Yolov5: NotImplementedError: Got <class 'NoneType'>, but numpy array, torch tensor, or caffe2 blob name are expected.

[jitunayak]

Before submitting a bug report, please be aware that your issue must be reproducible with all of the following, otherwise it is non-actionable, and we can not help you:

• Current repository: run git fetch && git status -uno to check and git pull to update your repo
• Common dataset: coco.yaml or coco128.yaml
• Common environment: Colab, Google Cloud, or Docker image. See https://github.com/ultralytics/yolov5#reproduce-our-environment

If this is a custom dataset/training question you must include your train*.jpg, test*.jpg and results.png figures, or we can not help you. You can generate results.png with utils.plot_results().

🐛 Bug

A clear and concise description of what the bug is.

To Reproduce (REQUIRED)

Input:

import torch

a = torch.tensor([5])
c = a / 0

Output:

Traceback (most recent call last):
  File "/Users/glennjocher/opt/anaconda3/envs/env1/lib/python3.7/site-packages/IPython/core/interactiveshell.py", line 3331, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-5-be04c762b799>", line 5, in <module>
    c = a / 0
RuntimeError: ZeroDivisionError

Expected behavior

A clear and concise description of what you expected to happen.

Environment

If applicable, add screenshots to help explain your problem.

• OS: [e.g. Ubuntu]
• GPU [e.g. 2080 Ti]

Additional context

Add any other context about the problem here.

[github-actions[bot]]

Hello @jitunayak, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Jupyter Notebook , Docker Image, and Google Cloud Quickstart Guide for example environments.

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 model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

[glenn-jocher]

@jitunayak if you do not include exact code to reproduce, there is nothing for us to do, and your issue is non-actionable.

[Lornatang]

@jitunayak @glenn-jocher This problem is caused by TensorBoard. PyTorch official has solved this problem.

run

pip install -q https://s3.amazonaws.com/ossci-linux/wheels/tensorboard-1.14.0a0-py3-none-any.whl --user

More details see: https://github.com/pytorch/pytorch/pull/16196 and https://github.com/pytorch/pytorch/commit/98e312cf96f6a5e23933cd8794097063ee3cbc8c

[josephofiowa]

@jitunayak How big was your dataset relative to your batch size? I was able to reproduce your error with a dataset that contained fewer images than my batch size.

Decreasing the batch size to be smaller than your training dataset size may resolve your issue. e.g.:
!python train.py --img 416 --batch 2 --epochs 300 --data '../data.yaml' --cfg ./models/custom_yolov5s.yaml --weights '' --name yolov5s_results --nosave --cache

[glenn-jocher]

@josephofiowa ah, interesting. There is actually existing code to check for this use case and adjust the batch size accordingly, but I have not tested it in a while. I'll try to reproduce.
https://github.com/ultralytics/yolov5/blob/d994ed25f1cc158c30b08cc19546e4ce5a9b32cc/train.py#L169-L170

[glenn-jocher]

@jitunayak @Lornatang @josephofiowa I was able to reproduce the error myself using the following notebook command:
!python train.py --data coco128.yaml --epochs 3 --img 64 --batch 150

I found the problem was produced by plotting code for the first 3 batches, which was glitching since these small datasets are composed of a single batch. Just pushed a fix now, problem should be resolved. Please git pull and try again.

[josephofiowa]

@glenn-jocher Confirming that resolved the issue.