分布式深度推荐系统 - Tensorflow:失败:在指定的导出位置找不到会话包或SavedModel包

时间:2017-07-14 10:02:59

标签: tensorflow tensorflow-serving

执行分布式张量流后,如以下链接所示:

https://github.com/tobegit3hub/deep_recommend_system/tree/master/distributed

我在./checkpoint文件夹中获得了以下内容;

checkpoint
graph.pbtxt
model.ckpt-269.data-00000-of-00001
model.ckpt-269.index
model.ckpt-269.meta

我想在TensorFlow Serving中提供的上述模型上运行tensorFlow服务。但是这样做时我会得到以下错误:

 ./tensorflow_model_server --port="9000" --model_base_path=./model/

2017-07-14 15:32:32.791636: I tensorflow_serving/model_servers/main.cc:151] Building single TensorFlow model file config:  model_name: default model_base_path: ./model/ model_version_policy: 0

2017-07-14 15:32:32.792156: I tensorflow_serving/model_servers/server_core.cc:375] Adding/updating models.
2017-07-14 15:32:32.792188: I tensorflow_serving/model_servers/server_core.cc:421]  (Re-)adding model: default
2017-07-14 15:32:32.893072: I tensorflow_serving/core/basic_manager.cc:698] Successfully reserved resources to load servable {name: default version: 1}
2017-07-14 15:32:32.893143: I tensorflow_serving/core/loader_harness.cc:66] Approving load for servable version {name: default version: 1}
2017-07-14 15:32:32.893165: I tensorflow_serving/core/loader_harness.cc:74] Loading servable version {name: default version: 1}
2017-07-14 15:32:32.893252: E tensorflow_serving/util/retrier.cc:38] Loading servable: {name: default version: 1} failed: Not found: Session bundle or SavedModel bundle not found at specified export location

对此有何建议?

0 个答案:

没有答案