Skip to content

Conversation

@kluge7
Copy link
Contributor

@kluge7 kluge7 commented Oct 26, 2025

  • Removed deprecated files (probably should have been a separate pull request 🤷)
  • Add slurm job

@kluge7 kluge7 linked an issue Oct 26, 2025 that may be closed by this pull request
9 tasks
@kluge7 kluge7 requested a review from Copilot October 26, 2025 18:29
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds training scripts and configurations for running YOLO and U-Net models on the Idun cluster, while restructuring the project to support multiple model training workflows.

Key Changes:

  • Added new training directories with scripts for YOLO and U-Net models
  • Created SLURM job configurations for GPU-based training on the Idun cluster
  • Updated CI/CD workflows to reference the new requirements.txt location

Reviewed Changes

Copilot reviewed 11 out of 13 changed files in this pull request and generated 3 comments.

Show a summary per file
File Description
yolo_roboflow_training/train.py Training script for YOLO model using Roboflow datasets
yolo_roboflow_training/requirements.txt Python dependencies for YOLO training
yolo_roboflow_training/Job.slurm SLURM configuration for YOLO training jobs
unet_roboflow_training/train.py Training script for U-Net segmentation model
unet_roboflow_training/test.py Inference script for testing trained U-Net models
unet_roboflow_training/requirements.txt Python dependencies for U-Net training
unet_roboflow_training/Job.slurm SLURM configuration for U-Net training jobs
YOLO-detect-buoys/requirements.txt Moved requirements file to project directory
YOLO-detect-buoys/main.py Updated to use Unix-style paths and added model export
YOLO-detect-buoys/Job.slurm SLURM configuration for buoy detection training
.github/workflows/pylint.yml Updated to reference new requirements.txt location
Comments suppressed due to low confidence (2)

YOLO-detect-buoys/Job.slurm:1

  • Invalid SLURM time format '999:99:99'. The time format should be DD-HH:MM:SS, HH:MM:SS, or MM:SS with valid values (e.g., hours 0-23, minutes/seconds 0-59).
    YOLO-detect-buoys/Job.slurm:1
  • The script references 'train.py' but the main entry point in this directory is 'main.py'. This should be 'python3 main.py' or 'python3 -m YOLO-detect-buoys'.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@kluge7 kluge7 force-pushed the 13-traning-on-idun branch from f207b2e to 562d266 Compare January 4, 2026 05:17
@kluge7 kluge7 requested review from MadsJJ, Copilot and gardeg January 4, 2026 09:36
@kluge7 kluge7 changed the title Scripts for traning models on idun Scripts for traning yolo object detection Jan 4, 2026
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 17 out of 25 changed files in this pull request and generated 9 comments.


💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

@kluge7 kluge7 self-assigned this Jan 4, 2026
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 17 out of 25 changed files in this pull request and generated 8 comments.


💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 19 out of 29 changed files in this pull request and generated 1 comment.


💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.


print("CUDA version:", torch.version.cuda)
print("cuDNN version:", torch.backends.cudnn.version())
print("Using GPU:", torch.cuda.get_device_name(0))
Copy link

Copilot AI Jan 8, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line 29 calls torch.cuda.get_device_name(0) without checking if GPU 0 exists. If the system has GPUs but not at index 0, or CUDA_VISIBLE_DEVICES is set differently, this could fail with an IndexError. Consider using torch.cuda.get_device_name(DEVICE) or checking the device count first.

Suggested change
print("Using GPU:", torch.cuda.get_device_name(0))
device_count = torch.cuda.device_count()
if isinstance(DEVICE, int) and 0 <= DEVICE < device_count:
print("Using GPU:", torch.cuda.get_device_name(DEVICE))
else:
print("Using CUDA device configuration:", DEVICE)

Copilot uses AI. Check for mistakes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Start the traning on idun

5 participants