Challenge: Build Simple VAE
In this challenge, you'll build and train a variational autoencoder (VAE) on the MNIST dataset — step by step. You'll define the architecture, implement the reparameterization trick, create the custom loss, and run the full training process.
To make your experience smoother, you can choose one of the following options to work with the code:
- Download the notebook and run it locally in your favorite environment (e.g., VSCode, Jupyter, PyCharm);
- Open in Google Colab - just one click and everything is ready to run online.
Once you open the notebook, you'll see a series of tasks. Each task includes:
- Clear instructions;
- Code with blanks to fill in;
- Checkers that verify your solution.
When your implementation is correct, the checker will display a short key. Collect all the keys from every step — you'll need them at the end.
Merci pour vos commentaires !
Demandez à l'IA
Demandez à l'IA
Posez n'importe quelle question ou essayez l'une des questions suggérées pour commencer notre discussion
Awesome!
Completion rate improved to 4.76Challenge: Build Simple VAE
Glissez pour afficher le menu
In this challenge, you'll build and train a variational autoencoder (VAE) on the MNIST dataset — step by step. You'll define the architecture, implement the reparameterization trick, create the custom loss, and run the full training process.
To make your experience smoother, you can choose one of the following options to work with the code:
- Download the notebook and run it locally in your favorite environment (e.g., VSCode, Jupyter, PyCharm);
- Open in Google Colab - just one click and everything is ready to run online.
Once you open the notebook, you'll see a series of tasks. Each task includes:
- Clear instructions;
- Code with blanks to fill in;
- Checkers that verify your solution.
When your implementation is correct, the checker will display a short key. Collect all the keys from every step — you'll need them at the end.
Merci pour vos commentaires !
