Tutorial

Interactive Tutorials

For interactive notebooks that demonstrate how to use leap-ie, visit the Google Colab notebooks below:

Quick Start:

An intro to the leap-ie library and how to generate Prototypes and Isolations.

Google Colaboratory

Interactive Prototype Playground:

An easy to use interactive playground allowing you to generate prototypes for any torchvision model.

Google Colaboratory

Tutorial:

An in-depth tutorial demonstrating all of the features and integrations of leap-ie.

Google Colaboratory

Tank Detection Case Study

A short case study demonstrating how leap-ie makes it possible to identify and fix dangerous biases in the model, and enables real-time understanding of model learning during training to facilitate hyperparameter selection.

Google Colaboratory

Prototype Generation

Given your model, we generate prototypes and entanglements We also isolate entangled features in your prototypes.

from leap_ie.vision import engine
from leap_ie.vision.models import get_model

config = {"leap_api_key": "YOUR_LEAP_API_KEY"}

# Replace this model with your own, or explore any imagenet classifier from torchvision (https://pytorch.org/vision/stable/models.html).
preprocessing_fn, model, class_list = get_model("resnet18", source="torchvision")

# indexes of classes to generate prototypes for. In this case, ['tench', 'goldfish', 'great white shark'].
target_classes = [0, 1, 2]

# generate prototypes
df_results, dict_results = engine.generate(
    project_name="resnet18",
    model=model,
    class_list=class_list,
    config=config,
    target_classes=target_classes,
    preprocessing=preprocessing_fn,
    samples=None,
    device=None,
    mode="pt",
)

# For the best experience, head to https://app.leap-labs.com/ to explore your prototypes and feature isolations in the browser!
# Or, if you're in a jupyter notebook, you can display your results inline:
engine.display_df(df_results)

Sample Feature Isolation

Given some input image, we can show you which features your model thinks belong to each class. If you specify target classes, we'll isolate features for those, or if not, we'll isolate features for the three highest probability classes.

from torchvision import transforms
from leap_ie.vision import engine
from leap_ie.vision.models import get_model
from PIL import Image

config = {"leap_api_key": "YOUR_LEAP_API_KEY"}

# Replace this model with your own, or explore any imagenet classifier from torchvision (https://pytorch.org/vision/stable/models.html).
preprocessing_fn, model, class_list = get_model("resnet18", source="torchvision")

# load an image
image_path = "tools.jpeg"
tt = transforms.ToTensor()
image = preprocessing_fn[0](tt(Image.open(image_path)).unsqueeze(0))

# to isolate features:
df_results, dict_results = engine.generate(
    project_name="resnet18",
    model=model,
    class_list=class_list,
    config=config,
    target_classes=None,
    preprocessing=preprocessing_fn,
    samples=image,
    mode="pt",
)

# For the best experience, head to https://app.leap-labs.com/ to explore your prototypes and feature isolations in the browser!
# Or, if you're in a jupyter notebook, you can display your results inline:
engine.display_df(df_results)