如何使用 tensorflow-serving 为模型提供服务，如果有 tf.contrib 操作。我通过 Docker(最新)(tf 1.11 版本)使用 Tensorflow Serving，当我提供模型时，会出现下一条消息:
“Failed to start server. Error: Unknown: 1 servable(s) did not become available: {{{name: slider_universal version: 1} due to error: Not found: Op type not registered ‘ImageProjectiveTransformV2’ in binary running on 254345a5d9f1. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) tf.contrib.resampler should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.}, }”
我也是用bazel构建的，但是出现了同样的错误
我使用 tf.contrib.image.transform
如果我在导出模型时删除这个操作，它可以由 tensorflow serving 提供服务
请您参考如下方法:
我在使用相同的操作时遇到了问题，似乎唯一的方法就是构建它。
tensorflow_serving/model_servers/BUILD 定义哪些 Tensorflow ops 将包含在变量 SUPPORTED_TENSORFLOW_OPS 中，我对此有点困惑，因为它指定应包含 contrib ops .但是，由于 tensorflow contrib 构建规则似乎不包含 contrib.image 下的操作，因此我通过将此变量更新为以下内容来明确添加这些操作
SUPPORTED_TENSORFLOW_OPS = [
"@org_tensorflow//tensorflow/contrib:contrib_kernels",
"@org_tensorflow//tensorflow/contrib:contrib_ops_op_lib",
"@org_tensorflow//tensorflow/contrib/image:image_ops_kernels",
"@org_tensorflow//tensorflow/contrib/image:image_ops_op_lib",
]
