del convert_tf_checkpoint_to_pytorch.py

pytorch-bert-code/bert/README.md

@@ -0,0 +1,39 @@
+### how to convert bert Converting Tensorflow Checkpoints to pytorch model file
+
+
+### 如何将bert model 的Tensorflow模型 转换为pytorch模型
+
+
+下载Tensorflow模型文件
+解压缩到文件夹下
+
+应该有
+
+- bert_config.json
+
+- bert_model.ckpt.data-00000-of-00001
+
+- bert_model.ckpt.index
+
+- bert_model.ckpt.meta
+
+- vocab.txt
+
+这几个文件
+运行run.sh
+后生成对应pytorch_model.bin
+
+具体代码
+
+```
+export BERT_BASE_DIR=。/
+
+transformers bert \
+  $BERT_BASE_DIR/bert_model.ckpt \
+  $BERT_BASE_DIR/bert_config.json \
+  $BERT_BASE_DIR/pytorch_model.bin
+
+```
+
+
+原来convert_tf_checkpoint_to_pytorch.py被新版本废除

pytorch-bert-code/bert/convert_tf_checkpoint_to_pytorch.py

@@ -1,105 +0,0 @@
-# coding=utf-8
-# Copyright 2018 The HugginFace Inc. team.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""Convert BERT checkpoint."""
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-
-import re
-import argparse
-import tensorflow as tf
-import torch
-import numpy as np
-
-from modeling import BertConfig, BertModel
-
-parser = argparse.ArgumentParser()
-
-## Required parameters
-parser.add_argument("--tf_checkpoint_path",
-                    default = None,
-                    type = str,
-                    required = True,
-                    help = "Path the TensorFlow checkpoint path.")
-parser.add_argument("--bert_config_file",
-                    default = None,
-                    type = str,
-                    required = True,
-                    help = "The config json file corresponding to the pre-trained BERT model. \n"
-                        "This specifies the model architecture.")
-parser.add_argument("--pytorch_dump_path",
-                    default = None,
-                    type = str,
-                    required = True,
-                    help = "Path to the output PyTorch model.")
-
-args = parser.parse_args()
-
-def convert():
-    # Initialise PyTorch model
-    config = BertConfig.from_json_file(args.bert_config_file)
-    model = BertModel(config)
-
-    # Load weights from TF model
-    path = args.tf_checkpoint_path
-    print("Converting TensorFlow checkpoint from {}".format(path))
-
-    init_vars = tf.train.list_variables(path)
-    names = []
-    arrays = []
-    for name, shape in init_vars:
-        print("Loading {} with shape {}".format(name, shape))
-        array = tf.train.load_variable(path, name)
-        print("Numpy array shape {}".format(array.shape))
-        names.append(name)
-        arrays.append(array)
-
-    for name, array in zip(names, arrays):
-        name = name[5:]  # skip "bert/"
-        print("Loading {}".format(name))
-        name = name.split('/')
-        if name[0] in ['redictions', 'eq_relationship']:
-            print("Skipping")
-            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':
-                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
-        pointer.data = torch.from_numpy(array)
-
-    # Save pytorch-model
-    torch.save(model.state_dict(), args.pytorch_dump_path)
-
-if __name__ == "__main__":
-    convert()

pytorch-bert-code/bert/run.sh

@@ -1 +1,3 @@
-python3 convert_tf_checkpoint_to_pytorch.py --tf_checkpoint_path bert_model.ckpt --bert_config_file bert_config.json --pytorch_dump_path bert_model.bin
+export BERT_BASE_DIR=./
+
+transformers bert   $BERT_BASE_DIR/bert_model.ckpt   $BERT_BASE_DIR/bert_config.json   $BERT_BASE_DIR/pytorch_model.bin