def testloadData(self):
nExamples = 15
train_data = '/home/bhanu/Downloads/relationClassification/dataCamera/allDataTrain.mat'
pre_trained_weights = '/home/bhanu/Downloads/relationClassification/dataCamera/pretrainedWeights.mat'
rnnData = RNNDataCorpus()
rnnData.load_data(load_file=train_data, nExamples=nExamples)
params = Params(data=rnnData, wordSize=50, rankWo=3)
# n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
# theta = np.random.normal(loc=0.0, scale=np.math.pow(10,-5)**2, size = n*(2*n+1) + n*2*n + nLabels*fanIn + n*nWords + (2*n*rank+n)*nWords)
#
# #init respective parameters with prior values
# W, WO, Wcat, Wv, Wo = unroll_theta(theta, params)
# Wo[:n,:] = np.ones((n,Wo.shape[1])) #init word matrices with Identity matrices + epsilon
#load pre-trained weights here
mats = sio.loadmat(pre_trained_weights)
Wv = mats.get('Wv')
W = mats.get('W')
WO = mats.get('WO')
Wo = np.ndarray(
shape=(2 * params.wordSize * params.rankWo + params.wordSize) *
params.nWords,
dtype='float64')
sentencesIdx = np.arange(nExamples)
[allSNum_batch, allSNN_batch, Wv_batch, Wo_batch,
allWordInds] = getRelevantWords(rnnData, sentencesIdx, Wv, Wo, params)
print
def train():
SEED = 131742
load_model = False
custom_load = True #loads model from previously saved model except Wcat
np.random.seed(SEED)
#get sentences, trees and labels
nExamples = 5
print "loading data.."
rnnData_train = RNNDataCorpus()
rnnData_train.load_data_srl(load_file=config.train_data_srl, nExamples=nExamples)
rnnData_dev = RNNDataCorpus()
rnnData_dev.load_data_srl(load_file=config.dev_data_srl, nExamples=nExamples)
print "Number of sentences loaded in training data: ", rnnData_train.ndoc()
#initialize params
print "initializing params"
params = Params(data=rnnData_train, wordSize=52, rankWo=2)
n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
if(load_model):
with open(config.saved_params_file+"_45", 'r') as loadfile:
rnn = cPickle.load(loadfile)
elif(custom_load):
d = 2#extra features for wordvectors
Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
Wv = 0.01*np.random.randn(n, nWords)
WO = 0.01*np.random.randn(n, 2*n)
W = 0.01*np.random.randn(n, 2*n+1)
#load pre-trained weights here
with open(config.saved_params_file+'_65', 'r') as loadfile:
oldrnn = cPickle.load(loadfile)
Wv[:-d,:] = oldrnn.Wv
# WO[:-d,:] = oldrnn.WO
rnn = MVRNN(W, WO, Wcat, Wv, Wo)
else:
Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
Wv = 0.01*np.random.randn(n, nWords)
WO = 0.01*np.random.randn(n, 2*n)
W = 0.01*np.random.randn(n, 2*n+1)
rnn = MVRNN(W, WO, Wcat, Wv, Wo)
[_, _, all_train_idx] = getRelevantWords(rnnData_train, rnn.Wv,rnn.Wo,params) #sets nWords_reduced, returns new arrays
params.setNumReducedWords(len(all_train_idx))
theta = rnn.getTheta(params, all_train_idx)
#optimize
print "starting training using SGD..."
nIter = 500
optimizer = StochasticGradientDescent(niter=nIter , learning_rate=0.01, learningrateFactor=1.0, printAt10Iter='.', printAt100Iter='\n+')
optimizer.minimizeBatches(rnn=rnn, rnnData_train=rnnData_train, allTrainSentIdx=all_train_idx, params=params, x0=theta, func=costFn, fprime=None,
rnnData_test=rnnData_dev, initialSetSize=1, niter=nIter, seed=17,
modelFileName=config.saved_params_file+'SGD_SRL', printStatistics=True, modelSaveIter=1, nIterInPart=1,
nFetch=-1, rnd=None, nodeid=-1)
print "Finished training! "
def testloadData(self):
nExamples = 15
train_data = '/home/bhanu/Downloads/relationClassification/dataCamera/allDataTrain.mat'
pre_trained_weights = '/home/bhanu/Downloads/relationClassification/dataCamera/pretrainedWeights.mat'
rnnData = RNNDataCorpus()
rnnData.load_data(load_file=train_data, nExamples=nExamples)
params = Params(data=rnnData, wordSize=50, rankWo=3)
# n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
# theta = np.random.normal(loc=0.0, scale=np.math.pow(10,-5)**2, size = n*(2*n+1) + n*2*n + nLabels*fanIn + n*nWords + (2*n*rank+n)*nWords)
#
# #init respective parameters with prior values
# W, WO, Wcat, Wv, Wo = unroll_theta(theta, params)
# Wo[:n,:] = np.ones((n,Wo.shape[1])) #init word matrices with Identity matrices + epsilon
#load pre-trained weights here
mats = sio.loadmat(pre_trained_weights)
Wv = mats.get('Wv'); W = mats.get('W'); WO = mats.get('WO')
Wo = np.ndarray(shape=(2*params.wordSize*params.rankWo + params.wordSize)*params.nWords, dtype='float64')
sentencesIdx = np.arange(nExamples)
[allSNum_batch, allSNN_batch, Wv_batch, Wo_batch, allWordInds] = getRelevantWords(rnnData, sentencesIdx, Wv,Wo,params)
print
def initMVRNN(self):
print "Node: ",self.index," Loading training and dev sets.."
self.rnnData_train = RNNDataCorpus()
self.rnnData_train.load_data_srl(config.train_data_srl, nExamples=self.nuse)
self.rnnData_dev = RNNDataCorpus()
self.rnnData_dev.load_data_srl(config.dev_data_srl, nExamples=self.nuse)
modelfilename = config.saved_params_file+'SGD_SRLiter305'
print "Node: ", self.index," Loading model: ", modelfilename
# mats = sio.loadmat(config.saved_params_file+'iter120.mat')
# Wv = mats.get('Wv') #L, as in paper
# W = mats.get('W') #W, as in paper
# WO = mats.get('WO') #Wm, as in paper
# Wo = mats.get('Wo')
# Wcat = mats.get('Wcat')
# n = Wv.shape[0]
# r = (Wo.shape[0] - n)/(2*n)
with open(modelfilename, 'r') as loadfile:
self.rnn = cPickle.load(loadfile)#MVRNN(W, WO, Wcat, Wv, Wo)
n = self.rnn.Wv.shape[0]
r = (self.rnn.Wo.shape[0] - n)/(2*n)
print "Node: ",self.index, "initializing params.."
self.params = Params(data=self.rnnData_train, wordSize=n, rankWo=r)
# #to be removed
# Wcat = 0.005*np.random.randn(self.params.categories, self.params.fanIn)
# self.rnn.Wcat = Wcat
if(self.index == 0):
print "Master## Total trees in training set: ", self.rnnData_train.ndoc()
print "Master## nFetch: ", self.nFetch
if(self.index!=0):
self.rnnData_train = self.get_subset(self.rnnData_train, self.index)
self.rnnData_dev = None # workers don't need test set and trainTest, so to free memory release them
[_, _, self.all_train_idx] = getRelevantWords(self.rnnData_train, self.rnn.Wv,self.rnn.Wo,self.params) #sets nWords_reduced, returns new arrays
def train():
np.random.seed(131742)
#get sentences, trees and labels
nExamples = -1
print "loading data.."
rnnData = RNNDataCorpus()
rnnData.load_data(load_file=config.train_data, nExamples=nExamples)
#initialize params
print "initializing params"
params = Params(data=rnnData, wordSize=50, rankWo=2)
#define theta
#one vector for all the parameters of mvrnn model: W, Wm, Wlabel, L, Lm
n = params.wordSize
fanIn = params.fanIn
nWords = params.nWords
nLabels = params.categories
rank = params.rankWo
Wo = 0.01 * np.random.randn(n + 2 * n * rank, nWords) #Lm, as in paper
Wo[:n, :] = np.ones((n, Wo.shape[1])) #Lm, as in paper
Wcat = 0.005 * np.random.randn(nLabels, fanIn) #Wlabel, as in paper
# Wv = 0.01*np.random.randn(n, nWords)
# WO = 0.01*np.random.randn(n, 2*n)
# W = 0.01*np.random.randn(n, 2*n+1)
#load pre-trained weights here
mats = sio.loadmat(config.pre_trained_weights)
Wv = mats.get('Wv') #L, as in paper
W = mats.get('W') #W, as in paper
WO = mats.get('WO') #Wm, as in paper
sentencesIdx = np.arange(rnnData.ndoc())
np.random.shuffle(sentencesIdx)
nTrain = 4 * len(sentencesIdx) / 5
trainSentIdx = sentencesIdx[0:nTrain]
testSentIdx = sentencesIdx[nTrain:]
batchSize = 5
nBatches = len(trainSentIdx) / batchSize
evalFreq = 5 #evaluate after every 5 minibatches
nTestSentEval = 50 #number of test sentences to be evaluated
rnnData_train = RNNDataCorpus()
rnnData.copy_into_minibatch(rnnData_train, trainSentIdx)
rnnData_test = RNNDataCorpus()
if (len(testSentIdx) > nTestSentEval):
# np.random.shuffle(testSentIdx) #choose random test examples
thisTestSentIdx = testSentIdx[:nTestSentEval]
else:
thisTestSentIdx = testSentIdx
rnnData.copy_into_minibatch(rnnData_test, thisTestSentIdx)
# [Wv_test, Wo_test, _] = getRelevantWords(rnnData_test, Wv,Wo,params)
[Wv_trainTest, Wo_trainTest, all_train_idx
] = getRelevantWords(rnnData, Wv, Wo,
params) #sets nWords_reduced, returns new arrays
theta = np.concatenate((W.flatten(), WO.flatten(), Wcat.flatten(),
Wv_trainTest.flatten(), Wo_trainTest.flatten()))
#optimize
print "starting training..."
nIter = 100
rnnData_minibatch = RNNDataCorpus()
for i in range(nIter):
#train in minibatches
# ftrain = np.zeros(nBatches)
# for ibatch in range(nBatches):
# set_minibatch(rnnData, rnnData_minibatch, ibatch, nBatches, trainSentIdx)
# print 'Iteration: ', i, ' minibatch: ', ibatch
tunedTheta, fbatch_train, _ = lbfgsb.fmin_l_bfgs_b(
func=costFn,
x0=theta,
fprime=None,
args=(rnnData_train, params),
approx_grad=0,
bounds=None,
m=5,
factr=1000000000000000.0,
pgtol=1.0000000000000001e-5,
epsilon=1e-08,
iprint=3,
maxfun=1,
disp=0)
#map parameters back
W[:, :], WO[:, :], Wcat[:, :], Wv_trainTest, Wo_trainTest = unroll_theta(
tunedTheta, params)
Wv[:, all_train_idx] = Wv_trainTest
Wo[:, all_train_idx] = Wo_trainTest
# ftrain[ibatch] = fbatch_train
theta = tunedTheta #for next iteration
print "========================================"
print "XXXXXXIteration ", i,
print "Average cost: ", np.average(fbatch_train)
evaluate(Wv, Wo, W, WO, Wcat, params, rnnData_test)
print "========================================"
#save weights
save_dict = {'Wv': Wv, 'Wo': Wo, 'Wcat': Wcat, 'W': W, 'WO': WO}
sio.savemat(config.saved_params_file + '_lbfgs_iter' + str(i),
mdict=save_dict)
print "saved tuned theta. "
def train():
SEED = 13742
load_model = False
custom_load = False
np.random.seed(SEED)
#get sentences, trees and labels
nExamples = 5
print "loading data.."
rnnData_train = RNNDataCorpus()
rnnData_train.load_data_srl(load_file=config.train_data_srl,
nExamples=nExamples)
rnnData_dev = RNNDataCorpus()
rnnData_dev.load_data_srl(load_file=config.dev_data_srl,
nExamples=nExamples)
print "Number of sentences loaded in training data: ", rnnData_train.ndoc()
#initialize params
print "initializing params"
params = Params(data=rnnData_train, wordSize=52, rankWo=2)
n = params.wordSize
fanIn = params.fanIn
nWords = params.nWords
nLabels = params.categories
rank = params.rankWo
if (load_model):
modelfile = config.saved_params_file + 'SGD_SLL300'
rnn = MVRNNSLL.load(modelfile)
print 'loaded model : ', modelfile
elif (custom_load):
modelfile = config.saved_params_file + 'SGD_SLL300'
print "loading customized model..", modelfile
# d = 2#extra features for wordvectors
# Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
# Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
# Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
# Wv = 0.01*np.random.randn(n, nWords)
# WO = 0.01*np.random.randn(n, 2*n)
# W = 0.01*np.random.randn(n, 2*n+1)
#load pre-trained weights here
oldrnn = MVRNNSLL.load(modelfile)
# Wv[:-d,:] = oldrnn.Wv
categories = [x.strip() for x in rnnData_train.categories]
Tran = init_transitions(dict(zip(categories, range(len(categories)))),
'iob')
rnn = MVRNNSLL(oldrnn.W, oldrnn.WO, oldrnn.Wcat, oldrnn.Wv, oldrnn.Wo,
Tran)
else:
#define theta
#one vector for all the parameters of mvrnn model: W, Wm, Wlabel, L, Lm
# n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
# Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
# Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
# Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
# #load pre-trained weights here
## mats = sio.loadmat(config.saved_params_file)
# oldrnn = MVRNNSLL.load(modelfile)
# Wv = oldrnn.Wv #L, as in paper
# W = oldrnn..get('W') #W, as in paper
# WO = mats.get('WO') #Wm, as in paper
Wo = 0.01 * np.random.randn(n + 2 * n * rank, nWords) #Lm, as in paper
Wo[:n, :] = np.ones((n, Wo.shape[1])) #Lm, as in paper
Wcat = 0.005 * np.random.randn(nLabels, fanIn) #Wlabel, as in paper
Wv = 0.01 * np.random.randn(n, nWords)
WO = 0.01 * np.random.randn(n, 2 * n)
W = 0.01 * np.random.randn(n, 2 * n + 1)
categories = [x.strip() for x in rnnData_train.categories]
Tran = init_transitions(dict(zip(categories, range(len(categories)))),
'iob')
rnn = MVRNNSLL(W, WO, Wcat, Wv, Wo, Tran)
# rnn = MVRNNSLL(W, WO, Wcat, Wv, Wo, Tran)
[_, _, all_train_idx
] = getRelevantWords(rnnData_train, rnn.Wv, rnn.Wo,
params) #sets nWords_reduced, returns new arrays
params.setNumReducedWords(len(all_train_idx))
theta = rnn.getTheta(params, all_train_idx)
#optimize
print "starting training using SGD..."
nIter = 500
optimizer = StochasticGradientDescent(niter=nIter,
learning_rate=0.01,
learningrateFactor=1.0,
printAt10Iter='.',
printAt100Iter='\n+')
optimizer.minimizeBatches(rnn=rnn,
rnnData_train=rnnData_train,
allTrainSentIdx=all_train_idx,
params=params,
x0=theta,
func=costFn,
fprime=None,
rnnData_test=rnnData_dev,
initialSetSize=1,
niter=nIter,
seed=SEED,
modelFileName=config.saved_params_file +
'SGD_SLL',
printStatistics=True,
modelSaveIter=100,
nIterInPart=1,
nFetch=-1,
rnd=None,
nodeid=-1)
def train():
SEED = 131742
load_model = False
custom_load = True #loads model from previously saved model except Wcat
np.random.seed(SEED)
#get sentences, trees and labels
nExamples = 5
print "loading data.."
rnnData_train = RNNDataCorpus()
rnnData_train.load_data_srl(load_file=config.train_data_srl,
nExamples=nExamples)
rnnData_dev = RNNDataCorpus()
rnnData_dev.load_data_srl(load_file=config.dev_data_srl,
nExamples=nExamples)
print "Number of sentences loaded in training data: ", rnnData_train.ndoc()
#initialize params
print "initializing params"
params = Params(data=rnnData_train, wordSize=52, rankWo=2)
n = params.wordSize
fanIn = params.fanIn
nWords = params.nWords
nLabels = params.categories
rank = params.rankWo
if (load_model):
with open(config.saved_params_file + "_45", 'r') as loadfile:
rnn = cPickle.load(loadfile)
elif (custom_load):
d = 2 #extra features for wordvectors
Wo = 0.01 * np.random.randn(n + 2 * n * rank, nWords) #Lm, as in paper
Wo[:n, :] = np.ones((n, Wo.shape[1])) #Lm, as in paper
Wcat = 0.005 * np.random.randn(nLabels, fanIn) #Wlabel, as in paper
Wv = 0.01 * np.random.randn(n, nWords)
WO = 0.01 * np.random.randn(n, 2 * n)
W = 0.01 * np.random.randn(n, 2 * n + 1)
#load pre-trained weights here
with open(config.saved_params_file + '_65', 'r') as loadfile:
oldrnn = cPickle.load(loadfile)
Wv[:-d, :] = oldrnn.Wv
# WO[:-d,:] = oldrnn.WO
rnn = MVRNN(W, WO, Wcat, Wv, Wo)
else:
Wo = 0.01 * np.random.randn(n + 2 * n * rank, nWords) #Lm, as in paper
Wo[:n, :] = np.ones((n, Wo.shape[1])) #Lm, as in paper
Wcat = 0.005 * np.random.randn(nLabels, fanIn) #Wlabel, as in paper
Wv = 0.01 * np.random.randn(n, nWords)
WO = 0.01 * np.random.randn(n, 2 * n)
W = 0.01 * np.random.randn(n, 2 * n + 1)
rnn = MVRNN(W, WO, Wcat, Wv, Wo)
[_, _, all_train_idx
] = getRelevantWords(rnnData_train, rnn.Wv, rnn.Wo,
params) #sets nWords_reduced, returns new arrays
params.setNumReducedWords(len(all_train_idx))
theta = rnn.getTheta(params, all_train_idx)
#optimize
print "starting training using SGD..."
nIter = 500
optimizer = StochasticGradientDescent(niter=nIter,
learning_rate=0.01,
learningrateFactor=1.0,
printAt10Iter='.',
printAt100Iter='\n+')
optimizer.minimizeBatches(rnn=rnn,
rnnData_train=rnnData_train,
allTrainSentIdx=all_train_idx,
params=params,
x0=theta,
func=costFn,
fprime=None,
rnnData_test=rnnData_dev,
initialSetSize=1,
niter=nIter,
seed=17,
modelFileName=config.saved_params_file +
'SGD_SRL',
printStatistics=True,
modelSaveIter=1,
nIterInPart=1,
nFetch=-1,
rnd=None,
nodeid=-1)
print "Finished training! "
def train():
np.random.seed(131742)
#get sentences, trees and labels
nExamples = -1
print "loading data.."
rnnData = RNNDataCorpus()
rnnData.load_data(load_file=config.train_data, nExamples=nExamples)
#initialize params
print "initializing params"
params = Params(data=rnnData, wordSize=50, rankWo=2)
#define theta
#one vector for all the parameters of mvrnn model: W, Wm, Wlabel, L, Lm
n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
# Wv = 0.01*np.random.randn(n, nWords)
# WO = 0.01*np.random.randn(n, 2*n)
# W = 0.01*np.random.randn(n, 2*n+1)
#load pre-trained weights here
mats = sio.loadmat(config.pre_trained_weights)
Wv = mats.get('Wv') #L, as in paper
W = mats.get('W') #W, as in paper
WO = mats.get('WO') #Wm, as in paper
sentencesIdx = np.arange(rnnData.ndoc())
np.random.shuffle(sentencesIdx)
nTrain = 4*len(sentencesIdx)/5
trainSentIdx = sentencesIdx[0:nTrain]
testSentIdx = sentencesIdx[nTrain:]
batchSize = 5
nBatches = len(trainSentIdx)/batchSize
evalFreq = 5 #evaluate after every 5 minibatches
nTestSentEval = 50 #number of test sentences to be evaluated
rnnData_train = RNNDataCorpus()
rnnData.copy_into_minibatch(rnnData_train, trainSentIdx)
rnnData_test = RNNDataCorpus()
if(len(testSentIdx) > nTestSentEval):
# np.random.shuffle(testSentIdx) #choose random test examples
thisTestSentIdx = testSentIdx[:nTestSentEval]
else:
thisTestSentIdx = testSentIdx
rnnData.copy_into_minibatch(rnnData_test, thisTestSentIdx)
# [Wv_test, Wo_test, _] = getRelevantWords(rnnData_test, Wv,Wo,params)
[Wv_trainTest, Wo_trainTest, all_train_idx] = getRelevantWords(rnnData, Wv,Wo,params) #sets nWords_reduced, returns new arrays
theta = np.concatenate((W.flatten(), WO.flatten(), Wcat.flatten(), Wv_trainTest.flatten(), Wo_trainTest.flatten()))
#optimize
print "starting training..."
nIter = 100
rnnData_minibatch = RNNDataCorpus()
for i in range(nIter):
#train in minibatches
# ftrain = np.zeros(nBatches)
# for ibatch in range(nBatches):
# set_minibatch(rnnData, rnnData_minibatch, ibatch, nBatches, trainSentIdx)
# print 'Iteration: ', i, ' minibatch: ', ibatch
tunedTheta, fbatch_train, _ = lbfgsb.fmin_l_bfgs_b(func=costFn, x0=theta, fprime=None, args=(rnnData_train, params), approx_grad=0, bounds=None, m=5,
factr=1000000000000000.0, pgtol=1.0000000000000001e-5, epsilon=1e-08,
iprint=3, maxfun=1, disp=0)
#map parameters back
W[:,:], WO[:,:], Wcat[:,:], Wv_trainTest, Wo_trainTest = unroll_theta(tunedTheta, params)
Wv[:,all_train_idx] = Wv_trainTest
Wo[:,all_train_idx] = Wo_trainTest
# ftrain[ibatch] = fbatch_train
theta = tunedTheta #for next iteration
print "========================================"
print "XXXXXXIteration ", i,
print "Average cost: ", np.average(fbatch_train)
evaluate(Wv,Wo,W,WO,Wcat,params, rnnData_test)
print "========================================"
#save weights
save_dict = {'Wv':Wv, 'Wo':Wo, 'Wcat':Wcat, 'W':W, 'WO':WO}
sio.savemat(config.saved_params_file+'_lbfgs_iter'+str(i), mdict=save_dict)
print "saved tuned theta. "
def train():
SEED = 13742
load_model = False
custom_load = False
np.random.seed(SEED)
#get sentences, trees and labels
nExamples = 5
print "loading data.."
rnnData_train = RNNDataCorpus()
rnnData_train.load_data_srl(load_file=config.train_data_srl, nExamples=nExamples)
rnnData_dev = RNNDataCorpus()
rnnData_dev.load_data_srl(load_file=config.dev_data_srl, nExamples=nExamples)
print "Number of sentences loaded in training data: ", rnnData_train.ndoc()
#initialize params
print "initializing params"
params = Params(data=rnnData_train, wordSize=52, rankWo=2)
n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
if(load_model):
modelfile = config.saved_params_file+'SGD_SLL300'
rnn = MVRNNSLL.load(modelfile)
print 'loaded model : ', modelfile
elif(custom_load):
modelfile = config.saved_params_file+'SGD_SLL300'
print "loading customized model..", modelfile
# d = 2#extra features for wordvectors
# Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
# Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
# Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
# Wv = 0.01*np.random.randn(n, nWords)
# WO = 0.01*np.random.randn(n, 2*n)
# W = 0.01*np.random.randn(n, 2*n+1)
#load pre-trained weights here
oldrnn = MVRNNSLL.load(modelfile)
# Wv[:-d,:] = oldrnn.Wv
categories = [x.strip() for x in rnnData_train.categories]
Tran = init_transitions(dict(zip(categories, range(len(categories)))), 'iob')
rnn = MVRNNSLL(oldrnn.W, oldrnn.WO, oldrnn.Wcat, oldrnn.Wv, oldrnn.Wo, Tran)
else:
#define theta
#one vector for all the parameters of mvrnn model: W, Wm, Wlabel, L, Lm
# n = params.wordSize; fanIn = params.fanIn; nWords = params.nWords; nLabels = params.categories; rank=params.rankWo
# Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
# Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
# Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
# #load pre-trained weights here
## mats = sio.loadmat(config.saved_params_file)
# oldrnn = MVRNNSLL.load(modelfile)
# Wv = oldrnn.Wv #L, as in paper
# W = oldrnn..get('W') #W, as in paper
# WO = mats.get('WO') #Wm, as in paper
Wo = 0.01*np.random.randn(n + 2*n*rank, nWords) #Lm, as in paper
Wo[:n,:] = np.ones((n,Wo.shape[1])) #Lm, as in paper
Wcat = 0.005*np.random.randn(nLabels, fanIn) #Wlabel, as in paper
Wv = 0.01*np.random.randn(n, nWords)
WO = 0.01*np.random.randn(n, 2*n)
W = 0.01*np.random.randn(n, 2*n+1)
categories = [x.strip() for x in rnnData_train.categories]
Tran = init_transitions(dict(zip(categories, range(len(categories)))), 'iob')
rnn = MVRNNSLL(W, WO, Wcat, Wv, Wo, Tran)
# rnn = MVRNNSLL(W, WO, Wcat, Wv, Wo, Tran)
[_, _, all_train_idx] = getRelevantWords(rnnData_train, rnn.Wv, rnn.Wo, params) #sets nWords_reduced, returns new arrays
params.setNumReducedWords(len(all_train_idx))
theta = rnn.getTheta(params, all_train_idx)
#optimize
print "starting training using SGD..."
nIter = 500
optimizer = StochasticGradientDescent(niter=nIter , learning_rate=0.01, learningrateFactor=1.0, printAt10Iter='.', printAt100Iter='\n+')
optimizer.minimizeBatches(rnn=rnn, rnnData_train=rnnData_train, allTrainSentIdx=all_train_idx, params=params, x0=theta, func=costFn, fprime=None,
rnnData_test=rnnData_dev, initialSetSize=1, niter=nIter, seed=SEED,
modelFileName=config.saved_params_file+'SGD_SLL', printStatistics=True, modelSaveIter=100, nIterInPart=1,
nFetch=-1, rnd=None, nodeid=-1)