def predict(self, predict_data_rows: Iterable[str]) -> List[ModelPredictionResults]:
predict_input_reader = self._create_data_reader(estimator_action=EstimatorAction.Predict)
input_iterator = predict_input_reader.process_and_iterate_input_from_data_lines(predict_data_rows)
all_model_prediction_results = []
for input_row in input_iterator:
# perform the actual prediction and get raw results.
input_for_predict = input_row[0][:4] # we want only the relevant input vectors (w.o. the targets).
prediction_results = self.keras_model_predict_function(input_for_predict)
# make `input_row` and `prediction_results` easy to read (by accessing named fields).
prediction_results = KerasPredictionModelOutput(
*common.squeeze_single_batch_dimension_for_np_arrays(prediction_results))
input_row = _KerasModelInputTensorsFormer(
estimator_action=EstimatorAction.Predict).from_model_input_form(input_row)
input_row = ReaderInputTensors(*common.squeeze_single_batch_dimension_for_np_arrays(input_row))
# calculate the attention weight for each context
attention_per_context = self._get_attention_weight_per_context(
path_source_strings=input_row.path_source_token_strings,
path_strings=input_row.path_strings,
path_target_strings=input_row.path_target_token_strings,
attention_weights=prediction_results.attention_weights
)
# store the calculated prediction results in the wanted format.
model_prediction_results = ModelPredictionResults(
original_name=common.binary_to_string(input_row.target_string.item()),
topk_predicted_words=common.binary_to_string_list(prediction_results.topk_predicted_words),
topk_predicted_words_scores=prediction_results.topk_predicted_words_scores,
attention_per_context=attention_per_context,
code_vector=prediction_results.code_vectors)
all_model_prediction_results.append(model_prediction_results)
return all_model_prediction_results
def predict(self, predict_data_lines: Iterable[str]) -> List[ModelPredictionResults]:
if self.predict_reader is None:
self.predict_reader = PathContextReader(vocabs=self.vocabs,
model_input_tensors_former=_TFEvaluateModelInputTensorsFormer(),
config=self.config, estimator_action=EstimatorAction.Predict)
self.predict_placeholder = tf.compat.v1.placeholder(tf.string)
reader_output = self.predict_reader.process_input_row(self.predict_placeholder)
self.predict_top_words_op, self.predict_top_values_op, self.predict_original_names_op, \
self.attention_weights_op, self.predict_source_string, self.predict_path_string, \
self.predict_path_target_string, self.predict_code_vectors = \
self._build_tf_test_graph(reader_output, normalize_scores=True)
self._initialize_session_variables()
self.saver = tf.compat.v1.train.Saver()
self._load_inner_model(sess=self.sess)
prediction_results: List[ModelPredictionResults] = []
for line in predict_data_lines:
batch_top_words, batch_top_scores, batch_original_name, batch_attention_weights, batch_path_source_strings,\
batch_path_strings, batch_path_target_strings, batch_code_vectors = self.sess.run(
[self.predict_top_words_op, self.predict_top_values_op, self.predict_original_names_op,
self.attention_weights_op, self.predict_source_string, self.predict_path_string,
self.predict_path_target_string, self.predict_code_vectors],
feed_dict={self.predict_placeholder: line})
# shapes:
# batch_top_words, top_scores: (batch, top_k)
# batch_original_name: (batch, )
# batch_attention_weights: (batch, max_context, 1)
# batch_path_source_strings, batch_path_strings, batch_path_target_strings: (batch, max_context)
# batch_code_vectors: (batch, code_vector_size)
# remove first axis: (batch=1, ...)
assert all(tensor.shape[0] == 1 for tensor in (batch_top_words, batch_top_scores, batch_original_name,
batch_attention_weights, batch_path_source_strings,
batch_path_strings, batch_path_target_strings,
batch_code_vectors))
top_words = np.squeeze(batch_top_words, axis=0)
top_scores = np.squeeze(batch_top_scores, axis=0)
original_name = batch_original_name[0]
attention_weights = np.squeeze(batch_attention_weights, axis=0)
path_source_strings = np.squeeze(batch_path_source_strings, axis=0)
path_strings = np.squeeze(batch_path_strings, axis=0)
path_target_strings = np.squeeze(batch_path_target_strings, axis=0)
code_vectors = np.squeeze(batch_code_vectors, axis=0)
top_words = common.binary_to_string_list(top_words)
original_name = common.binary_to_string(original_name)
attention_per_context = self._get_attention_weight_per_context(
path_source_strings, path_strings, path_target_strings, attention_weights)
prediction_results.append(ModelPredictionResults(
original_name=original_name,
topk_predicted_words=top_words,
topk_predicted_words_scores=top_scores,
attention_per_context=attention_per_context,
code_vector=(code_vectors if self.config.EXPORT_CODE_VECTORS else None)
))
return prediction_results
def evaluate(self) -> Optional[ModelEvaluationResults]:
eval_start_time = time.time()
if self.eval_reader is None:
self.eval_reader = PathContextReader(
vocabs=self.vocabs,
model_input_tensors_former=_TFEvaluateModelInputTensorsFormer(
),
config=self.config,
estimator_action=EstimatorAction.Evaluate)
input_iterator = tf.compat.v1.data.make_initializable_iterator(
self.eval_reader.get_dataset())
self.eval_input_iterator_reset_op = input_iterator.initializer
input_tensors = input_iterator.get_next()
self.eval_top_words_op, self.eval_top_values_op, self.eval_original_names_op, _, _, _, _, _, _, \
self.eval_code_vectors = self._build_tf_test_graph(input_tensors)
self.saver = tf.compat.v1.train.Saver()
if self.config.MODEL_LOAD_PATH and not self.config.TRAIN_DATA_PATH_PREFIX:
self._initialize_session_variables()
self._load_inner_model(self.sess)
if self.config.RELEASE:
release_name = self.config.MODEL_LOAD_PATH + '.release'
self.log('Releasing model, output model: %s' % release_name)
self.saver.save(self.sess, release_name)
return None # FIXME: why do we return none here?
with open('log.txt', 'w') as log_output_file:
if self.config.EXPORT_CODE_VECTORS:
code_vectors_file = open(
self.config.TEST_DATA_PATH + '.vectors', 'w')
total_predictions = 0
total_prediction_batches = 0
subtokens_evaluation_metric = SubtokensEvaluationMetric(
partial(common.filter_impossible_names,
self.vocabs.target_vocab.special_words))
topk_accuracy_evaluation_metric = TopKAccuracyEvaluationMetric(
self.config.TOP_K_WORDS_CONSIDERED_DURING_PREDICTION,
partial(common.get_first_match_word_from_top_predictions,
self.vocabs.target_vocab.special_words))
start_time = time.time()
self.sess.run(self.eval_input_iterator_reset_op)
self.log('Starting evaluation')
# Run evaluation in a loop until iterator is exhausted.
# Each iteration = batch. We iterate as long as the tf iterator (reader) yields batches.
try:
while True:
top_words, top_scores, original_names, code_vectors = self.sess.run(
[
self.eval_top_words_op, self.eval_top_values_op,
self.eval_original_names_op, self.eval_code_vectors
], )
# shapes:
# top_words: (batch, top_k); top_scores: (batch, top_k)
# original_names: (batch, ); code_vectors: (batch, code_vector_size)
top_words = common.binary_to_string_matrix(
top_words) # (batch, top_k)
original_names = common.binary_to_string_list(
original_names) # (batch,)
self._log_predictions_during_evaluation(
zip(original_names, top_words), log_output_file)
topk_accuracy_evaluation_metric.update_batch(
zip(original_names, top_words))
subtokens_evaluation_metric.update_batch(
zip(original_names, top_words))
total_predictions += len(original_names)
total_prediction_batches += 1
if self.config.EXPORT_CODE_VECTORS:
self._write_code_vectors(code_vectors_file,
code_vectors)
if total_prediction_batches % self.config.NUM_BATCHES_TO_LOG_PROGRESS == 0:
elapsed = time.time() - start_time
# start_time = time.time()
self._trace_evaluation(total_predictions, elapsed)
except tf.errors.OutOfRangeError:
pass # reader iterator is exhausted and have no more batches to produce.
self.log('Done evaluating, epoch reached')
log_output_file.write(
str(topk_accuracy_evaluation_metric.topk_correct_predictions) +
'\n')
if self.config.EXPORT_CODE_VECTORS:
code_vectors_file.close()
elapsed = int(time.time() - eval_start_time)
self.log("Evaluation time: %sH:%sM:%sS" %
((elapsed // 60 // 60), (elapsed // 60) % 60, elapsed % 60))
return ModelEvaluationResults(
topk_acc=topk_accuracy_evaluation_metric.topk_correct_predictions,
subtoken_precision=subtokens_evaluation_metric.precision,
subtoken_recall=subtokens_evaluation_metric.recall,
subtoken_f1=subtokens_evaluation_metric.f1)
