TensorboardPlugin3D - 3D Tensor Visualization
Introduction
TensorboardPlugin3D is an open-source Tensorboard plugin that supports visualizing 3D output within the Tensorboard application, JupyterLab, and Google Colab.
Installation
Install the PyPI package:
pip install tensorboard-plugin-3d
MONAI Notebook Examples
The Spleen Segmentation 3D tutorial shows how to integrate MONAI into an existing PyTorch medical DL program and demonstrates using TensorboardPlugin3D to view an image with a label to show the input data (shown in the first image) or to compare the model output with the input.
The UNet Segmentation 3D Ignite notebook provides a simple, fast-running notebook with demo data. If you're looking for a quick way to get started and see the plugin in action this is a great place to start.
The BRATS Segmentation 3D notebook demonstrates brain tumor 3D segmentation with MONAI. The tutorial shows how to construct a training workflow of multi-labels segmentation task.
Documentation
See the documentation for a guide on getting started.