Name	Name	Last commit message	Last commit date
parent directory ..
README.md	README.md
fine_tune_data_efficient_classifier.ipynb	fine_tune_data_efficient_classifier.ipynb
quick_start_with_hugging_face.ipynb	quick_start_with_hugging_face.ipynb
quick_start_with_model_garden.ipynb	quick_start_with_model_garden.ipynb
simplify_client_code_with_ez_wsi.ipynb	simplify_client_code_with_ez_wsi.ipynb
train_data_efficient_classifier_dicom.ipynb	train_data_efficient_classifier_dicom.ipynb
train_data_efficient_classifier_gcs.ipynb	train_data_efficient_classifier_gcs.ipynb

Name

Last commit message

Last commit date

Path Foundation Notebooks

Quick start with Hugging Face - Example of encoding a pathology image patch into an embedding vector by running the model locally from Hugging Face.
Quick start with Vertex Model Garden - Example of serving the model on Vertex AI and using Vertex AI APIs to encode pathology image patches to embeddings in online or batch workflows.
Train a data efficient classifier - GCS version - Example of using the generated embeddings to train a custom classifier with less data and compute. This version shows how to use the data as files in Cloud Storage (GCS).
Train a data efficient classifier - DICOMWeb version - Example of using the generated embeddings to train a custom classifier with less data and compute. This version shows how to use the data as DICOM objects in Cloud DICOM store.
Simplify client code with EZ-WSI - Instructions how to utilize EZ-WSI DicomWeb library to simplify client side code for working with DICOM data and generating embeddings from a variety of data sources including Cloud DICOM store, GCS, and locally stored files or in-memory data representations.
Fine-tune data efficient classifier Example of fine-tuning the weights of the pathology embedding model to classify pathology image patches as an alternative to a linear classifier.

Provide feedback