Improving the JKNET example.

[drivanov]

Description

Elimination of the UserWarning:

/usr/local/lib/python3.10/dist-packages/torch/nn/modules/rnn.py:881: UserWarning: RNN module weights are not part of single contiguous chunk of memory. This means they need to be compacted at every call, possibly greatly increasing memory usage. To compact weights again call flatten_parameters(). (Triggered internally at /opt/pytorch/pytorch/aten/src/ATen/native/cudnn/RNN.cpp:982.)

by using flatten_parameters() call for lstm mode.

Checklist

Please feel free to remove inapplicable items for your PR.

• I've leverage the tools to beautify the python and c++ code.
• The PR is complete and small, read the Google eng practice (CL equals to PR) to understand more about small PR. In DGL, we consider PRs with less than 200 lines of core code change are small (example, test and documentation could be exempted).
• To the best of my knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

[dgl-bot]

Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:

• @dgl-bot

[dgl-bot]

Commit ID: 4bc47b75d12f7dc4220e60a25085a1d63d8eda45

Build ID: 1

Status: ❌ CI test failed in Stage [Authentication].

Report path: link

Full logs path: link