python-3.x - 如何将 .ckpt 转换为 .pb？

Question

我是深度学习的新手，我想使用预训练 (EAST) 模型从 AI Platform Serving 提供服务，开发人员提供了以下文件:

model.ckpt-49491.data-00000-of-00001

检查站

model.ckpt-49491.index

model.ckpt-49491.meta

我想把它转换成 TensorFlow .pb格式。有没有办法做到这一点？我的模型来自 here

完整代码可用here .

我查过 here它显示了以下代码来转换它:

来自 tensorflow/models/research/

INPUT_TYPE=image_tensor
PIPELINE_CONFIG_PATH={path to pipeline config file}
TRAINED_CKPT_PREFIX={path to model.ckpt}
EXPORT_DIR={path to folder that will be used for export}

python object_detection/export_inference_graph.py \
    --input_type=${INPUT_TYPE} \
    --pipeline_config_path=${PIPELINE_CONFIG_PATH} \
    --trained_checkpoint_prefix=${TRAINED_CKPT_PREFIX} \
    --output_directory=${EXPORT_DIR}

我无法弄清楚要传递什么值:

INPUT_TYPE

PIPELINE_CONFIG_PATH。

Answer 1

这是将检查点转换为 SavedModel 的代码

import os
import tensorflow as tf

trained_checkpoint_prefix = 'models/model.ckpt-49491'
export_dir = os.path.join('export_dir', '0')

graph = tf.Graph()
with tf.compat.v1.Session(graph=graph) as sess:
    # Restore from checkpoint
    loader = tf.compat.v1.train.import_meta_graph(trained_checkpoint_prefix + '.meta')
    loader.restore(sess, trained_checkpoint_prefix)

    # Export checkpoint to SavedModel
    builder = tf.compat.v1.saved_model.builder.SavedModelBuilder(export_dir)
    builder.add_meta_graph_and_variables(sess,
                                         [tf.saved_model.TRAINING, tf.saved_model.SERVING],
                                         strip_default_attrs=True)
    builder.save()