This repository contains the solution files for the Jittor warmup task on
Cora node classification.
Task
Train a GCN model with Jittor and JittorGeometric on the Cora citation graph,
then predict the labels of test nodes. The required submission files are:
gcn.py: model definition, training, validation, and prediction script
The script reads the pickle data, trains several GCN runs, selects the best
validation run, and writes test-node predictions in the required JSON format.
Result
result.json contains 1000 predictions for node ids 1708 to 2707, with
class ids from 0 to 6.
Notes
The official data/cora.pkl file is not included in this repository. It should
be provided by the contest package.
Jittor_warmup
This repository contains the solution files for the Jittor warmup task on Cora node classification.
Task
Train a GCN model with Jittor and JittorGeometric on the Cora citation graph, then predict the labels of test nodes. The required submission files are:
gcn.py: model definition, training, validation, and prediction scriptresult.json: predicted labels for test nodesFiles
Usage
Place the official contest data at
data/cora.pkl, then run:The script reads the pickle data, trains several GCN runs, selects the best validation run, and writes test-node predictions in the required JSON format.
Result
result.jsoncontains 1000 predictions for node ids1708to2707, with class ids from0to6.Notes
The official
data/cora.pklfile is not included in this repository. It should be provided by the contest package.