def test_model(nn_model):
data = DataHolder('dev')
X_dev, Y_dev = data.get_full_data()
loss_and_metrics = model.evaluate(X_dev,
Y_dev,
batch_size=TRAIN_BATCH_SIZE)
print 'Evals:', loss_and_metrics
def get_classifier_results(data_set, model_path = SAVE_MODEL_DIR):
data = DataHolder(data_set)
with tf.Graph().as_default():
start = time.time()
model = PassClassifier(EmbeddingHolder().get_embeddings_mat(), True)
print "\nRebuild graph took " + str(time.time() - start) + " seconds"
saver = tf.train.Saver()
with tf.Session() as session:
session = session
saver.restore(session, model_path)
print 'Restored model. Predicting....'
preds = model.predict(session, data)
list_preds = list()
for batch in preds:
for row in batch:
list_preds.append(row)
preds = np.asarray(list_preds)
y = data.get_full_selected()
f = open('classifier_check_log', 'w')
f.write("File to check results of classifier:\n Preds Y")
for p_val, y_val in zip(preds, y):
f.write(str(p_val) + ' ' + str(y_val))
f.write('\n')
classifier_eval(preds, y)
print 'Done Predicting'
def train_model(nn_model):
data = DataHolder('train')
print 'Data retrieved'
for epoc in range(NUM_EPOCS):
for i in tqdm(range(1, data.get_num_iterations())):
X_batch, Y_batch = data.get_batch_data()
if X_batch is None or Y_batch is None: break
print X_batch.shape, Y_batch.shape
curr_loss = nn_model.train_on_batch(X_batch, Y_batch)
print 'LOSS:', curr_loss
if i % SAVE_PREDICTIONS_FREQUENCY == 0:
save_model(nn_model)
print 'finished EPOC: ', epoc
save_model(nn_model)
def get_preds(data_set, model_type = None, model_path = SAVE_MODEL_DIR, output_file_name='./data/last_preds.json'): pred_handler = PredictionHandler() data = DataHolder(data_set) with tf.Graph().as_default(): start = time.time() if model_type == 'l2_attn': model = l2_attn.TFModel(EmbeddingHolder().get_embeddings_mat(), True) elif model_type == 'l2_2attn': model = l2_2attn.TFModel(EmbeddingHolder().get_embeddings_mat(), True) elif model_type == 'l2_double_2attn': model = l2_double_2attn.TFModel(EmbeddingHolder().get_embeddings_mat(), True) elif model_type == 'ce_attn': model = ce_attn.TFModel(EmbeddingHolder().get_embeddings_mat(), True) elif model_type == 'ce_2attn': model = ce_2attn.TFModel(EmbeddingHolder().get_embeddings_mat(), True) else: return print "\nRebuild graph took " + str(time.time() - start) + " seconds" saver = tf.train.Saver() with tf.Session() as session: session = session saver.restore(session, model_path) print 'Restored model. Predicting....' preds = model.predict(session, data) pred_handler.write_preds(preds, output_file_name) print 'Done Predicting'
def keep_training(model_path = SAVE_MODEL_DIR, prev_best_rouge=0):
pred_handler = PredictionHandler()
data = DataHolder('train')
with tf.Graph().as_default():
start = time.time()
model = l2_double_2attn.TFModel(EmbeddingHolder().get_embeddings_mat())
print "\nRebuild graph took " + str(time.time() - start) + " seconds"
saver = tf.train.Saver()
with tf.Session() as session:
session = session
saver.restore(session, model_path)
print 'Restored model. Predicting....'
merged = tf.summary.merge_all()
model.best_rouge = prev_best_rouge
losses = model.fit(session, saver, merged, data)
model.train_writer.close()
model.test_writer.close()
model.log.close()
print 'Done continueing'
def __init__(self,
data_set=None,
output_file_name=OUTPUT_FILE_NAME,
build_ground_truth=False):
# To build ground truth, uncomment these two lines and run the comamand:
# python prediction_handler.py
if build_ground_truth:
self.data_set = data_set
self.data = DataHolder(data_set)
self.output_file_name = output_file_name
self.index_word = self.get_index_word_dict()
print "pred argmax ", self._temp_test_pred_argmax
print "train argmax ", np.argmax(preds_from_training, axis = 2)
print "answer indices ", self._temp_test_answer_indices
def __init__(self, embeddings, predicting=False):
self.predicting = predicting
self.pretrained_embeddings = tf.Variable(embeddings)
self.log = open(LOG_FILE_DIR, "a")
self.build()
if __name__ == "__main__":
print 'Starting, and now printing to log.txt'
data = DataHolder('train')
embeddings = EmbeddingHolder().get_embeddings_mat()
with tf.Graph().as_default():
start = time.time()
model = TFModel(embeddings)
model.log.write("\nBuild graph took " + str(time.time() - start) + " seconds")
init = tf.global_variables_initializer()
saver = tf.train.Saver()
model.log.write('\ninitialzed variables')
config = tf.ConfigProto()
# config.gpu_options.allow_growth=True
# config.gpu_options.per_process_gpu_memory_fraction = 0.6
with tf.Session(config=config) as session:
merged = tf.summary.merge_all()