pyg-team/pytorch_geometric

Provide a helper for easier batching

Open

#70 opened on Jan 10, 2019

View on GitHub
 (4 comments) (0 reactions) (0 assignees)Python (3,514 forks)batch import
2 - Priority P2featurehelp wantedloader

Repository metrics

Stars
 (19,985 stars)
PR merge metrics
 (Avg merge 35d 1h) (14 merged PRs in 30d)

Description

DataLoader are handy in some situations however they do not cover all potential use cases. For now, I only found the following way of handling batches without them. Would it be possible to have a nice helper in native torch for this?

def forward(self, x, edge_index):
        batch_size, n_size = x.shape[:2]
        batch = [torch_geometric.data.Data(x=t, edge_index=edge_index) for t in x]
        batch = torch_geometric.data.Batch.from_data_list(batch)
        x = self.net(batch.x, batch.edge_index).view(batch_size, n_size, 1)
        return x

Contributor guide

Research direction
Investigate the existing batching mechanisms in PyTorch Geometric (e.g., DataLoader, Batch.from data list) and propose a helper function that simplifies the pattern shown in the issue.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonPyTorchGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80