PyTorch Geometric

PyTorch Geometric (PyG) is a library for geometric deep learning, and Weights & Biases works with it for visualizing graphs and tracking experiments. This guide shows you how to authenticate to Weights & Biases, install the wandb library, visualize PyG graphs with PyVis or Plotly, and log training metrics from your PyG workflows. Use it to track experiments and share graph visualizations in Weights & Biases. After you install PyTorch Geometric, follow these steps to get started. An API key authenticates your machine to Weights & Biases. You can generate an API key from your user profile.

For a more streamlined approach, go to User settings and create an API key. Copy the API key immediately and save it in a secure location such as a password manager.

Click the account selector in the upper-right corner.
Select User settings, then scroll to the API keys section.

Install the `wandb` library and log in

To install the wandb library locally and log in:

Command Line
Python
Python notebook

Set the WANDB_API_KEY environment variable to your API key. Replace values enclosed in <> with your own:
export WANDB_API_KEY=<your_api_key>
Install the wandb library and log in.
pip install wandb wandb login

pip install wandb

import wandb
wandb.login()

!pip install wandb

import wandb
wandb.login()

Visualize the graphs

After you log in, you can begin sending graph visualizations and run data to Weights & Biases. You can save details about the input graphs, including number of edges, number of nodes, and more. Weights & Biases supports logging Plotly charts and HTML panels, so you can also log any visualizations you create for your graph to Weights & Biases. The following sections show two common approaches: PyVis for interactive HTML visualizations and Plotly for chart-based visualizations.

Use PyVis

The following snippet shows how to do that with PyVis and HTML.

from pyvis.network import Network
import wandb

with wandb.init(project="graph_vis") as run:
    net = Network(height="750px", width="100%", bgcolor="#222222", font_color="white")

    # Add the edges from the PyG graph to the PyVis network
    for e in tqdm(g.edge_index.T):
        src = e[0].item()
        dst = e[1].item()

        net.add_node(dst)
        net.add_node(src)
        
        net.add_edge(src, dst, value=0.1)

    # Save the PyVis visualisation to a HTML file
    net.show("graph.html")
    run.log({"eda/graph": wandb.Html("graph.html")})

Use Plotly

To use Plotly to create a graph visualization, first convert the PyG graph to a networkx object. Then create Plotly scatter plots for both nodes and edges. Use the following snippet for this task.

def create_vis(graph):
    G = to_networkx(graph)
    pos = nx.spring_layout(G)

    edge_x = []
    edge_y = []
    for edge in G.edges():
        x0, y0 = pos[edge[0]]
        x1, y1 = pos[edge[1]]
        edge_x.append(x0)
        edge_x.append(x1)
        edge_x.append(None)
        edge_y.append(y0)
        edge_y.append(y1)
        edge_y.append(None)

    edge_trace = go.Scatter(
        x=edge_x, y=edge_y,
        line=dict(width=0.5, color='#888'),
        hoverinfo='none',
        mode='lines'
    )

    node_x = []
    node_y = []
    for node in G.nodes():
        x, y = pos[node]
        node_x.append(x)
        node_y.append(y)

    node_trace = go.Scatter(
        x=node_x, y=node_y,
        mode='markers',
        hoverinfo='text',
        line_width=2
    )

    fig = go.Figure(data=[edge_trace, node_trace], layout=go.Layout())

    return fig


with wandb.init(project="visualize_graph") as run:
    run.log({"graph": wandb.Plotly(create_vis(graph))})

A visualization created using the example function and logged inside a W&B Table.

Log metrics

In addition to graph visualizations, you can use Weights & Biases to track your experiments and related metrics, such as loss functions, accuracy, and more. Add the following lines to your training loop:

with wandb.init(project="my_project", entity="my_entity") as run:
    run.log({
        'train/loss': training_loss,
        'train/acc': training_acc,
        'val/loss': validation_loss,
        'val/acc': validation_acc
        })

With graph visualizations and training metrics logged to Weights & Biases, you can compare runs and share results from your PyG experiments in your Weights & Biases workspace.

More resources

The following W&B reports show PyG in action:

Weights & Biases

Guides

Integrations

Reference

Support

Install the `wandb` library and log in

Visualize the graphs

Use PyVis

Use Plotly

Log metrics

More resources

​Sign up and create an API key

​Install the wandb library and log in

​Visualize the graphs

​Use PyVis

​Use Plotly

​Log metrics

​More resources

Sign up and create an API key

Install the `wandb` library and log in

Visualize the graphs

Use PyVis

Use Plotly

Log metrics

More resources