ultralytics/yolov3

Some confusion about torch.hub.load to load yolov3.pt, please help me

J-LINC opened this issue · 5 comments

J-LINC commented

Search before asking

Question

It took too long to load the YOLOv3 model using torch. hub. load，every time I rerun the test script, he gets stuck loading the model for a long time
image

image

Additional

No response

github-actions commented

👋 Hello @J-LINC, thank you for your interest in YOLOv3 🚀! 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 a minimum reproducible example to help us debug it.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset image examples and training logs, and verify you are following our Tips for Best Training Results.

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

YOLOv3 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

Status

YOLOv3 CI

If this badge is green, all YOLOv3 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training, validation, inference, export and benchmarks on macOS, Windows, and Ubuntu every 24 hours and on every commit.

Introducing YOLOv8 🚀

We're excited to announce the launch of our latest state-of-the-art (SOTA) object detection model for 2023 - YOLOv8 🚀!

Designed to be fast, accurate, and easy to use, YOLOv8 is an ideal choice for a wide range of object detection, image segmentation and image classification tasks. With YOLOv8, you'll be able to quickly and accurately detect objects in real-time, streamline your workflows, and achieve new levels of accuracy in your projects.

Check out our YOLOv8 Docs for details and get started with:

pip install ultralytics
glenn-jocher commented

Hello @J-LINC,

Thank you for reaching out to the YOLOv3 community. It seems like you are having trouble with loading the YOLOv3 model using torch.hub.load. Have you tried running the test script again after the model has finished loading? Depending on your system specifications, the first loading of the model may take longer than subsequent loads. However, if the loading is taking a very long time every time you run the script, there may be an issue with your setup.

Please let us know if you have any further questions or if you need additional help with this issue. We are happy to assist you in any way we can.

Best regards.

J-LINC commented

Hello @J-LINC,

Thank you for reaching out to the YOLOv3 community. It seems like you are having trouble with loading the YOLOv3 model using torch.hub.load. Have you tried running the test script again after the model has finished loading? Depending on your system specifications, the first loading of the model may take longer than subsequent loads. However, if the loading is taking a very long time every time you run the script, there may be an issue with your setup.

Please let us know if you have any further questions or if you need additional help with this issue. We are happy to assist you in any way we can.

Best regards.

when I first ran it, I waited for the model to load successfully and then ended normally.
image

However, when I ran the script again, I found that it became very slow
image

J-LINC commented

Hello @J-LINC,

Thank you for reaching out to the YOLOv3 community. It seems like you are having trouble with loading the YOLOv3 model using torch.hub.load. Have you tried running the test script again after the model has finished loading? Depending on your system specifications, the first loading of the model may take longer than subsequent loads. However, if the loading is taking a very long time every time you run the script, there may be an issue with your setup.

Please let us know if you have any further questions or if you need additional help with this issue. We are happy to assist you in any way we can.

Best regards.

wow， I tried some actions according to the warning prompts，i found that it succeeded and it is faste! I think I just ignored those warnings before.
Thank you for your quick response and excellent code

image

glenn-jocher commented

Hello @J-LINC,

We're glad to hear that our suggestions were helpful in resolving your issue. It's possible that the warning messages you were seeing were causing some delay in the model loading when you were running the script again. It's always a good idea to pay attention to warning and error messages as they can help you diagnose issues more easily.

If you have any further questions or need additional assistance with YOLOv3, please don't hesitate to reach out. We're here to support you in any way we can.

Best regards.