Flagged nnUNet Runner Command Construction Issue

[ericspod]

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

🧩 Analysis chain

🌐 Web query:

nnUNetv2_train argparse flags store_true --c --val --use_compressed --disable_checkpointing

💡 Result:

In nnU-Net v2, the command line utility nnUNetv2_train utilizes several argparse flags to control the training and validation process. These flags are implemented as store_true options, meaning they do not require an associated value and serve as toggles [1][2]. The requested flags perform the following functions: --c (Continue training): This flag instructs the trainer to resume training from the most recent checkpoint. It is essential if a training run was interrupted or if you wish to extend a previously stopped training session [2]. --val (Validation only): This flag sets the trainer to skip the training process and instead run only the final validation on the specified fold [2][3]. This is often used after a training run has completed or to re-run validation without re-training [4][3]. --use_compressed: This flag directs the system to use compressed data during training. By default, nnU-Net may decompress data; enabling this flag prevents decompression. It is noted that reading compressed data is significantly more CPU and potentially RAM intensive, and it should only be used when necessary [2]. --disable_checkpointing: This flag disables the saving of model checkpoints during training. This is useful in scenarios where you are testing a configuration or running quick experiments and do not want to consume disk space with multiple large model checkpoint files [2]. In addition to these, the --npz flag is frequently used alongside these commands. Although not explicitly in your list, it is critical to note that --npz is required if you intend to use nnUNetv2_find_best_configuration later, as it forces the model to save the softmax probabilities from the final validation, which are necessary for ensemble creation and model selection [4][3].

Citations:

• 1: nnUNetv2 parser plus MIC-DKFZ/nnUNet#1543
• 2: https://hackmd.io/n2NJtLqVT1iITYIBpzCLXA
• 3: https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/how-to/train-models.md
• 4: https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/how_to_use_nnunet.md

---

Fix argv construction for store_true kwargs (e.g., --c, --val) in monai/apps/nnunet/nnunetv2_runner.py (lines 585-605): the kwargs loop always appends str(_value), so documented boolean flags (c, val, use_compressed, disable_checkpointing) become --c True / --val True instead of being emitted as bare flags (the same pattern as the special-case --npz). Update the builder to emit --<flag> only when the value is True and omit the flag when False (and similarly only include pretrained_weights when it’s a real path, not False).

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@monai/apps/nnunet/nnunetv2_runner.py` around lines 585 - 605, The argv
builder in the kwargs loop currently always appends str(_value), causing
store_true options to appear as "--flag True" instead of a bare "--flag" and
including false/empty pretrained_weights; update the loop in nnunetv2_runner.py
where cmd is assembled so that for boolean flags (e.g., keys "c", "val",
"use_compressed", "disable_checkpointing" and any other store_true options) you
only append the flag name (prefix + _key) when _value is True and skip it when
False, and for "pretrained_weights" (or "-p") only append the option and its
value when _value is truthy (a non-empty path); keep the existing prefix
selection logic for short vs long options and continue converting items to
strings later.

Originally posted by @coderabbitai[bot] in #8887 (comment)