shamshad / deep-fake-detection-challenge

Facebook's Deep Fake Detection Challenge on Kaggle with AWS

Kaggle Competition

Train Your Model with AWS

Step 1: Create and Activate Your AWS Account

• https://aws.amazon.com/premiumsupport/knowledge-center/create-and-activate-aws-account/

Step 2: Apply Your AWS Credits (If Applicable)

• https://aws.amazon.com/awscredits/

Step 3: Create an S3 Bucket

• How to Create an S3 Bucket

Step 4: Choose a Region

• Review the Regions supported by Amazon SageMaker

Step 5: Manage/Increase SageMaker Instance Limits (see detailed instructions here)

• Review the Default Limits for Amazon SageMaker Service Limits
• Request a Limit Increase if needed via the AWS Support Center
• Review the SageMaker Instance Pricing for an overview of supported instance types

Step 6: Create a SageMaker Notebook Instance

• Select an Instance Type
• Select “Create a New IAM Role”
• Select the S3 Bucket Created Above
• Select “Jupyter” or “JupyterLab” to Launch the Notebook
• Connect to a Public or Private GitHub or GitLab repo using these instructions.

Step 7: Clone this GitHub Repo

• Open a New Terminal ()

• Clone this Repo using the Following Command

cd ~/SageMaker

git clone https://github.com/data-science-on-aws/deep-fake-detection-challenge

Step 8: Train a Model Using Your SageMaker Notebook Instance

• Sample TensorFlow Notebook using Distributed TensorFlow and SageMaker.
• Sample PyTorch Notebook using Distributed PyTorch and SageMaker.
• Sample MXNet Notebook using Distributed MXNet and SageMaker.
• To adapt a custom training script to SageMaker, please follow these instructions.

Step 9: Submit Your Trained Model to Kaggle

• Competition Code Requirements

More Resources

• Kaggle Challenge Introduction
• Deepfake Starter Kit
• Competition Code Requirements