Adding tracker after detection

[berkantay]

❔Question

First of all thanks for this repository, it is completely useful. I have reached the accuracy and the performance of detection for my specific case. Now my aim is to embed some tracking algorithm just after detection. How can I get the bounding box coordinates. I am planning to pass those coordinates to the tracker when detection is occured.

[glenn-jocher]

See https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading

import torch
from PIL import Image

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True).fuse().eval()  # yolov5s.pt
model = model.autoshape()  # for autoshaping of PIL/cv2/np inputs and NMS

# Images
img = Image.open('data/images/zidane.jpg')  # PIL image

# Inference
prediction = model(img)

[shashi7679]

@glenn-jocher Hi... I am trying to do inference in my own way, using the torchscript file trained on my custom dataset.
When I am using the method for inference, I am getting prediction as a tuple consisting of a tensor of size (1 X 25200 X 85).

Now how to get xmin, xmax, ymin, ymax from this point.

I have been following this (https://docs.ultralytics.com/yolov5/tutorials/pytorch_hub_model_loading#issuecomment-695146444) approach for inference.

Please help me out.

Thanks in advance.

[glenn-jocher]

@shashi7679 sorry for the confusion. PyTorch Hub YOLOv5 models treat torch inputs as pass-throughs, so no pre or post processing is performed on torch inputs.

If you want a results object then please pass numpy arrays, PIL, cv2, file paths, etc.

[shashi7679]

@glenn-jocher But when I am passing array/PIL/cv2.. I am getting this error.

RuntimeError: forward() Expected a value of type 'Tensor' for argument 'x' but instead found type 'JpegImageFile'.
Position: 1
Value: <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1796x2717 at 0x21D086F19A0>
Declaration: forward(torch.models.yolo.Model self, Tensor x) -> ((Tensor))
Cast error details: Unable to cast Python instance to C++ type (compile in debug mode for details)

[glenn-jocher]

@shashi7679 👋 hi, thanks for letting us know about this possible problem with YOLOv5 🚀. We've created a few short guidelines below to help users provide what we need in order to start investigating a possible problem.

How to create a Minimal, Reproducible Example

When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to reproduce the problem. This is referred to by community members as creating a minimum reproducible example. Your code that reproduces the problem should be:

• ✅ Minimal – Use as little code as possible to produce the problem
• ✅ Complete – Provide all parts someone else needs to reproduce the problem
• ✅ Reproducible – Test the code you're about to provide to make sure it reproduces the problem

For Ultralytics to provide assistance your code should also be:

• ✅ Current – Verify that your code is up-to-date with GitHub master, and if necessary git pull or git clone a new copy to ensure your problem has not already been solved in master.
• ✅ Unmodified – Your problem must be reproducible using official YOLOv5 code without changes. Ultralytics does not provide support for custom code ⚠️.

If you believe your problem meets all the above criteria, please close this issue and raise a new one using the 🐛 Bug Report template with a minimum reproducible example to help us better understand and diagnose your problem.

Thank you! 😃