RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation.

[JoaoMoranguinho]

When running the default Google Colab notebook a "RuntimeError: a view of a leaf Variable that requires grad is being used in an in-place operation." message is generated in the training phase of the model.

As I understand this issue is generated in the initialize_biases function in /models/yolo.py (line 150).

with torch.no_grad(): seems to solve this problem.

I don't know if this was a recent change in versioning or if it was a problem in my specific case.

If any other solutions arise please be sure to share them.

[github-actions]

👋 Hello @JoaoMoranguinho, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@JoaoMoranguinho I think this was resolved a long time ago in master. Are you using the official colab notebook here?
https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb

If you are using the latest master code and the notebook above and still see a reproducible issue, we suggest you close this issue and raise a new one using the 🐛 Bug Report template, providing screenshots and a minimum reproducible example to help us better understand and diagnose your problem. Thank you!

[AmulPatil]

Was facing same issue. its resolved by removing below command from roboflow version of colab script
!git reset --hard 68211f7

[glenn-jocher]

@AmulPatil @JoaoMoranguinho we do not support 3rd party training tools.

I would highly recommend using the official Colab notebook, which works correctly and is always up to date with the latest YOLOv5 version.
https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb