model_garden/notebooks/official/prediction

Custom model batch prediction with feature filtering

Learn how to create a custom-trained model from a Python script in a Docker container using the Vertex AI SDK for Python, and then run a batch prediction job by including or excluding a list of features.

The steps performed include:

- Create a Vertex AI custom `TrainingPipeline` for training a model.
- Train a TensorFlow model.
- Send batch prediction job.

   Learn more about Vertex AI Batch Prediction.

Serving PyTorch image models with prebuilt containers on Vertex AI

Learn how to package and deploy a PyTorch image classification model using a prebuilt Vertex AI container with TorchServe for serving online and batch predictions.

The steps performed include:

- Download a pretrained image model from PyTorch
- Create a custom model handler
- Package model artifacts in a model archive file
- Upload model for deployment
- Deploy model for prediction
- Make online predictions
- Make batch predictions

   Learn more about Pre-built containers for prediction.

Train and deploy PyTorch models with prebuilt containers on Vertex AI

Learn how to build, train and deploy a PyTorch image classification model using prebuilt containers for custom training and prediction.

The steps performed include:

- Package training application into a Python source distribution
- Configure and run training job in a prebuilt container
- Package model artifacts in a model archive file
- Upload model for deployment
- Deploy model using a prebuilt container for prediction
- Make online predictions