Comment on page
If, for some reason, your computer doesn't meet the requirements, hardware (no GPU) or software (no CUDA or nvidia-docker), there is a quick way to try training & inference with Supervisely on Amazon EC2.
If you have an account on EC2, deploying Supervisely agent is easy as one-two-three:
Select EC2, open "Instances" section and click "Launch Instance" button.
Search for "Deep Learning AMI". You will see a bunch of out-of-the-box images that have Docker and CUDA installed - exactly what we are looking for. We suggest to use "Deep Learning AMI (Amazon Linux 2)". Click "Select" button.
On a next step select "GPU compute" filter and select "p3.*" instance type. We suggest using "p3.2xlarge".
Different AMIs need different storage — i.e. "Deep Learning AMI (Ubuntu)" comes with Anaconda and multiple versions of CUDA so it's 100 Gb of already taken space. We suggest to configure at least 200 Gb volume size, because agent will download pretty large docker images. You can also attach additional EBS volume and create a symlink to
~/.supervisely-agent- this is where your model weights and images will be stored.
Click "Review and Launch" to start your instance.
You can always stop your instance when you don't need your GPU resources to save money and start it again later. Supervisely agent should run automatically on instance startup.