Prerequisites
Bazel
Using Bazel custom APT repository (recommended)
- Install JDK 8
- Add Bazel distribution URI as a package source (one time setup)
If you want to install the testing version of Bazel, replace stable with testing.
- Install and update Bazel
Once installed, you can upgrade to a newer version of Bazel with:
gRPC Python
Packages dependencies
TensorFlow Serving Python API PIP package
Installing from source
Clone the TensorFlow Serving repository
–recurse-submodules is required to fetch TensorFlow, gRPC, and other libraries that TensorFlow Serving depends on.
Note that these instructions will install the latest master branch of TensorFlow Serving. If you want to install a specific branch (such as a release branch), pass -b <branchname>
to the git clone command.
Install prerequisites
Follow the Prerequisites section above to install all dependencies. To configure TensorFlow, run
Build
Binaries are placed in the bazel-bin directory, and can be run using a command like:
To test your installation, execute:
Serving a TensorFlow Model
Train And Export TensorFlow Model
- step 0
- step 1
OR
list the model files
Each version sub-directory contains the following files:
- saved_model.pbis the serialized tensorflow::SavedModel. It includes one or more
- graphdefinitions of the model, as well as metadata of the model such as signatures.
variables are files that hold the serialized variables of the graphs.
Load Exported Model With Standard TensorFlow ModelServer
Test The Server
OR
Reference
- tensorflow servering installation
- Bazel-install-ubuntu
- grpc
- gRPC Python
- serving_basic
- mnist