这个错误是一个常见的Python错误,表明Python解释器无法在当前环境中找到名为mmdeploy_runtime的模块。这通常是因为该模块尚未安装,或者安装在了不同的Python环境中。 检查Python环境是否已安装mmdeploy_runtime模块: 你可以通过运行以下Python代码来检查mmdeploy_runtime模块是否已安装: python try: import mmdeploy_run...
I havemmdeploy_runtime.cp38-win_amd64.pydinD:\project\mmdeploy\build\**bin**\Release, does it ok? Does 'PYTHONPATH=D:\project\mmdeploy\build\lib\Release ' mean add this path to $env:PYTHONPATH, then runpython .\mmdeploy\demo\python\object_detection.py cuda D:\project\mmdeploy_model...
MMdeploy must be updated to support latest OpenVINO and onnxruntime which is officially supported ASAP. Related resources MMDeploy 2.3.0 requires onnxruntime <= v1.15.1 because MMDeploy SDK currently rely on Ort::CustomOpApi removed at v1.16.0. (see #2465 ) However, it seems that there...
Checklist I have searched related issues but cannot get the expected help. 2. I have read the FAQ documentation but cannot get the expected help. 3. The bug has not been fixed in the latest version. Describe the bug An error occurred whi...
/mmdeploy/configs/mmocr/text-detection/text-detection_onnxruntime_dynamic.py ../mmocr/configs/textdet/dbnet/dbnet_r50dcnv2_fpnc_1200e_icdar2015.py ../epoch_540.pth ../test.jpg --work-dir work_dir --device 'cpu' And I modify code inference ...
2 changes: 1 addition & 1 deletion 2 csrc/mmdeploy/backend_ops/onnxruntime/nms_match/nms_match.h Original file line numberDiff line numberDiff line change @@ -17,7 +17,7 @@ struct NMSMatchKernel { void Compute(OrtKernelContext* context); private: Ort::CustomOpApi ort_; const OrtAp...
I added import mmdeploy.codebase.mmpretrain.models in the noted place but the outputs of tensorrt and onnx are still all zero. Is this problem anything to do with 'visualize onnxruntime model failed' mentioned above? to note , the output of my machine 'uname -a' is Linux AST1 5.15...