def do_training(indices, training_blob, heldout_blob, weights, weights_out, debiasing_weights):
"""
Helper/wrapper function for parallel perceptron training.
Runs one epoch of perceptron training and reports current accuracy on
training data and on heldout data.
"""
# Under de-biasing mode, we only allow features present in a given initial
# weight vector. These are features that have been "selected" under a previously
# run regularized training scheme.
valid_feature_names = None
if FLAGS.debiasing:
valid_feature_names = getFeatureNames(debiasing_weights)
for epoch in range(FLAGS.maxepochs):
# Randomize order of examples; broadcast this randomized order to all processes.
# The particular subset any perceptron process gets for this epoch is dependent
# upon this randomized ordering.
if myRank == 0 and FLAGS.shuffle:
random.shuffle(indices)
indices = mpi.broadcast(value=indices, root=0)
##################################################
# SEARCH: Find 1-best under current model
##################################################
# Run one epoch over training data
io_helper.write_master("===EPOCH %d TRAINING===\n" %(epoch))
newWeights_avg = perceptron_parallel(epoch, indices, training_blob, weights,
valid_feature_names)
####################################
# Dump weights for this iteration
####################################
if myRank == 0:
cPickle.dump(newWeights_avg, weights_out, protocol=cPickle.HIGHEST_PROTOCOL)
# Need to flush output somehow here. Does weights_out.flush() work?
weights_out.flush()
##################################################
# Try a corpus re-decode here with the new weights
# This returns a HELDOUT F-SCORE
##################################################
# Decode dev data with same new learned weight vector
if FLAGS.decodeheldout:
io_helper.write_master("===EPOCH %d DECODE HELDOUT===\n" %(epoch))
decode_parallel(newWeights_avg, indices_dev, heldout_blob, "dev")
if myRank == 0:
weights_out.close()
def do_training(indices, training_blob, heldout_blob, weights, weights_out, debiasing_weights):
"""
Helper/wrapper function for parallel perceptron training.
Runs one epoch of perceptron training and reports current accuracy on
training data and on heldout data.
"""
# Under de-biasing mode, we only allow features present in a given initial
# weight vector. These are features that have been "selected" under a previously
# run regularized training scheme.
valid_feature_names = None
if FLAGS.debiasing:
valid_feature_names = getFeatureNames(debiasing_weights)
for epoch in range(FLAGS.maxepochs):
# Randomize order of examples; broadcast this randomized order to all processes.
# The particular subset any perceptron process gets for this epoch is dependent
# upon this randomized ordering.
if myRank == 0 and FLAGS.shuffle:
random.shuffle(indices)
indices = mpi.broadcast(value=indices, root=0)
##################################################
# SEARCH: Find 1-best under current model
##################################################
# Run one epoch over training data
io_helper.write_master("===EPOCH %d TRAINING===\n" %(epoch))
newWeights_avg = perceptron_parallel(epoch, indices, training_blob, weights,
valid_feature_names)
####################################
# Dump weights for this iteration
####################################
if myRank == 0:
cPickle.dump(newWeights_avg, weights_out, protocol=cPickle.HIGHEST_PROTOCOL)
# Need to flush output somehow here. Does weights_out.flush() work?
weights_out.flush()
##################################################
# Try a corpus re-decode here with the new weights
# This returns a HELDOUT F-SCORE
##################################################
# Decode dev data with same new learned weight vector
if FLAGS.decodeheldout:
io_helper.write_master("===EPOCH %d DECODE HELDOUT===\n" %(epoch))
decode_parallel(newWeights_avg, indices_dev, heldout_blob, "dev")
if myRank == 0:
weights_out.close()
def do_training(indices, training_blob, heldout_blob, weights, weights_out, debiasing_weights):
"""
Helper/wrapper function for parallel perceptron training.
Runs one epoch of perceptron training and reports current accuracy on
training data and on heldout data.
"""
# Under de-biasing mode, we only allow features present in a given initial
# weight vector. These are features that have been "selected" under a previously
# run regularized training scheme.
valid_feature_names = None
if FLAGS.debiasing:
valid_feature_names = getFeatureNames(debiasing_weights)
# load training instances into memory
active_instances = [key for key in ['f_instances','e_instances','etree_instances','ftree_instances','gold_instances','a1_instances','a2_instances','inverse_instances'] if training_blob[key] is not None]
for key in active_instances:
training_blob[key+'_unshuffled'] = training_blob[key].readlines()
for epoch in range(FLAGS.maxepochs):
# Randomize order of examples; broadcast this randomized order to all processes.
# The particular subset any perceptron process gets for this epoch is dependent
# upon this randomized ordering.
if myRank == 0 and FLAGS.shuffle:
random.shuffle(indices)
indices = mpi.bcast(indices, root=0)
# Create virtual files in shuffled order
for key in active_instances:
shuffled = StringIO.StringIO()
unshuffled = training_blob[key+'_unshuffled']
for i in indices:
shuffled.write(unshuffled[i])
shuffled.seek(0)
training_blob[key] = shuffled
##################################################
# SEARCH: Find 1-best under current model
##################################################
# Run one epoch over training data
io_helper.write_master("===EPOCH %d TRAINING===\n" %(epoch))
newWeights_avg = perceptron_parallel(epoch, indices, training_blob, weights,
valid_feature_names)
####################################
# Dump weights for this iteration
####################################
if myRank == 0:
json.dump(newWeights_avg, weights_out)
weights_out.write('\n')
weights_out.flush()
##################################################
# Try a corpus re-decode here with the new weights
# This returns a HELDOUT F-SCORE
##################################################
# Decode dev data with same new learned weight vector
if FLAGS.decodeheldout:
io_helper.write_master("===EPOCH %d DECODE HELDOUT===\n" %(epoch))
decode_parallel(newWeights_avg, indices_dev, heldout_blob, "dev")
##################################################
# Reset heldout files for reading
##################################################
if FLAGS.decodeheldout:
for key in active_instances:
heldout_blob[key].seek(0)
if myRank == 0:
weights_out.close()
