Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Is there a script to test the mAP of the engine file? #5278

Closed
shihanyu opened this issue Oct 21, 2021 · 13 comments
Closed

Is there a script to test the mAP of the engine file? #5278

shihanyu opened this issue Oct 21, 2021 · 13 comments
Labels
enhancement New feature or request Stale

Comments

@shihanyu
Copy link

🚀 Feature

 When a model file is transferred into tensorrt format (.pt to .engine ), the performance may be infulenced. so is there a test file to culculate the mAP with the engine file?

Motivation

Pitch

Alternatives

Additional context
@shihanyu shihanyu added the enhancement New feature or request label Oct 21, 2021
@github-actions
Copy link
Contributor

github-actions bot commented Oct 21, 2021 •
edited by glenn-jocher
Loading

👋 Hello @shihanyu, 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 Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python>=3.6.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

$ git clone https://github.com/ultralytics/yolov5
$ cd yolov5
$ 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):

Status

CI CPU testing

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
Copy link
Member

@shihanyu no there is not. val.py will only produce metrics on PyTorch models currently.

Detect.py will run inference on PyTorch, ONNX runtime, ONNX OpenCV DNN, TorchScript, TFLite models, TF pb and TF saved_model formats.

@francescotaioli
Copy link

@shihanyu coco eval api could be used to get the mAP. In order to do so, you have to create the json (in the coco format) that contain the prediction. You can create this json using the output from the engine.
See also https://stackoverflow.com/a/69556204/5723524

@glenn-jocher
Copy link
Member

@shihanyu good news 😃! Your original issue may now be partially addressed ✅ in PR #5549. This PR consolidates all backends into a single YOLOv5 DetectMultiBackend() class. Supports following model formats:

  • PyTorch *.pt
  • TorchScript *.torchscript.pt
  • CoreML *.mlmodel
  • TensorFlow saved_model
  • TensorFlow *.pb
  • TensorFlow Lite *.tflite
  • TensorFlow.js web_model
  • ONNX Runtime *.onnx
  • OpenCV DNN *.onnx

TensorRT is not currently supported, but if you have experience with it please consider submitting a PR to help others run inference with it.

Usage

# Export
python export.py --weights yolov5s.pt --include tflite

# Inference
python detect.py --weights yolov5s.tflite
python val.py --weights yolov5s.tflite

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 Open In Colab Open In Kaggle
  • Docker – sudo docker pull ultralytics/yolov5:latest to update your image Docker Pulls

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 🚀!

@shihanyu
Copy link
Author

shihanyu commented Nov 10, 2021 via email

@glenn-jocher
Copy link
Member

@shihanyu hmm interesting. Maybe I'll contact the trtx author to see if he'd help us with a PR.

@shihanyu
Copy link
Author

shihanyu commented Nov 12, 2021 via email

@shihanyu
Copy link
Author

shihanyu commented Nov 12, 2021 via email

@glenn-jocher
Copy link
Member

@shihanyu great, I will take a look today!

@shihanyu
Copy link
Author

shihanyu commented Nov 15, 2021 via email

@shihanyu
Copy link
Author

shihanyu commented Nov 16, 2021 via email

@glenn-jocher
Copy link
Member

@shihanyu yes, all 3rd party dependencies that are not part of requirements.txt can be placed in check_requirements() calls only if/when they are actually used. For example ONNX inference first checks to see if onnx and onnxruntime are installed here before importing them. If a user never uses ONNX models, these packages are never installed.

yolov5/models/common.py

Lines 315 to 319 in e80a09b

elif onnx: # ONNX Runtime
LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
check_requirements(('onnx', 'onnxruntime-gpu' if torch.has_cuda else 'onnxruntime'))
import onnxruntime
session = onnxruntime.InferenceSession(w, None)

This was referenced Nov 16, 2021
Merged
Closed
@github-actions
Copy link
Contributor

github-actions bot commented Dec 17, 2021 •
edited by glenn-jocher
Loading

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

Access additional Ultralytics ⚡ resources:

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

@github-actions github-actions bot added the Stale label Dec 17, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request Stale
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@francescotaioli @shihanyu @glenn-jocher