在TensorFlow中加載輸出模型

Question

我有一臺在GPU機器上訓練過的TensorFLow模型。接下來，我需要將其導出並部署在僅限CPU的生產機器上。

我已經使用了MNIST export example中描述的輸出。上面初始化了保存對象。

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!') 

接下來，我試圖加載保存模型：

new_saver = tf.train.import_meta_graph('assets/saved_model/export.meta') 
new_saver.restore(sess, 'assets/saved_model/export') 

什麼，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' 

什麼是錯誤的原因，以及它如何可能被修復？

此外，也許還有其他方式導入TensorFlow模型到Python？

Answer 1

最好是使用TensorFlow服務加載出口型號：https://tensorflow.github.io/serving/serving_basic

這個錯誤說「SaveV2」未在註冊OPS找到。所以你可以嘗試將TensorFlow升級到最新版本。