🔥🔥 Evaluate DGCNN Model Weights & Biases 🪄🐝

This notebook demonstrates the evaluation of Dynamic Graph CNN for point cloud segmnetation. You can check the following notebook for referring to the training code:

Install Required Packages

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 ShapeNet Dataset using PyTorch Geometric

We now load, preprocess and batch the ModelNet dataset for training, validation/testing and visualization.

Load Checkpoint

Since we saved the checkpoints as artifacts on our Weights & Biases workspace, we can now fetch and load them.

Evaluation

We evaluate the results and store them in a Weights & Biases Table.