state.BATCH_TEST = 100
state.BATCH_CREATION_LIBSVM = 500
state.NB_MAX_TRAINING_EXAMPLES_SVM = 10000
#NB_MAX_TRAINING_EXAMPLES_SVM = 1000 # FIXME: Change back to 10000 <========================================================================
# 1000 is just for fast running during development
#NB_MAX_TRAINING_EXAMPLES_SVM = 100 # FIXME: Change back to 10000 <========================================================================
# # 100 is just for superfast running during development
state.SVM_INITIALC = 0.001
state.SVM_STEPFACTOR = 10.
state.SVM_MAXSTEPS = 10
#hardcoded path to your liblinear source:
#state.SVMPATH = '/work/glorotxa/netscale_sentiment_for_ET/lib/liblinear/'
state.SVMPATH = '/home/turian/dev/python/DARPA-preprocessor/preprocessor_baseline_UdeM/lib/install/bin/'
state.batchsize = 10
# The total number of files into which the training set is broken
state.nb_files = 15
#state.path_data = '/scratch/glorotxa/OpenTable/'
#state.path_data = '/home/turian/data/DARPAproject/randomprojection.dimensions=1000.seed=0.randomization=gaussian.mode=online.scale=0.172946.squash=erf/'
#state.path_data = '/home/turian/data/DARPAproject/randomprojection.dimensions=1000.seed=0.randomization=ternary.ternary_non_zero_percent=0.010000.mode=online.scale=1.748360.squash=erf/'
state.path_data = '/home/turian/data/DARPAproject/'
# Train and test (validation) here should be disjoint subsets of the
# original full training set.
state.name_traindata = 'OpenTable_5000_train_instances'
state.name_trainlabel = 'OpenTable_5000_train_labels'
state.name_testdata = 'OpenTable_5000_test_instances'
state.name_testlabel = 'OpenTable_5000_test_labels'
#epochstest = [[0,5,30],[0,5,30],[0,2,4,8,16,30]] state.BATCH_TEST = 100 state.BATCH_CREATION_LIBSVM = 500 state.NB_MAX_TRAINING_EXAMPLES_SVM = 10000 #NB_MAX_TRAINING_EXAMPLES_SVM = 1000 # FIXME: Change back to 10000 <======================================================================== # 1000 is just for fast running during development #NB_MAX_TRAINING_EXAMPLES_SVM = 100 # FIXME: Change back to 10000 <======================================================================== # # 100 is just for superfast running during development state.SVM_INITIALC = 0.001 state.SVM_STEPFACTOR = 10. state.SVM_MAXSTEPS = 10 #hardcoded path to your liblinear source: state.SVMPATH = '/work/glorotxa/netscale_sentiment_for_ET/lib/liblinear/' state.batchsize = 10 # The total number of files into which the training set is broken state.nb_files = 15 state.path_data = '/scratch/glorotxa/OpenTable/' # Train and test (validation) here should be disjoint subsets of the # original full training set. state.name_traindata = 'OpenTable_5000_train_instances' state.name_trainlabel = 'OpenTable_5000_train_labels' state.name_testdata = 'OpenTable_5000_test_instances' state.name_testlabel = 'OpenTable_5000_test_labels' # If there is a model file specified to build upon, the output of this # model is the input for the model we are currently building.
#epochstest = [[0,5,30],[0,5,30],[0,2,4,8,16,30]]
state.BATCH_TEST = 100
state.BATCH_CREATION_LIBSVM = 500
state.NB_MAX_TRAINING_EXAMPLES_SVM = 10000
#NB_MAX_TRAINING_EXAMPLES_SVM = 1000 # FIXME: Change back to 10000 <========================================================================
# 1000 is just for fast running during development
#NB_MAX_TRAINING_EXAMPLES_SVM = 100 # FIXME: Change back to 10000 <========================================================================
# # 100 is just for superfast running during development
state.SVM_INITIALC = 0.001
state.SVM_STEPFACTOR = 10.
state.SVM_MAXSTEPS = 10
#hardcoded path to your liblinear source:
state.SVMPATH = '/work/glorotxa/netscale_sentiment_for_ET/lib/liblinear/'
state.batchsize = 10
# The total number of files into which the training set is broken
state.nb_files = 15
state.path_data = '/scratch/glorotxa/OpenTable/'
# Train and test (validation) here should be disjoint subsets of the
# original full training set.
state.name_traindata = 'OpenTable_5000_train_instances'
state.name_trainlabel = 'OpenTable_5000_train_labels'
state.name_testdata = 'OpenTable_5000_test_instances'
state.name_testlabel = 'OpenTable_5000_test_labels'
# If there is a model file specified to build upon, the output of this
# model is the input for the model we are currently building.
