Fixing --save_w2v and --save_t2v options

Author: urialon

config.py

@@ -13,7 +13,7 @@ def arguments_parser(cls) -> ArgumentParser:
         parser.add_argument("-d", "--data", dest="data_path",
                             help="path to preprocessed dataset", required=False)
         parser.add_argument("-te", "--test", dest="test_path",
-                            help="path to test file", metavar="FILE", required=False)
+                            help="path to test file", metavar="FILE", required=False, default='')
         parser.add_argument("-s", "--save", dest="save_path",
                             help="path to save the model file", metavar="FILE", required=False)
         parser.add_argument("-w2v", "--save_word2v", dest="save_w2v",
@@ -117,7 +117,7 @@ def __init__(self, set_defaults: bool = False, load_from_args: bool = False, ver
         self.MODEL_SAVE_PATH: Optional[str] = None
         self.MODEL_LOAD_PATH: Optional[str] = None
         self.TRAIN_DATA_PATH_PREFIX: Optional[str] = None
-        self.TEST_DATA_PATH: Optional[str] = None
+        self.TEST_DATA_PATH: Optional[str] = ''
         self.RELEASE: bool = False
         self.EXPORT_CODE_VECTORS: bool = False
         self.SAVE_W2V: Optional[str] = None   # TODO: update README;
@@ -171,8 +171,6 @@ def test_steps(self) -> int:
         return ceil(self.NUM_TEST_EXAMPLES / self.TEST_BATCH_SIZE) if self.TEST_BATCH_SIZE else 0
 
     def data_path(self, is_evaluating: bool = False):
-        if self.RELEASE:
-            return ''
         return self.TEST_DATA_PATH if is_evaluating else self.train_data_path
 
     def batch_size(self, is_evaluating: bool = False):

tensorflow_model.py

@@ -378,12 +378,28 @@ def _load_inner_model(self, sess=None):
     def _get_vocab_embedding_as_np_array(self, vocab_type: VocabType) -> np.ndarray:
         assert vocab_type in VocabType
         vocab_tf_variable_name = self.vocab_type_to_tf_variable_name_mapping[vocab_type]
-        with tf.compat.v1.variable_scope('model', reuse=None):
-            embeddings = tf.compat.v1.get_variable(vocab_tf_variable_name)
-            self.saver = tf.compat.v1.train.Saver()
-            self._load_inner_model(self.sess)
-            vocab_embedding_matrix = self.sess.run(embeddings)
-            return vocab_embedding_matrix
+        
+        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._build_tf_test_graph(input_iterator.get_next())
+
+        if vocab_type is VocabType.Token:
+            shape = (self.vocabs.token_vocab.size, self.config.TOKEN_EMBEDDINGS_SIZE)
+        elif vocab_type is VocabType.Target:
+            shape = (self.vocabs.target_vocab.size, self.config.TARGET_EMBEDDINGS_SIZE)
+        elif vocab_type is VocabType.Path:
+            shape = (self.vocabs.path_vocab.size, self.config.PATH_EMBEDDINGS_SIZE)
+
+        with tf.compat.v1.variable_scope('model', reuse=True):
+            embeddings = tf.compat.v1.get_variable(vocab_tf_variable_name, shape=shape)
+        self.saver = tf.compat.v1.train.Saver()
+        self._initialize_session_variables() 
+        self._load_inner_model(self.sess) 
+        vocab_embedding_matrix = self.sess.run(embeddings)
+        return vocab_embedding_matrix
 
     def get_should_reuse_variables(self):
         if self.config.TRAIN_DATA_PATH_PREFIX: