updating code organization to fix imports

pytorch_pretrained_bert/modeling.py

@@ -33,7 +33,6 @@ from torch import nn
 from torch.nn import CrossEntropyLoss
 
 from .file_utils import cached_path
-from .convert_tf_checkpoint_to_pytorch import load_tf_weights_in_bert
 
 logger = logging.getLogger(__name__)
 
@@ -50,6 +49,59 @@ CONFIG_NAME = 'bert_config.json'
 WEIGHTS_NAME = 'pytorch_model.bin'
 TF_WEIGHTS_NAME = 'model.ckpt'
 
+def load_tf_weights_in_bert(model, tf_checkpoint_path):
+    """ Load tf checkpoints in a pytorch model
+    """
+    tf_path = os.path.abspath(tf_checkpoint_path)
+    print("Converting TensorFlow checkpoint from {}".format(tf_path))
+    # Load weights from TF model
+    init_vars = tf.train.list_variables(tf_path)
+    names = []
+    arrays = []
+    for name, shape in init_vars:
+        print("Loading TF weight {} with shape {}".format(name, shape))
+        array = tf.train.load_variable(tf_path, name)
+        names.append(name)
+        arrays.append(array)
+
+    for name, array in zip(names, arrays):
+        name = name.split('/')
+        # adam_v and adam_m are variables used in AdamWeightDecayOptimizer to calculated m and v
+        # which are not required for using pretrained model
+        if any(n in ["adam_v", "adam_m"] for n in name):
+            print("Skipping {}".format("/".join(name)))
+            continue
+        pointer = model
+        for m_name in name:
+            if re.fullmatch(r'[A-Za-z]+_\d+', m_name):
+                l = re.split(r'_(\d+)', m_name)
+            else:
+                l = [m_name]
+            if l[0] == 'kernel' or l[0] == 'gamma':
+                pointer = getattr(pointer, 'weight')
+            elif l[0] == 'output_bias' or l[0] == 'beta':
+                pointer = getattr(pointer, 'bias')
+            elif l[0] == 'output_weights':
+                pointer = getattr(pointer, 'weight')
+            else:
+                pointer = getattr(pointer, l[0])
+            if len(l) >= 2:
+                num = int(l[1])
+                pointer = pointer[num]
+        if m_name[-11:] == '_embeddings':
+            pointer = getattr(pointer, 'weight')
+        elif m_name == 'kernel':
+            array = np.transpose(array)
+        try:
+            assert pointer.shape == array.shape
+        except AssertionError as e:
+            e.args += (pointer.shape, array.shape)
+            raise
+        print("Initialize PyTorch weight {}".format(name))
+        pointer.data = torch.from_numpy(array)
+    return model
+
+
 def gelu(x):
     """Implementation of the gelu activation function.
         For information: OpenAI GPT's gelu is slightly different (and gives slightly different results):