-
-
Notifications
You must be signed in to change notification settings - Fork 16k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Device mismatch when an image in the input batch gives 0 detections at inference time #1617
Comments
Hello @baldassarreFe, 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. RequirementsPython 3.8 or later with all requirements.txt dependencies installed, including $ pip install -r requirements.txt EnvironmentsYOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):
StatusIf 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. |
Workaround issue ultralytics#1617. Probably, the actual solution is to modify `non_max_suppression`.
@baldassarreFe thanks for the bug report. I am able to reproduce this in a Colab notebook. It looks like the best solution would be to properly initialize the empty tensors on the same device as the incoming data in the NMS function. I will take a look. |
Thanks for the quick fix! |
@baldassarreFe thanks for the feedback! If you see any other areas that need improvement please let us know. |
🐛 Bug
The bug happens when:
To Reproduce
Input:
Output:
Expected behavior
Running inference on a batch should not cause an error if one of the images in the batch contains no objects.
Example (one image only, containing some object):
Environment
Additional context
The bug happens because the method
non_max_suppression
called on line 166 ofmodels/common.py
. The method correctly returns an empty tensor if no objects are detected, however, the tensor is always placed on the CPU, regardless of the original placement:Using the same two images as before and running in the debugger we can we print
y
just after the call tonon_max_suppression
. The first tensor, relative to the first image, is empty but is on the wrong deviceThe text was updated successfully, but these errors were encountered: