Resolved Issue: Fix Exporting ONNX Model with Fixed Batch Size of 1 Using export_tensorrt_engine

zhiqwang / yolort

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

https://zhiqwang.com/yolort

GNU General Public License v3.0

708 stars 153 forks source link

Resolved Issue: Fix Exporting ONNX Model with Fixed Batch Size of 1 Using export_tensorrt_engine #509

Closed laugh12321 closed 6 months ago

laugh12321 commented 6 months ago

Description:

This PR resolves #508 . The fix ensures that the exported models now correctly retain the specified batch size as intended, providing improved flexibility for users working with ONNX models.

Before Fix:

After Fix:

CLAassistant commented 6 months ago

All committers have signed the CLA.