🔥🔥 Explore ModelNet Datasets using PyTorch Geometric and Weights & Biases 🪄🐝

Install Required Libraries

We now install PyTorch Geometric according to our PyTorch Version. We also install Weights & Biases.

Import Libraries

Initialize Weights & Biases

We need to call wandb.init() once at the beginning of our program to initialize a new job. This creates a new run in W&B and launches a background process to sync data.

Load ModelNet Dataset using PyTorch Geometric

Log Data to wandb.Table

We now log the dataset using a Weights & Biases Table, which includes visualizing the individual point clouds as W&B's interactive 3D visualization format wandb.object3D. We also log the frequency distribution of the classes in the dataset using wandb.plot.

Next, you can check out the following notebook to learn how to compare different sampling strategies in PyTorch Geometric using Weights & Biases