我在GPU机器上训练了TensorFLow模型。接下来,我需要将其导出并部署在仅CPU的生产机器上。
我使用MNIST export example中描述的导出。 Saver对象已在上面初始化。
with graph.as_default():
saver = tf.train.Saver(tf.all_variables(), sharded=True)
...
export_path = 'resnet34_rmsprop_wd1e-1/saves/'
print('Exporting trained model to %s' % export_path)
init_op = tf.group(tf.initialize_all_tables(), name='init_op')
model_exporter = exporter.Exporter(saver)
model_exporter.init(sess.graph.as_graph_def(),
init_op=init_op,
default_graph_signature=exporter.classification_signature(input_tensor=inference_images,
classes_tensor=inference_class,
scores_tensor=inference_predictions),
named_graph_signatures={'inputs': exporter.generic_signature({'images': inference_images}),
'outputs': exporter.generic_signature({'class': inference_class, 'predictions': inference_predictions})})
model_exporter.export(export_path, tf.constant(1), sess)
print('Done exporting!')
接下来,我尝试使用以下方法加载已保存的模型
new_saver = tf.train.import_meta_graph('assets/saved_model/export.meta')
new_saver.restore(sess, 'assets/saved_model/export')
我得到的是:
Traceback (most recent call last):
File "script_test_classifier.py", line 4, in <module>
...
line 33, in __initialize_session__
new_saver = tf.train.import_meta_graph('assets/saved_model/export.meta')
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1711, in import_meta_graph
read_meta_graph_file(meta_graph_or_file), clear_devices)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1598, in _import_meta_graph_def
input_graph_def, name="", producer_op_list=producer_op_list)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/importer.py", line 258, in import_graph_def
op_def = op_dict[node.op]
KeyError: u'SaveV2'
错误的原因是什么以及如何解决?
另外,也许还有其他方法可以将TensorFlow模型导入Python?
答案 0 :(得分:1)
最好使用TensorFlow服务来加载导出的模型:https://tensorflow.github.io/serving/serving_basic
此错误表示在注册的操作系统中找不到“SaveV2”。因此,您可以尝试将TensorFlow升级到最新版本。