Amazon AMI images and Docker are the easiest way to go. Both contain a ready to go deepdetect server as well as pre-trained googlenet, resnet_50 image classification models and many others for the AMIs. This allows to spin up an image classification service in minutes on a variety of machines with both CPU and GPU support.

Amazon AMI images

If your target is Amazon AWS, we recommend you take a look at our official GPU AMI or CPU AMI.

These images come pre-built with support for Caffe, Tensorflow and XGBoost, along with a set of more than twenty pre-trained neural network models for image and text classification.

Full instructions are available from our AMI product page.

Docker images

Pre-built docker images for both CPU and GPU machines are available from https://hub.docker.com/u/beniz/

Docker images are the way to get started very quickly:

docker pull deepdetect_cpu
docker run -d -p 8080:8080 beniz/deepdetect_cpu

Check that dede server is listening properly:

curl http://localhost:8080/info
{
  "status":{
    "code":200,
    "msg":"OK"
  },
  "head":{
    "method":"/info",
    "version":"0.1",
    "branch":"master",
    "commit":"c8556f0b3e7d970bcd9861b910f9eae87cfd4b0c",
    "services":[]
  }
}

Full instructions are available from https://github.com/beniz/deepdetect/blob/master/docker/README.md


DeepDetect documentation