def filter_low_segment_documents(self, documents):
new_documents = []
skipped = 0
for sample in documents:
sentences, groundTruths = zip(*sample)
avg_seg = compute_avg_seg_len(groundTruths)
if avg_seg >= MIN_TRAIN_AVG_SEGMENT_LENGTH:
new_documents.append(sample)
else:
skipped += 1
# pdb.set_trace()
print "Skipped %d documents due to MIN_TRAIN_AVG_SEGMENT_LENGTH=%d" %(skipped, MIN_TRAIN_AVG_SEGMENT_LENGTH)
return new_documents
def custom_fit(X_train, Y_train, X_test, Y_test, model, batch_size, epochs=10):
# Print Train stats
total_sentences, total_documents = 0, 0
total_documents = X_train.shape[0]
total_sentences = sum([doc.shape[0] for doc in X_train])
print "X-wiki TRAIN stats: Total %d sentences in %d documents" % (
total_sentences, total_documents)
class_weight = None
if SCALE_LOSS_FUN:
# Iterate as the no of sentences in each document is different
# so np.unique() messes up.
classes, counts = None, []
for _temp_Yi in Y_train:
classes, _temp_counts = np.unique(_temp_Yi, return_counts=True)
counts.append(_temp_counts)
counts = np.sum(counts, axis=0)
class_weight = dict(zip(classes.tolist(), counts / float(sum(counts))))
print class_weight
train_avg_seg_len = np.mean(
[helper.compute_avg_seg_len(Yi) for Yi in Y_train], axis=0)
print ">> Train AVG_SEGMENT_LENGTH:", train_avg_seg_len
print 'Train...'
start_epoch = 0
if LOAD_SAVED_MODEL_AND_CONTINUE_TRAIN: # If we have saved model, then continue from the last epoch where we stopped
start_epoch = saved_model_epoch_done # The epoch count is zero indexed in TRAIN, while the count in saved file is 1 indexed
print_iter_count = 0
for epoch in range(start_epoch, epochs):
mean_tr_acc, mean_tr_loss, mean_tr_rec = [], [], []
rLoss, rRecall, rAcc = 0, 0, 0 # Running parameters for printing while training
for batch_count, (
batch_X_left, batch_X_mid, batch_X_right,
batch_Y_mid) in enumerate(
batch_gen_consecutive_context_segments_from_big_seq(
"train", X_train, Y_train, batch_size,
ONE_SIDE_CONTEXT_SIZE)):
#batch_Y_vec = to_categorical_MULTI_DIM(batch_Y, nb_classes=2)
try:
#pdb.set_trace()
batch_Y_mid = to_categorical(batch_Y_mid, nb_classes=2)
start = time.time()
tr_loss, tr_acc, tr_rec = model.train_on_batch(
[batch_X_left, batch_X_mid, batch_X_right], batch_Y_mid)
speed = time.time() - start
mean_tr_acc.append(tr_acc)
mean_tr_loss.append(tr_loss)
mean_tr_rec.append(tr_rec)
#rLoss, rRecall, rAcc = (rLoss*batch_count + tr_loss)/(batch_count + 1), (rRecall*batch_count + tr_rec)/(batch_count + 1), (rAcc*batch_count + tr_acc)/(batch_count + 1)
#progbar.prog_bar(True, total_sentences, epochs, batch_size, epoch, batch_count, speed=speed, data={ 'rLoss': rLoss, 'rAcc': rAcc, 'rRec': rRecall })
progbar.prog_bar(True,
total_sentences,
epochs,
batch_size,
epoch,
batch_count,
speed=speed,
data={
'Loss': tr_loss,
'Acc': tr_acc,
'Rec': tr_rec
})
# Print test results after every 100 batch trains
#if (not batch_count % 100) and batch_count != 0:
# print "\nTEST-ITER-COUNT: %d" %(print_iter_count)
# testing_on_data("Wikipedia(DEVELOPMENT)", X_test, Y_test, model, batch_size, summary_only=True)
# testing_on_data("Clinical", X_cli, Y_cli, model, batch_size, summary_only=True)
# testing_on_data("Biography", X_bio, Y_bio, model, batch_size)
# testing_on_data("Fiction", X_fic, Y_fic, model, batch_size, summary_only=True)
# testing_on_data("Wikipedia(BENCHMARK)", X_wikitest, Y_wikitest, model, batch_size, summary_only=True)
# print_iter_count += 1
except KeyboardInterrupt, SystemExit:
print ""
print "########################################################"
print "###### Pausing execution. Press ENTER to continue #####"
print "########################################################"
out = raw_input(
'Enter "pdb" to get prompt or ENTER to exit.> ')
if out == "pdb":
pdb.set_trace()
except Exception as e:
print e
print ">>>>> Is it intentional ?"
def custom_fit(X_train, Y_train, X_test, Y_test, model, batch_size, epochs=10):
# Print Train stats
total_sentences, total_documents = 0, 0
total_documents = X_train.shape[0]
total_sentences = sum([doc.shape[0] for doc in X_train])
print "X-wiki TRAIN stats: Total %d sentences in %d documents" % (
total_sentences, total_documents)
class_weight = None
if SCALE_LOSS_FUN:
# Iterate as the no of sentences in each document is different
# so np.unique() messes up.
classes, counts = None, []
for _temp_Yi in Y_train:
classes, _temp_counts = np.unique(_temp_Yi, return_counts=True)
counts.append(_temp_counts)
counts = np.sum(counts, axis=0)
class_weight = dict(zip(classes.tolist(), counts / float(sum(counts))))
print class_weight
train_avg_seg_len = np.mean(
[helper.compute_avg_seg_len(Yi) for Yi in Y_train], axis=0)
print ">> Train AVG_SEGMENT_LENGTH:", train_avg_seg_len
print 'Train...'
start_epoch = 0
if LOAD_SAVED_MODEL_AND_CONTINUE_TRAIN: # If we have saved model, then continue from the last epoch where we stopped
start_epoch = saved_model_epoch_done # The epoch count is zero indexed in TRAIN, while the count in saved file is 1 indexed
print_iter_count = 0
for epoch in range(start_epoch, epochs):
mean_tr_acc, mean_tr_loss, mean_tr_rec = [], [], []
batch_count = 0
rLoss, rRecall, rAcc = 0, 0, 0 # Running parameters for printing while training
for i in range(total_documents):
X, Y = X_train[i], Y_train[i]
for (batch_X, batch_Y) in batch_gen_sentences_without_context(
X, Y, batch_size, fixed_size=False):
#pdb.set_trace()
batch_Y = to_categorical(
batch_Y, nb_classes=2) # Convert to output as 2 classes
start = time.time()
tr_loss, tr_acc, tr_rec = model.train_on_batch([batch_X],
batch_Y)
speed = time.time() - start
mean_tr_acc.append(tr_acc)
mean_tr_loss.append(tr_loss)
mean_tr_rec.append(tr_rec)
#rLoss, rRecall, rAcc = (rLoss*batch_count + tr_loss)/(batch_count + 1), (rRecall*batch_count + tr_rec)/(batch_count + 1), (rAcc*batch_count + tr_acc)/(batch_count + 1)
#progbar.prog_bar(True, total_sentences, epochs, batch_size, epoch, batch_count, speed=speed, data={ 'rLoss': rLoss, 'rAcc': rAcc, 'rRec': rRecall })
progbar.prog_bar(True,
total_sentences,
epochs,
batch_size,
epoch,
batch_count,
speed=speed,
data={
'Loss': tr_loss,
'Acc': tr_acc,
'Rec': tr_rec
})
batch_count += 1
progbar.end()
if SAVE_MODEL_AFTER_EACH_EPOCH:
model.save("model_trainable_%s_epoc_%d.h5" %
(str(TRAINABLE_EMBEDDINGS), epoch + 1))
print ">> Epoch: %d/%d" % (epoch + 1, epochs)
print('accuracy training = {}'.format(np.mean(mean_tr_acc)))
print('recall training = {}'.format(np.mean(mean_tr_rec)))
print('loss training = {}'.format(np.mean(mean_tr_loss)))
testing_on_data("Wikipedia(DEVELOPMENT)",
X_test,
Y_test,
model,
batch_size,
summary_only=True)
testing_on_data("Clinical",
X_cli,
Y_cli,
model,
batch_size,
summary_only=True)
#testing_on_data("Biography", X_bio, Y_bio, model, batch_size)
testing_on_data("Fiction",
X_fic,
Y_fic,
model,
batch_size,
summary_only=True)
testing_on_data("Wikipedia(BENCHMARK)",
X_wikitest,
Y_wikitest,
model,
batch_size,
summary_only=True)
print('___________________________________')
# Testing
print "####################################################################"
print ">> (TEST) >> Testing, X:", X_test.shape, "Y:", Y_test.shape
mean_te_acc, mean_te_loss, mean_te_rec = [], [], []
for i in range(X_test.shape[0]):
X, Y = X_test[i], Y_test[i]
for batch_X, batch_Y in batch_gen_sentences_without_context(
X, Y, batch_size, fixed_size=False):
te_loss, te_acc, te_rec = model.test_on_batch([batch_X], batch_Y)
mean_te_acc.append(te_acc)
mean_te_loss.append(te_loss)
mean_te_rec.append(te_rec)
print('accuracy testing = {}'.format(np.mean(mean_te_acc)))
print('recall testing = {}'.format(np.mean(mean_te_rec)))
print('loss testing = {}'.format(np.mean(mean_te_loss)))