AttributeError: 'Tensor' object has no attribute 'tensor_split'

[1JAEWOOCHOI1]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

train.py을 사용하는 중
AttributeError: 'Tensor' object has no attribute 'tensor_split'
문제가 발생했습니다.
하지만 이것을 해결할 실력이 되질 않습니다

Additional

No response

[github-actions]

👋 Hello @1JAEWOOCHOI1, 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://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

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), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@1JAEWOOCHOI1 good news 😃! Your original issue may now be fixed ✅ in PR #7074. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

[1JAEWOOCHOI1]

다시 시도해보고 있는데 아직 해결을 하지 못했습니다.

[glenn-jocher]

@1JAEWOOCHOI1 #7074 resolves your original issue. You need to update your code per the above instructions.

[marvision-ai]

Hi @glenn-jocher

I have updated the repo with the PR but still run into the same problem.

[kimkihoon0515]

@glenn-jocher
Ya same for me. Just updated the repo by using git pull but still problem not fixed

[glenn-jocher]

@marvision-ai @kimkihoon0515 oh interesting. This is in the loss function rather than the model itself. Maybe torch.Tensor.tensor_split() was only introduced recently. What version of torch are you guys using?

[kimkihoon0515]

@glenn-jocher I'm using 1.7.1

[glenn-jocher]

@marvision-ai @kimkihoon0515 it looks like torch.Tensor.tensor_split was first introduced in torch 1.8.0:
https://pytorch.org/docs/1.8.0/tensors.html?highlight=tensor_split#torch.Tensor.tensor_split

Since our requirements are torch>=1.7.0 we have a problem now... let me think about this

[kimkihoon0515]

@glenn-jocher should i upgrade my torch above to 1.8.0??

[glenn-jocher]

@kimkihoon0515 yes if you upgrade the problem will be solved. I need to figure out if I can replace tensor_split with something 1.7.0 compatible though for everyone else, otherwise I'll have to raise the YOLOv5 requirements to 1.8.0, which we probably want to avoid.

[kimkihoon0515]

@glenn-jocher which version of torch and cuDNN u use? i just upgraded my torch and seems the cuDNN version doesn't match with my torch ver

[glenn-jocher]

@kimkihoon0515 see https://pytorch.org/get-started/previous-versions/

[glenn-jocher]

@kimkihoon0515 @marvision-ai good news 😃! Your original issue may now be fixed ✅ in PR #7102. To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!