Tensorflow CPU Inference API For Windows and Linux

This is a repository for an object detection inference API using the Tensorflow framework.

This repo is based on Tensorflow Object Detection API.

The Tensorflow version used is 1.13.1. The inference REST API works on CPU and doesn't require any GPU usage. It's supported on both Windows and Linux Operating systems.

Models trained using our training tensorflow repository can be deployed in this API. Several object detection models can be loaded and used at the same time.

predict image

Prerequisites

Check for prerequisites

To check if you have docker-ce installed:

docker --version

Install prerequisites

Ubuntu

Use the following command to install docker on Ubuntu:

chmod +x install_prerequisites.sh && source install_prerequisites.sh

Windows 10

To install Docker on Windows, please follow the link.

P.S: For Windows users, open the Docker Desktop menu by clicking the Docker Icon in the Notifications area. Select Settings, and then Advanced tab to adjust the resources available to Docker Engine.

Build The Docker Image

In order to build the project run the following command from the project's root directory:

sudo docker build -t tensorflow_inference_api_cpu -f docker/dockerfile .

Behind a proxy

sudo docker build --build-arg http_proxy='' --build-arg https_proxy='' -t tensorflow_inference_api_cpu -f ./docker/dockerfile .

Run the docker container

To run the API, go the to the API's directory and run the following:

Using Linux based docker:

sudo docker run -itv $(pwd)/models:/models -p <docker_host_port>:4343 tensorflow_inference_api_cpu

Using Windows based docker:

docker run -itv ${PWD}/models:/models -p <docker_host_port>:4343 tensorflow_inference_api_cpu

The can be any unique port of your choice.

The API file will be run automatically, and the service will listen to http requests on the chosen port.

API Endpoints

To see all available endpoints, open your favorite browser and navigate to:

http://<machine_IP>:<docker_host_port>/docs

The 'predict_batch' endpoint is not shown on swagger. The list of files input is not yet supported.

P.S: If you are using custom endpoints like /load, /detect, and /get_labels, you should always use the /load endpoint first and then use /detect or /get_labels

Endpoints summary

/load (GET)

Loads all available models and returns every model with it's hashed value. Loaded models are stored and aren't loaded again

load model

/detect (POST)

Performs inference on specified model, image, and returns bounding-boxes

detect image

/get_labels (POST)

Returns all of the specified model labels with their hashed values

get model labels

/models/{model_name}/predict_image (POST)

Performs inference on specified model, image, draws bounding boxes on the image, and returns the actual image as response

predict image

/models (GET)

Lists all available models

/models/{model_name}/load (GET)

Loads the specified model. Loaded models are stored and aren't loaded again

/models/{model_name}/predict (POST)

Performs inference on specified model, image, and returns bounding boxes.

/models/{model_name}/labels (GET)

Returns all of the specified model labels

/models/{model_name}/config (GET)

Returns the specified model's configuration

/models/{model_name}/predict_batch (POST)

Performs inference on specified model and a list of images, and returns bounding boxes

P.S: Custom endpoints like /load, /detect, and /get_labels should be used in a chronological order. First you have to call /load, and then call /detect or /get_labels

Model structure

The folder "models" contains subfolders of all the models to be loaded. Inside each subfolder there should be a:

Benchmarking

Windows Ubuntu
Network\Hardware Intel Xeon CPU 2.3 GHz Intel Xeon CPU 2.3 GHz Intel Xeon CPU 3.60 GHz GeForce GTX 1080
ssd_fpn 0.867 seconds/image 1.016 seconds/image 0.434 seconds/image 0.0658 seconds/image
frcnn_resnet_50 4.029 seconds/image 4.219 seconds/image 1.994 seconds/image 0.148 seconds/image
ssd_mobilenet 0.055 seconds/image 0.106 seconds/image 0.051 seconds/image 0.052 seconds/image
frcnn_resnet_101 4.469 seconds/image 4.985 seconds/image 2.254 seconds/image 0.364 seconds/image
ssd_resnet_50 1.34 seconds/image 1.462 seconds/image 0.668 seconds/image 0.091 seconds/image
ssd_inception 0.094 seconds/image 0.15 seconds/image 0.074 seconds/image 0.0513 seconds/image

Acknowledgment

inmind.ai

robotron.de

Joe Sleiman, inmind.ai , Beirut, Lebanon

Antoine Charbel, inmind.ai, Beirut, Lebanon