Download and Deploy your DLS trained model on your machine

Download the trained model with deployment code

Once your are done with the training you will be able to download the deployment code. To download , follow the steps below:
  1. 1.
    Go to Inference/Deploy in your project
  2. 2.
    Click on "Download trained model with deployment code"
It will download a zip files which contains the trained model and deployment server packages. Now follow the next section to use the downloaded file.

Deploy your trained model on your local machine.

Make sure that conda installed on your system, if not Installed, Please install conda/Miniconda. Check conda installtion guide for Windows or Linux
  1. 1.
    Extract the downloaded zip file.
  2. 2.
    Launch command prompt(Windows) or terminal(Linux/Ubuntu)
  3. 3.
    change the directory to the extract path
  4. 4.
    Create conda enviroment
    Note : In the older version yaml file name may be different , please use it accordingly
    a) for windows cpu version:
    conda env create -f env_windows_cpu.yaml -n deployment_env
    b) for windows gpu version:
    conda env create -f env_windows_gpu.yaml -n deployment_env
    c) for linux cpu version:
    conda env create -f env_linux_cpu.yaml -n deployment_env
    d) for linux gpu version:
    conda env create -f env_linux_gpu.yaml -n deployment_env
    Note : If you don't find any environment yaml please download it from the one of this link-
  5. 5.
    Activate the environment
    conda activate deployment_env
  6. 6.
    Set the deployment directory
    If you are using terminal or bash:
    export DEPLOY_DIR=./
    If you using windows cmd:
    set DEPLOY_DIR=.\
  7. 7.
    Start the deployment server
    olympus up --no-debug --port 11111 --host &
    olympus deploy --name MNISTHandwrittenDigitsClassifierUsingRNN_Run0_deploy_model --version 1 --framework keras ./model/
  • If you are using any cloud machine/server/instance for the deployment, You need to connect to the ssh and follow the steps 3-6.