fix: remove hardcoded CUDA assumptions in ERFNet to support CPU-only execution

[Fahmid-Arman]

What type of PR is this?
/kind bug

What this PR does / why we need it:
The ERFNet training and evaluation utilities contained hardcoded CUDA availability assumptions, causing the pipeline to crash immediately on CPU-only machines and Apple Silicon devices.

• Dynamically assigned self.cuda = torch.cuda.is_available() (and self.no_cuda) within TrainArgs and ValArgs in utils/args.py.
• Refactored checkpoint loading in train.py to use a dynamic map_location supporting CPU fallback.
• Added a missing if self.args.cuda: guard around a target.cuda() call within the training() loop in train.py to match the surrounding tensor handling logic.

This unblocks ERFNet execution for contributors running the benchmark on non-NVIDIA hardware.

Which issue(s) this PR fixes:
Fixes #471

[kubeedge-bot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: Fahmid-Arman
To complete the pull request process, please assign jaypume after the PR has been reviewed.
You can assign the PR to them by writing /assign @jaypume in a comment when ready.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[gemini-code-assist]

Code Review

This pull request dynamically configures CUDA usage based on GPU availability instead of hardcoding it. Key changes include conditional checkpoint loading and tensor GPU transfer in train.py, and initializing CUDA flags dynamically using torch.cuda.is_available() in utils/args.py. The review feedback suggests improving this by using the configured args.gpu_ids instead of hardcoding 'cuda:0' when loading checkpoints, and allowing cuda and no_cuda parameters to be overridden via kwargs in both TrainArgs and ValArgs to prevent conflicting states and support explicit CPU execution.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[Fahmid-Arman]

Feedback addressed:

• Parameterized GPU ID indexing in map_location and added kwargs overrides for cuda and no_cuda flags to prevent state conflicts.

/assign @jaypume