def train_mlp(L1_reg = 0.0, L2_reg = 0.0000, num_batches_per_bunch = 512, batch_size = 1, num_bunches_queue = 5, offset = 0, path_name = '/afs/inf.ed.ac.uk/user/s12/s1264845/scratch/s1264845/data/'):
voc_list = Vocabulary(path_name + 'train')
voc_list.vocab_create()
vocab = voc_list.vocab
vocab_size = voc_list.vocab_size
voc_list_valid = Vocabulary(path_name + 'valid')
voc_list_valid.vocab_create()
valid_words_count = voc_list_valid.count
#print valid_words_count
valid_lines_count = voc_list_valid.line_count
#print valid_lines_count
voc_list_test = Vocabulary(path_name + 'test')
voc_list_test.vocab_create()
test_words_count = voc_list_test.count
#print test_words_count
test_lines_count = voc_list_test.line_count
#print test_lines_count
dataprovider_train = DataProvider(path_name + 'train', vocab, vocab_size )
dataprovider_valid = DataProvider(path_name + 'valid', vocab, vocab_size )
dataprovider_test = DataProvider(path_name + 'test', vocab, vocab_size )
#exp_name = 'fine_tuning.hdf5'
print '..building the model'
#symbolic variables for input, target vector and batch index
index = T.lscalar('index')
x = T.fvector('x')
y = T.ivector('y')
learning_rate = T.fscalar('learning_rate')
#theano shared variables for train, valid and test
train_set_x = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
train_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
valid_set_x = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
valid_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
test_set_x = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
test_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
rng = numpy.random.RandomState()
classifier = MLP(rng = rng, input = x, n_in = vocab_size, fea_dim = 30, context_size = 2, n_hidden = 60 , n_out = vocab_size)
cost = classifier.negative_log_likelihood(y) + L1_reg * classifier.L1 + L2_reg * classifier.L2_sqr
#constructor for learning rate class
learnrate_schedular = LearningRateNewBob(start_rate=0.005, scale_by=.5, max_epochs=9999,\
min_derror_ramp_start=.01, min_derror_stop=.01, init_error=100.)
#learnrate_schedular = LearningRateList(learn_list)
frame_error = classifier.errors(y)
likelihood = classifier.sum(y)
#test_model
test_model = theano.function(inputs = [], outputs = likelihood, \
givens = {x: test_set_x,
y: test_set_y})
#validation_model
validate_model = theano.function(inputs = [], outputs = [frame_error, likelihood], \
givens = {x: valid_set_x,
y: valid_set_y})
gradient_param = []
#calculates the gradient of cost with respect to parameters
for param in classifier.params:
gradient_param.append(T.cast(T.grad(cost, param), 'float32'))
updates = []
#updates the parameters
for param, gradient in zip(classifier.params, gradient_param):
updates.append((param, param - learning_rate * gradient))
#training_model
train_model = theano.function(inputs = [theano.Param(learning_rate, default = 0.01)], outputs = cost, updates = updates, \
givens = {x: train_set_x,
y: train_set_y})
training(dataprovider_train, dataprovider_valid, learnrate_schedular, classifier, train_model, validate_model, train_set_x, train_set_y, valid_set_x, valid_set_y, batch_size, num_batches_per_bunch, valid_words_count, valid_lines_count)
testing(dataprovider_test, classifier, test_model, test_set_x, test_set_y, test_words_count, test_lines_count)
def train_mlp(feature_dimension, context, hidden_size, weight_path, file_name1, file_name2, file_name3, L1_reg = 0.0, L2_reg = 0.0000, path_name = '/exports/work/inf_hcrc_cstr_udialogue/siva/data/'):
#voc_list = Vocabulary(path_name + 'train_modified1')
#voc_list.vocab_create()
#vocab = voc_list.vocab
#vocab_size = voc_list.vocab_size
#short_list = voc_list.short_list
#short_list_size = voc_list.short_list_size
#path = '/exports/work/inf_hcrc_cstr_udialogue/siva/data_normalization/vocab/wlist5c.nvp'
voc_list = Vocabularyhash('/exports/work/inf_hcrc_cstr_udialogue/siva/data_normalization/vocab/wlist5c.nvp')
voc_list.hash_create()
vocab = voc_list.voc_hash
vocab_size = voc_list.vocab_size
#dataprovider_train = DataProvider(path_name + 'train', vocab, vocab_size, short_list )
#dataprovider_valid = DataProvider(path_name + 'valid', vocab, vocab_size, short_list )
#dataprovider_test = DataProvider(path_name + 'test', vocab, vocab_size , short_list)
dataprovider_train = DataProvider(path_name + 'train_modified1_20m', vocab, vocab_size)
dataprovider_valid = DataProvider(path_name + 'valid_modified1', vocab, vocab_size)
dataprovider_test = DataProvider(path_name + 'test_modified1', vocab, vocab_size)
print '..building the model'
#symbolic variables for input, target vector and batch index
index = T.lscalar('index')
x1 = T.fvector('x1')
x2 = T.fvector('x2')
y = T.ivector('y')
learning_rate = T.fscalar('learning_rate')
#theano shared variables for train, valid and test
train_set_x1 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
train_set_x2 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
train_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
valid_set_x1 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
valid_set_x2 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
valid_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
test_set_x1 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
test_set_x2 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
test_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
rng = numpy.random.RandomState()
classifier = MLP(rng = rng, input1 = x1, input2 = x2, n_in = vocab_size, fea_dim = int(feature_dimension), context_size = int(context), n_hidden =int(hidden_size), n_out = vocab_size)
cost = classifier.negative_log_likelihood(y) + L1_reg * classifier.L1 + L2_reg * classifier.L2_sqr
#constructor for learning rate class
learnrate_schedular = LearningRateNewBob(start_rate=0.005, scale_by=.5, max_epochs=9999,\
min_derror_ramp_start=.01, min_derror_stop=.01, init_error=100.)
frame_error = classifier.errors(y)
log_likelihood = classifier.sum(y)
likelihood = classifier.likelihood(y)
#test_model
test_model = theano.function(inputs = [], outputs = [log_likelihood, likelihood], \
givens = {x1: test_set_x1,
x2: test_set_x2,
y: test_set_y})
#validation_model
validate_model = theano.function(inputs = [], outputs = [frame_error, log_likelihood], \
givens = {x1: valid_set_x1,
x2: valid_set_x2,
y: valid_set_y})
gradient_param = []
#calculates the gradient of cost with respect to parameters
for param in classifier.params:
gradient_param.append(T.cast(T.grad(cost, param), 'float32'))
updates = []
#updates the parameters
for param, gradient in zip(classifier.params, gradient_param):
updates.append((param, param - learning_rate * gradient))
#training_model
train_model = theano.function(inputs = [learning_rate], outputs = [cost], updates = updates, \
givens = {x1: train_set_x1,
x2: train_set_x2,
y: train_set_y})
print '.....training'
best_valid_loss = numpy.inf
start_time = time.time()
while(learnrate_schedular.get_rate() != 0):
print 'learning_rate:', learnrate_schedular.get_rate()
print 'epoch_number:', learnrate_schedular.epoch
frames_showed, progress = 0, 0
start_epoch_time = time.time()
dataprovider_train.reset()
for feats_lab_tuple in dataprovider_train:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
train_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
train_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
train_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = train_model(numpy.array(learnrate_schedular.get_rate(), dtype = 'float32'))
progress += 1
if progress%10000==0:
end_time_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, frames_showed,(end_time_progress-start_epoch_time))
train_set_x1.set_value(numpy.empty((1), dtype = 'float32'))
train_set_x2.set_value(numpy.empty((1), dtype = 'float32'))
train_set_y.set_value(numpy.empty((1), dtype = 'int32'))
end_time_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, frames_showed,(end_time_progress-start_epoch_time))
classifier_name = 'MLP' + str(learnrate_schedular.epoch)
save_mlp(classifier, weight_path+file_name1 , classifier_name)
save_learningrate(learnrate_schedular.get_rate(), weight_path+file_name3, classifier_name)
print 'Validating...'
valid_losses = []
log_likelihood = []
valid_frames_showed, progress = 0, 0
start_valid_time = time.time() # it is also stop of training time
dataprovider_valid.reset()
for feats_lab_tuple in dataprovider_valid:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
valid_frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
valid_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
valid_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
valid_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = validate_model()
error_rate = out[0]
likelihoods = out[1]
valid_losses.append(error_rate)
log_likelihood.append(likelihoods)
valid_set_x1.set_value(numpy.empty((1), 'float32'))
valid_set_x2.set_value(numpy.empty((1), 'float32'))
valid_set_y.set_value(numpy.empty((1), 'int32'))
progress += 1
if progress%1000==0:
end_time_valid_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, valid_frames_showed, end_time_valid_progress - start_valid_time)
end_time_valid_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, valid_frames_showed, end_time_valid_progress - start_valid_time)
this_validation_loss = numpy.mean(valid_losses)
entropy = (-numpy.sum(log_likelihood)/valid_frames_showed)
print this_validation_loss, entropy, numpy.sum(log_likelihood)
if entropy < best_valid_loss:
learning_rate = learnrate_schedular.get_next_rate(entropy)
best_valid_loss = entropy
else:
learnrate_schedular.rate = 0.0
end_time = time.time()
print 'The fine tuning ran for %.2fm' %((end_time-start_time)/60.)
print 'Testing...'
log_likelihood = []
likelihoods = []
test_frames_showed, progress = 0, 0
start_test_time = time.time() # it is also stop of training time
dataprovider_test.reset()
for feats_lab_tuple in dataprovider_test:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
test_frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
test_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
test_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
test_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = test_model()
log_likelihood.append(out[0])
likelihoods.append(out[1])
progress += 1
if progress%1000==0:
end_time_test_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, test_frames_showed, end_time_test_progress - start_test_time)
end_time_test_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, test_frames_showed, end_time_test_progress - start_test_time)
save_posteriors(log_likelihood, likelihoods, weight_path+file_name2)
print numpy.sum(log_likelihood)
likelihood_sum = (-numpy.sum(log_likelihood)/test_frames_showed)
print 'entropy:', likelihood_sum
def testing_tunedweights(path, feature_dimension, context, hidden_size, weight_path, file_name1, model_number):
x1 = T.fvector('x1')
x2 = T.fvector('x2')
y = T.ivector('y')
#voc_list = Vocabulary(path + 'train_modified1')
#voc_list.vocab_create()
#vocab = voc_list.vocab
#vocab_size = voc_list.vocab_size
#short_list = voc_list.short_list
#short_list_size = voc_list.short_list_size
voc_list = Vocabularyhash('/exports/work/inf_hcrc_cstr_udialogue/siva/data_normalization/vocab/wlist5c.nvp')
voc_list.hash_create()
vocab = voc_list.voc_hash
vocab_size = voc_list.vocab_size
dataprovider_test = DataProvider(path + 'test_modified1_1m', vocab, vocab_size)
#dataprovider_test = DataProvider(path + 'test', vocab, vocab_size , short_list)
test_set_x1 = theano.shared(numpy.empty((1), dtype='float32'))
test_set_x2 = theano.shared(numpy.empty((1), dtype='float32'))
test_set_y = theano.shared(numpy.empty((1), dtype = 'int32'))
rng = numpy.random.RandomState()
classifier = MLP(rng = rng, input1 = x1, input2 = x2, n_in = vocab_size, fea_dim = int(feature_dimension), context_size = int(context), n_hidden = int(hidden_size) , n_out = vocab_size)
log_likelihood = classifier.sum(y)
likelihood = classifier.likelihood(y)
#test_model
test_model = theano.function(inputs = [], outputs = [log_likelihood, likelihood], \
givens = {x1: test_set_x1,
x2: test_set_x2,
y: test_set_y})
classifier_name = 'MLP' + str(model_number)
f = h5py.File(weight_path+file_name1, "r")
for i in xrange(0, classifier.no_of_layers, 2):
path_modified = '/' + classifier_name + '/layer' + str(i/2)
if i == 4:
classifier.params[i].set_value(numpy.asarray(f[path_modified + "/W"].value, dtype = 'float32'), borrow = True)
else:
classifier.params[i].set_value(numpy.asarray(f[path_modified + "/W"].value, dtype = 'float32'), borrow = True)
classifier.params[i + 1].set_value(numpy.asarray(f[path_modified + "/b"].value, dtype = 'float32'), borrow = True)
f.close()
print 'Testing...'
log_likelihood = []
likelihoods = []
test_frames_showed, progress = 0, 0
start_test_time = time.time() # it is also stop of training time
dataprovider_test.reset()
for feats_lab_tuple in dataprovider_test:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
test_frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
test_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
test_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
test_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = test_model()
log_likelihood.append(out[0])
likelihoods.append(out[1])
progress += 1
if progress%1000==0:
end_time_test_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, test_frames_showed, end_time_test_progress - start_test_time)
end_time_test_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, test_frames_showed, end_time_test_progress - start_test_time)
#save_posteriors(log_likelihood, likelihoods, path_name+exp_name2)
print numpy.sum(log_likelihood)
entropy = (-numpy.sum(log_likelihood)/test_frames_showed)
print 'entropy', entropy
def train_mlp(feature_dimension, context, hidden_size, weight_path, file_name1, file_name3, learn_rate, epoch, valid_loss, L1_reg = 0.0, L2_reg = 0.0000, path_name = '/exports/work/inf_hcrc_cstr_udialogue/siva/data/'):
#voc_list = Vocabulary(path_name + 'train')
#voc_list.vocab_create()
#vocab = voc_list.vocab
#vocab_size = voc_list.vocab_size
#short_list = voc_list.short_list
#short_list_size = voc_list.short_list_size
voc_list = Vocabularyhash('/exports/work/inf_hcrc_cstr_udialogue/siva/data_normalization/vocab/wlist5c.nvp')
voc_list.hash_create()
vocab = voc_list.voc_hash
vocab_size = voc_list.vocab_size
#dataprovider_train = DataProvider(path_name + 'train', vocab, vocab_size, short_list )
#dataprovider_valid = DataProvider(path_name + 'valid', vocab, vocab_size, short_list )
#dataprovider_test = DataProvider(path_name + 'test', vocab, vocab_size , short_list)
#dataprovider_train = DataProvider(path_name + 'train', vocab, vocab_size)
#dataprovider_valid = DataProvider(path_name + 'valid', vocab, vocab_size)
#dataprovider_test = DataProvider(path_name + 'test', vocab, vocab_size)
dataprovider_train = DataProvider(path_name + 'train_modified1_20m', vocab, vocab_size)
dataprovider_valid = DataProvider(path_name + 'valid_modified1', vocab, vocab_size)
dataprovider_test = DataProvider(path_name + 'test_modified1', vocab, vocab_size)
#exp_name1 = 'fine_tuning.h5'
#exp_name2 = 'posteriors.h5'
#path = weight_path
print '..building the model'
#symbolic variables for input, target vector and batch index
index = T.lscalar('index')
x1 = T.fvector('x1')
x2 = T.fvector('x2')
y = T.ivector('y')
learning_rate = T.fscalar('learning_rate')
#theano shared variables for train, valid and test
train_set_x1 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
train_set_x2 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
train_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
valid_set_x1 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
valid_set_x2 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
valid_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
test_set_x1 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
test_set_x2 = theano.shared(numpy.empty((1), dtype='float32'), allow_downcast = True)
test_set_y = theano.shared(numpy.empty((1), dtype = 'int32'), allow_downcast = True)
rng = numpy.random.RandomState()
classifier = MLP(rng = rng, input1 = x1, input2 = x2, n_in = vocab_size, fea_dim = int(feature_dimension), context_size = int(context), n_hidden =int(hidden_size) , n_out = vocab_size)
cost = classifier.negative_log_likelihood(y) + L1_reg * classifier.L1 + L2_reg * classifier.L2_sqr
#constructor for learning rate class
learnrate_schedular = LearningRateNewBob(start_rate = float(learn_rate), scale_by=.5, max_epochs=9999,\
min_derror_ramp_start=.01, min_derror_stop=.01, init_error = float(valid_loss), epoch_number = int(epoch))
frame_error = classifier.errors(y)
log_likelihood = classifier.sum(y)
likelihood = classifier.likelihood(y)
#test_model
test_model = theano.function(inputs = [], outputs = [log_likelihood, likelihood], \
givens = {x1: test_set_x1,
x2: test_set_x2,
y: test_set_y})
#validation_model
validate_model = theano.function(inputs = [], outputs = [frame_error, log_likelihood], \
givens = {x1: valid_set_x1,
x2: valid_set_x2,
y: valid_set_y})
gradient_param = []
#calculates the gradient of cost with respect to parameters
for param in classifier.params:
gradient_param.append(T.cast(T.grad(cost, param), 'float32'))
updates = []
#updates the parameters
for param, gradient in zip(classifier.params, gradient_param):
updates.append((param, param - learning_rate * gradient))
#training_model
train_model = theano.function(inputs = [learning_rate], outputs = [cost], updates = updates, \
givens = {x1: train_set_x1,
x2: train_set_x2,
y: train_set_y})
f = h5py.File(weight_path+file_name1, "r")
for i in xrange(0, classifier.no_of_layers, 2):
path_modified = '/' + 'MLP'+ str(10) + '/layer' + str(i/2)
if i == 4:
classifier.params[i].set_value(numpy.asarray(f[path_modified + "/W"].value, dtype = 'float32'), borrow = True)
else:
classifier.params[i].set_value(numpy.asarray(f[path_modified + "/W"].value, dtype = 'float32'), borrow = True)
classifier.params[i + 1].set_value(numpy.asarray(f[path_modified + "/b"].value, dtype = 'float32'), borrow = True)
f.close()
print '.....training'
#best_valid_loss = numpy.inf
best_valid_loss = float(valid_loss)
start_time = time.time()
while(learnrate_schedular.get_rate() != 0):
print 'learning_rate:', learnrate_schedular.get_rate()
print 'epoch_number:', learnrate_schedular.epoch
frames_showed, progress = 0, 0
start_epoch_time = time.time()
dataprovider_train.reset()
for feats_lab_tuple in dataprovider_train:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
train_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
train_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
train_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = train_model(numpy.array(learnrate_schedular.get_rate(), dtype = 'float32'))
progress += 1
if progress%10000==0:
end_time_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, frames_showed,(end_time_progress-start_epoch_time))
train_set_x1.set_value(numpy.empty((1), dtype = 'float32'))
train_set_x2.set_value(numpy.empty((1), dtype = 'float32'))
train_set_y.set_value(numpy.empty((1), dtype = 'int32'))
end_time_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, frames_showed,(end_time_progress-start_epoch_time))
classifier_name = 'MLP' + str(learnrate_schedular.epoch)
save_mlp(classifier, weight_path+file_name1 , classifier_name)
save_learningrate(learnrate_schedular.get_rate(), weight_path+file_name3, classifier_name)
print 'Validating...'
valid_losses = []
log_likelihood = []
valid_frames_showed, progress = 0, 0
start_valid_time = time.time() # it is also stop of training time
dataprovider_valid.reset()
for feats_lab_tuple in dataprovider_valid:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
valid_frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
valid_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
valid_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
valid_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = validate_model()
error_rate = out[0]
likelihoods = out[1]
valid_losses.append(error_rate)
log_likelihood.append(likelihoods)
valid_set_x1.set_value(numpy.empty((1), 'float32'))
valid_set_x2.set_value(numpy.empty((1), 'float32'))
valid_set_y.set_value(numpy.empty((1), 'int32'))
progress += 1
if progress%1000==0:
end_time_valid_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, valid_frames_showed, end_time_valid_progress - start_valid_time)
end_time_valid_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, valid_frames_showed, end_time_valid_progress - start_valid_time)
this_validation_loss = numpy.mean(valid_losses)
entropy = (-numpy.sum(log_likelihood)/valid_frames_showed)
print this_validation_loss, entropy, numpy.sum(log_likelihood)
if entropy < best_valid_loss:
learning_rate = learnrate_schedular.get_next_rate(entropy)
best_valid_loss = entropy
else:
learnrate_schedular.rate = 0.0
end_time = time.time()
print 'The fine tuning ran for %.2fm' %((end_time-start_time)/60.)
print 'Testing...'
log_likelihood = []
likelihoods = []
test_frames_showed, progress = 0, 0
start_test_time = time.time() # it is also stop of training time
dataprovider_test.reset()
for feats_lab_tuple in dataprovider_test:
features, labels = feats_lab_tuple
if labels is None or features is None:
continue
test_frames_showed += features.shape[0]
for temp, i in zip(features, xrange(len(labels))):
temp_features1 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features2 = numpy.zeros(vocab_size, dtype = 'float32')
temp_features1[temp[0]] = 1
temp_features2[temp[1]] = 1
test_set_x1.set_value(numpy.asarray(temp_features1, dtype = 'float32'), borrow = True)
test_set_x2.set_value(numpy.asarray(temp_features2, dtype = 'float32'), borrow = True)
test_set_y.set_value(numpy.asarray([labels[i]], dtype = 'int32'), borrow = True)
out = test_model()
log_likelihood.append(out[0])
likelihoods.append(out[1])
progress += 1
if progress%1000==0:
end_time_test_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, test_frames_showed, end_time_test_progress - start_test_time)
end_time_test_progress = time.time()
print 'PROGRESS: Processed %i bunches (%i frames), TIME: %f in seconds'\
%(progress, test_frames_showed, end_time_test_progress - start_test_time)
#save_posteriors(log_likelihood, likelihoods, weight_path+file_name2)
print numpy.sum(log_likelihood)
likelihood_sum = (-numpy.sum(log_likelihood)/test_frames_showed)
print 'entropy:', likelihood_sum
def train_mlp(
L1_reg=0.0,
L2_reg=0.0000,
num_batches_per_bunch=512,
batch_size=1,
num_bunches_queue=5,
offset=0,
path_name='/afs/inf.ed.ac.uk/user/s12/s1264845/scratch/s1264845/data/'
):
voc_list = Vocabulary(path_name + 'train')
voc_list.vocab_create()
vocab = voc_list.vocab
vocab_size = voc_list.vocab_size
voc_list_valid = Vocabulary(path_name + 'valid')
voc_list_valid.vocab_create()
valid_words_count = voc_list_valid.count
#print valid_words_count
valid_lines_count = voc_list_valid.line_count
#print valid_lines_count
voc_list_test = Vocabulary(path_name + 'test')
voc_list_test.vocab_create()
test_words_count = voc_list_test.count
#print test_words_count
test_lines_count = voc_list_test.line_count
#print test_lines_count
dataprovider_train = DataProvider(path_name + 'train', vocab, vocab_size)
dataprovider_valid = DataProvider(path_name + 'valid', vocab, vocab_size)
dataprovider_test = DataProvider(path_name + 'test', vocab, vocab_size)
#exp_name = 'fine_tuning.hdf5'
print '..building the model'
#symbolic variables for input, target vector and batch index
index = T.lscalar('index')
x = T.fvector('x')
y = T.ivector('y')
learning_rate = T.fscalar('learning_rate')
#theano shared variables for train, valid and test
train_set_x = theano.shared(numpy.empty((1), dtype='float32'),
allow_downcast=True)
train_set_y = theano.shared(numpy.empty((1), dtype='int32'),
allow_downcast=True)
valid_set_x = theano.shared(numpy.empty((1), dtype='float32'),
allow_downcast=True)
valid_set_y = theano.shared(numpy.empty((1), dtype='int32'),
allow_downcast=True)
test_set_x = theano.shared(numpy.empty((1), dtype='float32'),
allow_downcast=True)
test_set_y = theano.shared(numpy.empty((1), dtype='int32'),
allow_downcast=True)
rng = numpy.random.RandomState()
classifier = MLP(rng=rng,
input=x,
n_in=vocab_size,
fea_dim=30,
context_size=2,
n_hidden=60,
n_out=vocab_size)
cost = classifier.negative_log_likelihood(
y) + L1_reg * classifier.L1 + L2_reg * classifier.L2_sqr
#constructor for learning rate class
learnrate_schedular = LearningRateNewBob(start_rate=0.005, scale_by=.5, max_epochs=9999,\
min_derror_ramp_start=.01, min_derror_stop=.01, init_error=100.)
#learnrate_schedular = LearningRateList(learn_list)
frame_error = classifier.errors(y)
likelihood = classifier.sum(y)
#test_model
test_model = theano.function(inputs = [], outputs = likelihood, \
givens = {x: test_set_x,
y: test_set_y})
#validation_model
validate_model = theano.function(inputs = [], outputs = [frame_error, likelihood], \
givens = {x: valid_set_x,
y: valid_set_y})
gradient_param = []
#calculates the gradient of cost with respect to parameters
for param in classifier.params:
gradient_param.append(T.cast(T.grad(cost, param), 'float32'))
updates = []
#updates the parameters
for param, gradient in zip(classifier.params, gradient_param):
updates.append((param, param - learning_rate * gradient))
#training_model
train_model = theano.function(inputs = [theano.Param(learning_rate, default = 0.01)], outputs = cost, updates = updates, \
givens = {x: train_set_x,
y: train_set_y})
training(dataprovider_train, dataprovider_valid, learnrate_schedular,
classifier, train_model, validate_model, train_set_x, train_set_y,
valid_set_x, valid_set_y, batch_size, num_batches_per_bunch,
valid_words_count, valid_lines_count)
testing(dataprovider_test, classifier, test_model, test_set_x, test_set_y,
test_words_count, test_lines_count)