Handle None values in _inner_loop tensor conversion

[Copilot]

Change Description

_inner_loop crashes when prepare_inputs returns None values, which occurs in supervised models with missing labels. The function unconditionally calls torch.from_numpy() on all values, including None.

Solution Description

Added None checks before tensor conversion in _inner_loop:

# Before
if isinstance(batch, tuple):
    batch = tuple(torch.from_numpy(i).to(device) for i in batch)
else:
    batch = torch.from_numpy(batch).to(device)

# After  
if isinstance(batch, tuple):
    batch = tuple(torch.from_numpy(i).to(device) if i is not None else None for i in batch)
elif batch is not None:
    batch = torch.from_numpy(batch).to(device)

Added test coverage for tuple with None element, None batch, and regression cases.

Code Quality

• I have read the Contribution Guide and agree to the Code of Conduct
• My code follows the code style of this project
• My code builds (or compiles) cleanly without any errors or warnings
• My code contains relevant comments and necessary documentation

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• www.cs.toronto.edu
  • Triggering command: /usr/bin/python /usr/bin/python -m ipykernel_launcher -f /tmp/tmpu0iebvur.json --HistoryManager.hist_file=:memory: --from without_precedin--columns=500 --to rst --columns=500 pandoc --eo�� lf --from ve_divs+raw_html--columns=500 --to rst --columns=500 pandoc (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>If prepare_data returns a None, pytorch_ignite will error</issue_title>
<issue_description>Bug report
In _inner_loop, when we try to convert numpy to Tensors, if there is a None that is returned from prepare_data, the conversion will fail.

Max ran into this with a supervised model that used a prepare_data function that returns None when there are no labels. Changing this to return an empty array instead of None fixed the problem, but we should be more accommodating.
</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes If prepare_data returns a None, pytorch_ignite will error #688

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.