simple_tensorflow_serving

(★ 757)

Generic and easy-to-use serving service for machine learning models

File Explorer

Download Latest Version (.zip)

- - 0.jpg
  - benchmark_grpc_client.py
  - benchmark_http_client.py
  - benchmark_http_client_batch.py
  - data.json
  - data_for_tensorflow_serving.json
- - benchmark_grpc_client.py
  - benchmark_http_client.py
  - benchmark_http_client_batch.py
  - data.json
  - data_for_tensorflow_serving.json
  - run_ab_benchmark.sh
- - benchmark_grpc_client.py
  - benchmark_http_client.py
  - data.json
  - data_for_tensorflow_serving.json
  - tensorflow_template_application_data.json
  - tensorflow_template_application_data_for_tensorflow_serving.json
- - .gitkeeper
- benchmark_simplest_client.py
- benchmark_template_client.py
- README.md
- start_client.sh
- start_servers.sh
- check.py
- - 1.jpg
  - auth_client.sh
  - client.sh
  - image_client.sh
  - README.md
- - README.md
  - WORKSPACE
- - client.erl
  - README.md
- - client.go
  - README.md
- - README.md
- - README.md
- - client.js
  - README.md
- - README.md
- - client.lua
  - README.md
- - client.pl
  - README.md
- - client.php
  - README.md
- - auth_client.py
  - client.py
  - estimator_client.py
  - h2o_prostate_client.py
  - image_client.py
  - mllib_lr_client.py
  - mxnet_mlp_client.py
  - onnx_mnist_client.py
  - pmml_iris_client.py
  - prostate_test_data.json
  - README.md
  - requirements.txt
  - scikitlearn_iris_client.py
  - simplest_client.py
  - xgboost_iris_client.py
- - client.R
  - README.md
- - client.rb
  - README.md
- - README.md
- - README.md
- - client.swift
  - README.md
- - advanced_usage.md
  - api.md
  - clients.md
  - conf.py
  - development.md
  - image_model.md
  - index.rst
  - installation.md
  - introduction.md
  - models.md
  - performance.md
  - quick_start.md
- make.bat
- Makefile
- - build_custom_op.sh
  - README.md
  - train.py
  - zero_out.cc
- model_config_file.json
- one_tensorflow_model.json
- tensorflow_gpu_session_config.json
- tensorflow_mxnet_models.json
- architecture.jpeg
- benchmark_batch_size.jpeg
- benchmark_concurrency.jpeg
- benchmark_latency.jpeg
- cpu_gpu_benchmark.png
- dashboard.png
- dashboard_multiple_models.png
- gen_python_code.png
- image_inference.png
- mew.jpg
- mew_224_224.jpg
- postman.png
- savedmodel_files.png
- simple_tensorflow_serving_introduction.jpeg
- - GLM_model_python_1525255083960_17
- - mx_mlp-0001.params
  - mx_mlp-signature.json
  - mx_mlp-symbol.json
- - onnx_model.proto
- - DecisionTreeIris.pmml
- - model.joblib
  - model.pkl
  - postprocess_function.marshal
  - preprocess_function.marshal
- - model.bst
  - model.joblib
  - model.pkl
- README.md
- - __init__.py
  - gen_bash.py
  - gen_client.py
  - gen_golang.py
  - gen_javascript.py
  - gen_python.py
- - __init__.py
  - request_util.py
- - footer.html
  - generate_clients.html
  - header.html
  - image_inference.html
  - index.html
  - json_inference.html
- __init__.py
- abstract_inference_service.py
- base64_util.py
- base64_util_test.py
- BUILD
- command.py
- filesystem_util.py
- h2o_inference_service.py
- manager.py
- mxnet_inference_service.py
- onnx_inference_service.py
- pmml_inference_service.py
- preprocess_util.py
- python_predict_client.py
- pytorch_onnx_inference_service.py
- README.md
- scikitlearn_inference_service.py
- server.py
- spark_inference_service.py
- tensorflow_inference_service.py
- xgboost_inference_service.py
- - README.md
- - openscoring-server-executable-1.4-SNAPSHOT.jar
- - generate_python.sh
  - generate_python_client.sh
- - load_lr_model.py
- - http_client.py
  - http_deploy_model.py
  - pmml_sdk_client.py
- - README.md
- - convert_estimator_savedmodel.py
  - data.txt
  - generate_estimator_string.py
  - local_inference.py
  - README.md
- - python_client.py
  - python_grpc_client.py
  - README.md
- check_model.py
- local_inference.py
.dockerignore
.gitignore
docker-compose.yml
Dockerfile
Dockerfile.latest-gpu
Dockerfile.latest-hdfs
Dockerfile.latest-py34
Dockerfile.latest-py37
LICENSE
MANIFEST.in
README.md
requirements-gpu.txt
requirements-rtfd.txt
requirements.txt
setup.py
simple_tensorflow_serving.yaml
WORKSPACE
wsgi.py

🚀 Installation Guide

1. Get the code

git clone https://github.com/tobegit3hub/simple_tensorflow_serving

Downloads the entire project code from GitHub to your computer.

cd simple_tensorflow_serving

Moves into the project folder you just downloaded.

2. Official Install Script

Easy Recommended

Prerequisites

Python 3 Python is required to use pip.

pip install simple_tensorflow_serving

Installs the package published on PyPI directly — no need to clone the source.

✅ After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.

Pulled directly from this repo's README.

3. Docker

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Docker Desktop Needed to build and run containers. Install it and keep it running in the background.

docker run -d -p 8500:8500 tobegit3hub/simple_tensorflow_serving

Runs the built image as an actual container.

docker run -d -p 8500:8500 tobegit3hub/simple_tensorflow_serving:latest-gpu

Runs the built image as an actual container.

docker run -d -p 8500:8500 tobegit3hub/simple_tensorflow_serving:latest-hdfs

Runs the built image as an actual container.

docker run -d -p 8500:8500 tobegit3hub/simple_tensorflow_serving:latest-py34

Runs the built image as an actual container.

docker-compose up -d

Runs the command against the services defined in the compose file.

✅ Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.

Pulled directly from this repo's README.

4. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install simple_tensorflow_serving

Installs the package published on PyPI directly — no need to clone the source.

✅ If it runs without errors and prints output in the terminal, it worked.

Pulled directly from this repo's README.

5. Make

Medium

Prerequisites

Git Needed to download the project code from GitHub.
Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).

cd docs

This project's files live in a subfolder, so move into it first.

make

Compiles the code based on the generated build configuration to produce an executable.

✅ If it finishes without errors, it worked. Try running the generated executable directly.