def run(self, epochs=EPOCHS, learning_rate=LEARNING_RATE, regularization=REGULARIZATION, momentum=MOMENTUM): processor = NN_process.lengthPairProcessor( '../data/tweets/pairs/sets/tweet-pairs-train.txt', '../data/tweets/pairs/sets/tweet-no-pairs-train.txt', '../data/wiki/model/docfreq.npy', '../data/wiki/model/minimal', WORDS, EMBEDDING_DIM, BATCH_SIZE) train_x1 = theano.shared(value=processor.x1, name='train_x1', borrow=False) train_x2 = theano.shared(value=processor.x2, name='train_x2', borrow=False) train_l1 = theano.shared(value=processor.l1, name='train_l1', borrow=False) train_l2 = theano.shared(value=processor.l2, name='train_l2', borrow=False) train_y = theano.shared(value=processor.y, name='train_y', borrow=False) train_z = theano.shared(value=processor.z, name='train_z', borrow=False) print 'Initializing train function...' train = self.train_function_momentum(train_x1, train_x2, train_l1, train_l2, train_y, train_z) lin = numpy.linspace(0, float(WORDS) - 1.0, float(WORDS)) c = [] t = Thread(target=processor.process) t.start() for e in xrange(epochs): processor.new_epoch() processor.lock.acquire() while not processor.ready: processor.lock.wait() processor.lock.release() train_x1.set_value(processor.x1, borrow=False) train_x2.set_value(processor.x2, borrow=False) train_l1.set_value(processor.l1, borrow=False) train_l2.set_value(processor.l2, borrow=False) train_y.set_value(processor.y, borrow=False) train_z.set_value(processor.z, borrow=False) processor.lock.acquire() processor.cont = True processor.ready = False processor.lock.notifyAll() processor.lock.release() for b in xrange(BATCHES): c = [] cost = train(lr=learning_rate, reg=regularization, mom=momentum) c.append(cost) processor.lock.acquire() while not processor.ready: processor.lock.wait() processor.lock.release() # print 'Training, batch %d (from %d), cost %.5f' % (b, BATCHES, cost) # we = self.model1.W.get_value() # print we # temp = math.log(1 - math.exp(-we[0])) / (WORDS - 1.0) # f = numpy.exp(we[0] + lin * temp) + (1 - math.exp(we[0])) # print f train_x1.set_value(processor.x1, borrow=False) train_x2.set_value(processor.x2, borrow=False) train_l1.set_value(processor.l1, borrow=False) train_l2.set_value(processor.l2, borrow=False) train_y.set_value(processor.y, borrow=False) train_z.set_value(processor.z, borrow=False) processor.lock.acquire() if b < BATCHES - 2: processor.cont = True processor.ready = False if b == BATCHES - 1 and e == epochs - 1: processor.stop = True processor.lock.notifyAll() processor.lock.release() print 'Training, epoch %d, cost %.5f' % (e, numpy.mean(c)) we = self.model1.W.get_value() s = 1.0 / (1.0 + numpy.exp(-we)) print we print s temp = math.log(1 - math.exp(-s[0])) / (WORDS - 1.0) f = numpy.exp(s[0] + lin * temp) + (1 - math.exp(s[0])) print f t.join() self.save_me('run6.npy')
def run(self, epochs=EPOCHS, learning_rate=LEARNING_RATE, regularization=REGULARIZATION, momentum=MOMENTUM): processor = NN_process.lengthPairProcessor('../data/tweets/pairs/sets/tweet-pairs-train.txt', '../data/tweets/pairs/sets/tweet-no-pairs-train.txt', '../data/wiki/model/docfreq.npy', '../data/wiki/model/minimal', WORDS, EMBEDDING_DIM, BATCH_SIZE) train_x1 = theano.shared(value=processor.x1, name='train_x1', borrow=False) train_x2 = theano.shared(value=processor.x2, name='train_x2', borrow=False) train_l1 = theano.shared(value=processor.l1, name='train_l1', borrow=False) train_l2 = theano.shared(value=processor.l2, name='train_l2', borrow=False) train_y = theano.shared(value=processor.y, name='train_y', borrow=False) train_z = theano.shared(value=processor.z, name='train_z', borrow=False) print 'Initializing train function...' train = self.train_function_momentum(train_x1, train_x2, train_l1, train_l2, train_y, train_z) lin = numpy.linspace(0, float(WORDS) - 1.0, float(WORDS)) c = [] t = Thread(target=processor.process) t.start() for e in xrange(epochs): processor.new_epoch() processor.lock.acquire() while not processor.ready: processor.lock.wait() processor.lock.release() train_x1.set_value(processor.x1, borrow=False) train_x2.set_value(processor.x2, borrow=False) train_l1.set_value(processor.l1, borrow=False) train_l2.set_value(processor.l2, borrow=False) train_y.set_value(processor.y, borrow=False) train_z.set_value(processor.z, borrow=False) processor.lock.acquire() processor.cont = True processor.ready = False processor.lock.notifyAll() processor.lock.release() for b in xrange(BATCHES): c = [] cost = train(lr=learning_rate, reg=regularization, mom=momentum) c.append(cost) processor.lock.acquire() while not processor.ready: processor.lock.wait() processor.lock.release() train_x1.set_value(processor.x1, borrow=False) train_x2.set_value(processor.x2, borrow=False) train_l1.set_value(processor.l1, borrow=False) train_l2.set_value(processor.l2, borrow=False) train_y.set_value(processor.y, borrow=False) train_z.set_value(processor.z, borrow=False) processor.lock.acquire() if b < BATCHES-2: processor.cont = True processor.ready = False if b == BATCHES-1 and e == epochs-1: processor.stop = True processor.lock.notifyAll() processor.lock.release() print 'Training, epoch %d, cost %.5f' % (e, numpy.mean(c)) we = self.model1.W.get_value() print we f = we[0] * (lin ** 4) + we[1] * (lin ** 3) + we[2] * (lin ** 2) + we[3] * lin + 1.0 print f self.save_me('run5.npy')
def run(self, epochs=EPOCHS, learning_rate=LEARNING_RATE, regularization=REGULARIZATION, momentum=MOMENTUM): processor = NN_process.lengthPairProcessor( '../data/pairs/sets/enwiki_pairs_' + WORDS_FILE + '-train.txt', '../data/pairs/sets/enwiki_no_pairs_' + WORDS_FILE + '-train.txt', '../data/model/docfreq.npy', '../data/model/minimal', WORDS, EMBEDDING_DIM, BATCH_SIZE) train_x1 = theano.shared(value=processor.x1, name='train_x1', borrow=False) train_x2 = theano.shared(value=processor.x2, name='train_x2', borrow=False) train_l1 = theano.shared(value=processor.l1, name='train_l1', borrow=False) train_l2 = theano.shared(value=processor.l2, name='train_l2', borrow=False) train_y = theano.shared(value=processor.y, name='train_y', borrow=False) train_z = theano.shared(value=processor.z, name='train_z', borrow=False) print 'Initializing train function...' train = self.train_function_momentum(train_x1, train_x2, train_l1, train_l2, train_y, train_z) lin = numpy.linspace(0, 29.0, 30.0) t = Thread(target=processor.process) t.start() for e in xrange(epochs): processor.new_epoch() processor.lock.acquire() while not processor.ready: processor.lock.wait() processor.lock.release() train_x1.set_value(processor.x1, borrow=False) train_x2.set_value(processor.x2, borrow=False) train_l1.set_value(processor.l1, borrow=False) train_l2.set_value(processor.l2, borrow=False) train_y.set_value(processor.y, borrow=False) train_z.set_value(processor.z, borrow=False) processor.lock.acquire() processor.cont = True processor.ready = False processor.lock.notifyAll() processor.lock.release() for b in xrange(BATCHES): #c = [] cost = train(lr=learning_rate, reg=regularization, mom=momentum) #c.append(cost) print 'Training, batch %d, cost %.5f' % (b, cost) we = self.model1.W.get_value() print repr(we) f = we[0] * (lin**2) + we[1] * lin + we[2] print f processor.lock.acquire() while not processor.ready: processor.lock.wait() processor.lock.release() train_x1.set_value(processor.x1, borrow=False) train_x2.set_value(processor.x2, borrow=False) train_l1.set_value(processor.l1, borrow=False) train_l2.set_value(processor.l2, borrow=False) train_y.set_value(processor.y, borrow=False) train_z.set_value(processor.z, borrow=False) processor.lock.acquire() if b < BATCHES - 2: processor.cont = True processor.ready = False if b == BATCHES - 1 and e == epochs - 1: processor.stop = True processor.lock.notifyAll() processor.lock.release() #print 'Training, epoch %d, cost %.5f' % (e, numpy.mean(c)) self.save_me('run4.npy')