def __init__(self): print 'call me' self.parameters = Parameters() if LBL: graph.output_weights = self.parameters.output_weights graph.output_biases = self.parameters.output_biases graph.score_biases = self.parameters.score_biases else: graph.hidden_weights = self.parameters.hidden_weights graph.hidden_biases = self.parameters.hidden_biases graph.output_weights = self.parameters.output_weights graph.output_biases = self.parameters.output_biases # (self.graph_train, self.graph_predict, self.graph_verbose_predict) = graph.functions(self.parameters) import sets self.train_loss = MovingAverage() self.train_err = MovingAverage() self.train_lossnonzero = MovingAverage() self.train_squashloss = MovingAverage() self.train_unpenalized_loss = MovingAverage() self.train_l1penalty = MovingAverage() self.train_unpenalized_lossnonzero = MovingAverage() self.train_correct_score = MovingAverage() self.train_noise_score = MovingAverage() self.train_cnt = 0
def __init__(self, modelname="", window_size=HYPERPARAMETERS["WINDOW_SIZE"], vocab_size=vocabulary.wordmap().len, embedding_size=HYPERPARAMETERS["EMBEDDING_SIZE"], hidden_size=HYPERPARAMETERS["HIDDEN_SIZE"], seed=miscglobals.RANDOMSEED, initial_embeddings=None, two_hidden_layers=HYPERPARAMETERS["TWO_HIDDEN_LAYERS"]): self.modelname = modelname self.parameters = Parameters(window_size, vocab_size, embedding_size, hidden_size, seed, initial_embeddings, two_hidden_layers) if LBL: graph.output_weights = self.parameters.output_weights graph.output_biases = self.parameters.output_biases graph.score_biases = self.parameters.score_biases else: graph.hidden_weights = self.parameters.hidden_weights graph.hidden_biases = self.parameters.hidden_biases if self.parameters.two_hidden_layers: graph.hidden2_weights = self.parameters.hidden2_weights graph.hidden2_biases = self.parameters.hidden2_biases graph.output_weights = self.parameters.output_weights graph.output_biases = self.parameters.output_biases # (self.graph_train, self.graph_predict, self.graph_verbose_predict) = graph.functions(self.parameters) import sets self.train_loss = MovingAverage() self.train_err = MovingAverage() self.train_lossnonzero = MovingAverage() self.train_squashloss = MovingAverage() self.train_unpenalized_loss = MovingAverage() self.train_l1penalty = MovingAverage() self.train_unpenalized_lossnonzero = MovingAverage() self.train_correct_score = MovingAverage() self.train_noise_score = MovingAverage() self.train_cnt = 0
#RELOAD previous model channel.save() err = dict([(trainsize, {}) for trainsize in VALIDATION_TRAININGSIZE]) rebuildunsup(model, LR, NOISE_LVL, ACTIVATION_REGULARIZATION_COEFF, WEIGHT_REGULARIZATION_COEFF, BATCHSIZE, train) epoch = 0 if epoch in EPOCHSTEST: svm_validation(err, epoch, model, train, datatrain, datatrainsave, datatest, datatestsave, VALIDATION_TRAININGSIZE, VALIDATION_RUNS_FOR_EACH_TRAININGSIZE, PATH_SAVE, PATH_DATA, NAME_DATATEST) channel.save() train_reconstruction_error_mvgavg = MovingAverage() for epoch in xrange(1, NEPOCHS + 1): time1 = time.time() state.currentepoch = epoch for filenb in xrange(1, NB_FILES + 1): print >> sys.stderr, "\t\tAbout to read file %s..." % percent( filenb, NB_FILES) print >> sys.stderr, "\t\t", stats() # initial_file_time = time.time() f = open(PATH_DATA + NAME_DATA + '_%s.pkl' % filenb, 'r') object = numpy.asarray(cPickle.load(f), dtype=theano.config.floatX) print >> sys.stderr, "\t\t...read file %s" % percent( filenb, NB_FILES) print >> sys.stderr, "\t\t", stats() # The last training file is not of the same shape as the other training files. # So, to avoid a GPU memory error, we want to make sure it is the same size.
import sys # Restrict to a particular path. class RequestHandler(SimpleXMLRPCRequestHandler): rpc_paths = ('/RPC2', ) # Create server server = SimpleXMLRPCServer(("0.0.0.0", jv_port + 1), requestHandler=RequestHandler) server.register_introspection_functions() from common.movingaverage import MovingAverage broke = MovingAverage() def extractKeyphrases(txt): if broke.cnt % 100 == 0: print >> sys.stderr, "%s documents could NOT have keyphrase extracted" % broke try: kw = s.kea.extractKeyphrases(txt) broke.add(0) return kw except: print >> sys.stderr, "Oops! Couldn't extract keyphrases over:", repr( txt) broke.add(1) return []