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 from_model_input_form(self, input_row) -> ReaderInputTensors:
return ReaderInputTensors(
target_index=input_row[0],
path_source_token_indices=input_row[1],
path_indices=input_row[2],
path_target_token_indices=input_row[3],
context_valid_mask=input_row[4]
)
def from_model_input_form(self, input_row) -> ReaderInputTensors:
inputs, targets = input_row
return ReaderInputTensors(
path_source_token_indices=inputs[0],
path_indices=inputs[1],
path_target_token_indices=inputs[2],
context_valid_mask=inputs[3],
target_index=targets if self.estimator_action.is_train else targets['target_index'],
target_string=targets['target_string'] if not self.estimator_action.is_train else None,
path_source_token_strings=inputs[4] if self.estimator_action.is_predict else None,
path_strings=inputs[5] if self.estimator_action.is_predict else None,
path_target_token_strings=inputs[6] if self.estimator_action.is_predict else None
)
def from_model_input_form(self, input_row) -> ReaderInputTensors:
inputs, targets = input_row
return ReaderInputTensors(
path_source_token_indices=inputs[0],
path_indices=inputs[1],
path_target_token_indices=inputs[2],
context_valid_mask=inputs[3],
#I'm changing this for the same reason of the changes in previous function.
#target_index=targets if self.estimator_action.is_train else targets['target_index'],
#target_string=targets['target_string'] if not self.estimator_action.is_train else None,
target_index=targets,
target_string=None,
path_source_token_strings=inputs[4]
if self.estimator_action.is_predict else None,
path_strings=inputs[5]
if self.estimator_action.is_predict else None,
path_target_token_strings=inputs[6]
if self.estimator_action.is_predict else None)