@ -21,9 +21,8 @@ import jobman, jobman.sql from pylearn.io import filetensor -from ift6266 import datasets - from utils import produit_cartesien_jobs +from copy import copy from sgd_optimization import SdaSgdOptimizer @@ -31,49 +30,8 @@ from ift6266.utils.seriestables import * import tables -############################################################################## -# GLOBALS - -TEST_CONFIG = False - -#NIST_ALL_LOCATION = '/data/lisa/data/nist/by_class/all' -JOBDB = 'postgres://ift6266h10@gershwin/ift6266h10_sandbox_db/sylvainpl_sda_vsylvain' -EXPERIMENT_PATH = "ift6266.deep.stacked_dae.v_sylvain.nist_sda.jobman_entrypoint" - -REDUCE_TRAIN_TO = None -MAX_FINETUNING_EPOCHS = 1000 -# number of minibatches before taking means for valid error etc. -REDUCE_EVERY = 100 - -if TEST_CONFIG: - REDUCE_TRAIN_TO = 1000 - MAX_FINETUNING_EPOCHS = 2 - REDUCE_EVERY = 10 - MINIBATCH_SIZE=20 - -# Possible values the hyperparameters can take. These are then -# combined with produit_cartesien_jobs so we get a list of all -# possible combinations, each one resulting in a job inserted -# in the jobman DB. -JOB_VALS = {'pretraining_lr': [0.1],#, 0.01],#, 0.001],#, 0.0001], - 'pretraining_epochs_per_layer': [10], - 'hidden_layers_sizes': [500], - 'corruption_levels': [0.1], - 'minibatch_size': [20], - 'max_finetuning_epochs':[MAX_FINETUNING_EPOCHS], - 'finetuning_lr':[0.1], #0.001 was very bad, so we leave it out - 'num_hidden_layers':[1,1]} - -# Just useful for tests... minimal number of epochs -DEFAULT_HP_NIST = DD({'finetuning_lr':0.1, - 'pretraining_lr':0.1, - 'pretraining_epochs_per_layer':2, - 'max_finetuning_epochs':2, - 'hidden_layers_sizes':500, - 'corruption_levels':0.2, - 'minibatch_size':20, - 'reduce_train_to':10000, - 'num_hidden_layers':1}) +from ift6266 import datasets +from config import * ''' Function called by jobman upon launching each job @@ -85,48 +43,82 @@ # TODO: remove this, bad for number of simultaneous requests on DB channel.save() - workingdir = os.getcwd() - - ########### Il faudrait arranger ici pour train plus petit - -## print "Will load NIST" -## -## nist = NIST(minibatch_size=20) -## -## print "NIST loaded" -## # For test runs, we don't want to use the whole dataset so # reduce it to fewer elements if asked to. rtt = None if state.has_key('reduce_train_to'): - rtt = int(state['reduce_train_to']/state['minibatch_size']) + rtt = state['reduce_train_to'] elif REDUCE_TRAIN_TO: - rtt = int(REDUCE_TRAIN_TO/MINIBATCH_SIZE) - - if rtt: - print "Reducing training set to "+str(rtt*state['minibatch_size'])+ " examples" - else: - rtt=float('inf') #No reduction -## nist.reduce_train_set(rtt) -## -## train,valid,test = nist.get_tvt() -## dataset = (train,valid,test) - + rtt = REDUCE_TRAIN_TO + n_ins = 32*32 n_outs = 62 # 10 digits, 26*2 (lower, capitals) - + + examples_per_epoch = NIST_ALL_TRAIN_SIZE + series = create_series(state.num_hidden_layers) print "Creating optimizer with state, ", state - optimizer = SdaSgdOptimizer(dataset=datasets.nist_all, hyperparameters=state, \ + optimizer = SdaSgdOptimizer(dataset=datasets.nist_all, + hyperparameters=state, \ n_ins=n_ins, n_outs=n_outs,\ - series=series) + examples_per_epoch=examples_per_epoch, \ + series=series, + max_minibatches=rtt) - optimizer.pretrain(datasets.nist_all,rtt) + parameters=[] + optimizer.pretrain(datasets.nist_all) channel.save() + + #Set some of the parameters used for the finetuning + if state.has_key('finetune_set'): + finetune_choice=state['finetune_set'] + else: + finetune_choice=FINETUNE_SET + + if state.has_key('max_finetuning_epochs'): + max_finetune_epoch_NIST=state['max_finetuning_epochs'] + else: + max_finetune_epoch_NIST=MAX_FINETUNING_EPOCHS + + if state.has_key('max_finetuning_epochs_P07'): + max_finetune_epoch_P07=state['max_finetuning_epochs_P07'] + else: + max_finetune_epoch_P07=max_finetune_epoch_NIST + + #Decide how the finetune is done + + if finetune_choice==0: + print('\n\n\tfinetune avec nist\n\n') + optimizer.reload_parameters() + optimizer.finetune(datasets.nist_all,max_finetune_epoch_NIST) + if finetune_choice==1: + print('\n\n\tfinetune avec P07\n\n') + optimizer.reload_parameters() + optimizer.finetune(datasets.nist_P07,max_finetune_epoch_P07) + if finetune_choice==2: + print('\n\n\tfinetune avec nist suivi de P07\n\n') + optimizer.reload_parameters() + optimizer.finetune(datasets.nist_all,max_finetune_epoch_NIST) + optimizer.finetune(datasets.nist_P07,max_finetune_epoch_P07) - optimizer.finetune(datasets.nist_all,rtt) + if finetune_choice==-1: + print('\nSerie de 3 essais de fine-tuning') + print('\n\n\tfinetune avec nist\n\n') + optimizer.reload_parameters() + optimizer.finetune(datasets.nist_all,max_finetune_epoch_NIST) + channel.save() + print('\n\n\tfinetune avec P07\n\n') + optimizer.reload_parameters() + optimizer.finetune(datasets.nist_P07,max_finetune_epoch_P07) + channel.save() + print('\n\n\tfinetune avec nist suivi de P07\n\n') + optimizer.reload_parameters() + optimizer.finetune(datasets.nist_all,max_finetune_epoch_NIST) + optimizer.finetune(datasets.nist_P07,max_finetune_epoch_P07) + channel.save() + channel.save() return channel.COMPLETE @@ -207,98 +199,19 @@ print "inserted" -class NIST: - def __init__(self, minibatch_size, basepath=None, reduce_train_to=None): - global NIST_ALL_LOCATION - - self.minibatch_size = minibatch_size - self.basepath = basepath and basepath or NIST_ALL_LOCATION - - self.set_filenames() - - # arrays of 2 elements: .x, .y - self.train = [None, None] - self.test = [None, None] - - self.load_train_test() - - self.valid = [[], []] - self.split_train_valid() - if reduce_train_to: - self.reduce_train_set(reduce_train_to) - - def get_tvt(self): - return self.train, self.valid, self.test - - def set_filenames(self): - self.train_files = ['all_train_data.ft', - 'all_train_labels.ft'] - - self.test_files = ['all_test_data.ft', - 'all_test_labels.ft'] - - def load_train_test(self): - self.load_data_labels(self.train_files, self.train) - self.load_data_labels(self.test_files, self.test) - - def load_data_labels(self, filenames, pair): - for i, fn in enumerate(filenames): - f = open(os.path.join(self.basepath, fn)) - pair[i] = filetensor.read(f) - f.close() - - def reduce_train_set(self, max): - self.train[0] = self.train[0][:max] - self.train[1] = self.train[1][:max] - - if max < len(self.test[0]): - for ar in (self.test, self.valid): - ar[0] = ar[0][:max] - ar[1] = ar[1][:max] - - def split_train_valid(self): - test_len = len(self.test[0]) - - new_train_x = self.train[0][:-test_len] - new_train_y = self.train[1][:-test_len] - - self.valid[0] = self.train[0][-test_len:] - self.valid[1] = self.train[1][-test_len:] - - self.train[0] = new_train_x - self.train[1] = new_train_y - -def test_load_nist(): - print "Will load NIST" - - import time - t1 = time.time() - nist = NIST(20) - t2 = time.time() - - print "NIST loaded. time delta = ", t2-t1 - - tr,v,te = nist.get_tvt() - - print "Lenghts: ", len(tr[0]), len(v[0]), len(te[0]) - - raw_input("Press any key") - if __name__ == '__main__': - import sys - args = sys.argv[1:] - if len(args) > 0 and args[0] == 'load_nist': - test_load_nist() + #if len(args) > 0 and args[0] == 'load_nist': + # test_load_nist() - elif len(args) > 0 and args[0] == 'jobman_insert': + if len(args) > 0 and args[0] == 'jobman_insert': jobman_insert_nist() elif len(args) > 0 and args[0] == 'test_jobman_entrypoint': chanmock = DD({'COMPLETE':0,'save':(lambda:None)}) - jobman_entrypoint(DEFAULT_HP_NIST, chanmock) + jobman_entrypoint(DD(DEFAULT_HP_NIST), chanmock) else: print "Bad arguments"