def on_epoch_end(self, epoch, logs={}):
self.losses.append(logs.get('loss'))
evaluation_parameter = predict(self.conf, self.concept, self.positives,
self.vocab, self.entity_model,
self.concept_model, self.model,
self.val_data)
self.accuracy.append(evaluation_parameter)
with open(self.history, 'a', encoding='utf-8') as f:
f.write(
'Epoch: {0}, Training loss: {1}, validation accuracy: {2}\n'.
format(epoch, logs.get('loss'), evaluation_parameter))
if evaluation_parameter > self.best:
logging.info('Intermediate model saved.')
self.best = evaluation_parameter
self.model.save(self.model_path)
self.wait = 0
# something here to print trec_eval doc
else:
self.wait += 1
if self.wait > int(self.conf['training']['patience']):
self.stopped_epoch = epoch
self.model.stop_training = True
if self.save and self.model.stop_training:
logger.info('Saving predictions to {0}'.format(
self.conf['model']['path_saved_predictions']))
model_tools.save_predictions(
self.conf['model']['path_saved_predictions'],
test_y) #(filename,predictions)
logger.info(
'Testing: epoch: {0}, self.model.stop_training: {1}'.format(
epoch, self.model.stop_training))
return
def on_epoch_end(self, epoch, logs={}):
self.losses.append(logs.get('loss'))
#before = datetime.now()
test_y = self.model.predict(self.val_data.x)
#after = datetime.now()
#logger.info('Time taken for prediction without speedup:{0}'.format(after-before))
evaluation_parameter = evaluate(self.val_data.mentions, test_y,
self.val_data.y)
self.accuracy.append(evaluation_parameter)
with open(self.history, 'a', encoding='utf-8') as f:
f.write(
'Epoch: {0}, Training loss: {1}, validation accuracy: {2}\n'.
format(epoch, logs.get('loss'), evaluation_parameter))
if evaluation_parameter > self.best:
logging.info('Intermediate model saved.')
self.best = evaluation_parameter
self.model.save(self.model_path)
self.wait = 0
# something here to print trec_eval doc
else:
self.wait += 1
if self.wait > int(self.conf['training']['patience']):
self.stopped_epoch = epoch
self.model.stop_training = True
if self.save and self.model.stop_training:
logger.info('Saving predictions to {0}'.format(
self.conf['model']['path_saved_predictions']))
model_tools.save_predictions(
self.conf['model']['path_saved_predictions'],
test_y) #(filename,predictions)
logger.info(
'Testing: epoch: {0}, self.model.stop_training: {1}'.format(
epoch + 1, self.model.stop_training))
return