optical_toolkit 0.7.1

An API for streamlining unsupervised ML ops such as visualizations, clustering, CNN insights, etc.

OpticalToolkit

A collection of deep learning -- computer vision utility functions

Installation

pip install optical_toolkit

Visualize

• Visualize a dataset in a grid

• Visualize the 2d and 3d embeddings of images

from sklearn.datasets import load_digits
from optical_toolkit.embeddings import get_embeddings

X, y = load_digits()

2d_embeddings, fig_2d = get_embeddings(X, y, dims=2, embedding_type="tsne", return_plot=True)
3d_embeddings, fig_3d = get_embeddings(X, y, dims=3, embedding_type="tsne", return_plot=True)

Insight

• Visualize the filters of a (trained) CNN model

from optical_toolkit.cnn_filters import display_filters, display_model_filters

model_name = "xception"

layer_names = [
    "block2_sepconv1",
    "block5_sepconv1",
    "block9_sepconv1",
    "block14_sepconv1",
]

for layer_name in layer_names:
    display_filters(
    model=model_name,
    layer_name=layer_name,
)

display_model_filters(model=model_name)

Analyze

• Analyze 'highly confident' errors in classification tasks
  • Confusion matrix normalized by row/column