Apply make_divisible for ONNX models in Autoshape

[janus-zheng]

At line 697 we have this make_divisible function applied on input images for pytorch models.

• Context: we want to run inference on varied input sizes instead of fixed image size.
• When I test an image of size [720, 720] for a pytorch model (e.g., yolov5n.pt), we can see that it will be reshaped to [736, 736] by the function. This is as expected.
• When I test the same image for the onnx model (e.g., yolov5n.onnx, exported with --dynamic), I got an error and it's due to the indivisible problem

onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running Concat node. Name:'Concat_143' Status Message: concat.cc:156 PrepareForCompute Non concat axis dimensions must match: Axis 3 has mismatched dimensions of 45 and 46

The simple solution is to enable the make_divisible function for onnx model too.

Signed-off-by: janus-zheng 106574221+janus-zheng@users.noreply.github.com

🛠️ PR Summary

_{Made with ❤️ by Ultralytics Actions}

🌟 Summary

Enhanced image pre-processing in YOLOv5's inference pipeline.

📊 Key Changes

• Streamlined the image sizing process during the inference stage, removing a conditional check for PyTorch training.

🎯 Purpose & Impact

• 👍 Improves the efficiency of image pre-processing by eliminating unnecessary code when not in training mode.
• 🚀 Potentially increases the speed of model inference, leading to faster results for end-users.
• 🧑‍💻 Provides a more simplified codebase for developers working with the inference part of YOLOv5's code.

[glenn-jocher]

@janus-zheng I've updated this to apply to all models, as they should all inherit a default stride=32 on DetectMultiBackend init here:

yolov5/models/common.py

Line 339 in e40662f

stride = 32 # default stride

Does this work for you?

[janus-zheng]

@janus-zheng I've updated this to apply to all models, as they should all inherit a default stride=32 on DetectMultiBackend init here:

yolov5/models/common.py

Line 339 in e40662f

stride = 32 # default stride

Does this work for you?

@glenn-jocher that's better, thanks!

[glenn-jocher]

@janus-zheng perfect. PR is merged. Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐