Deepdrive docs
  • Deepdrive
  • vendor
    • openai
      • README
        • PPO2
        • A2C
    • tensorflow
      • Surgically extracted MobileNetV2 from tensorflow/models @ 84da970ee43c04fbd53a1db3c824ea32cec8936b
        • TensorFlow Research Models
          • slim
            • nets
              • README
          • Running the TensorFlow Official ResNet with TensorRT
  • Deepdrive
  • docs
    • tutorial
      • cloud
        • Cloud setup
      • uepy
        • UnrealEnginePython Tutorial
      • leaderboard
        • Submitting to the Deepdrive leaderboard
    • Miniconda
  • README
Powered by GitBook
On this page
  • Miniconda
  • Clone
  • Run

Was this helpful?

  1. docs
  2. tutorial
  3. cloud

Cloud setup

PreviouscloudNextuepy

Last updated 5 years ago

Was this helpful?

We've tested on Paperspace's ML-in-a-Box Linux public template with a P6000 which already has Tensorflow installed and just requires

To set it up choose your region, then go to Public Templates, and choose the ML-in-a-Box template

Paperspace

Miniconda

Now run the Miniconda installer

bash Miniconda3-latest-Linux-x86_64.sh

Next, create a conda env for deepdrive

bash # to get conda in your shell
conda create -n dd python=3.7
conda activate dd

Clone

Now clone our repo

git clone https://github.com/deepdrive/deepdrive

Run

And finally run the install

cd deepdrive
python install.py

You can validate everything is working by running

python example.py

If you run into issues, try starting the sim directly as Unreal may need to install some prerequisetes (i.e. DirectX needs to be installed on the Paperspace Parsec Windows box). The default location of the Unreal sim binary is in your user directory under Deepdrive/deepdrive-sim*/DeepDrive/Binaries/Linux/DeepDrive, i.e.

/home/YOURUSERNAME/Deepdrive/deepdrive-sim-linux-3.1.20191112232556/DeepDrive/Binaries/Linux/DeepDrive

Then download the 64-bit Linux installer from or click

You can continue testing things out by running the rest of our examples

Miniconda
here
here