open-mmlab/mmdeploy

Issues

• [Bug] rtmo tensorrt model with 1x3x1280x640 has problem while tensorrt model with 1x3x640x640 works well

  #2776 opened 5 days ago by senbinyu
  1

• [Bug] NYI: Named tensors are not supported with the tracer

  #2769 opened 22 days ago by d710055071
  2

• [Bug] How to get the pred_instances for the mask2Former tensorrt model

  #2775 opened 8 days ago by moliwei2019
  0

• Support for TensorRT 10.0 [Feature]

  #2758 opened a month ago by thu-bear
  1

• [Bug]

  #2774 opened 10 days ago by limesqueezy
  1

• Error while converting mmdet3d model to tensorRT engine

  #2773 opened 12 days ago by VeeranjaneyuluToka
  0

• Any plans for tflite int8 or onnxruntime int8 RTMdet exports?

  #2772 opened 13 days ago by ramonhollands
  0

• [Bug] Converting to ONNX: Dynamic batch size on input gives all dynamic axes on output.

  #2731 opened 2 months ago by erogodsky
  2

• [Bug] SDK Inference Using ONNX-GPU: Segmentation fault (core dumped)

  #2770 opened 19 days ago by heylamourding
  0

• [Bug] The serialized model is larger than the 2GiB limit imposed by the protobuf library

  #2768 opened a month ago by maximefuchs
  0

• A problem occurred when I tried to use C++ to deploy TensorRT+cuda under windows. Device "cuda" not found.

  #2767 opened a month ago by HBC11
  0

• [Bug] How do I use multiprocess or multithreaded loading models

  #2723 opened 2 months ago by jiadong696
  1

• When object detection returns a large number of detection boxes, drawing boxes is very time-consuming. Is there any method[Feature]

  #2766 opened a month ago by xiao-song2022
  0

• [Bug] support rtmdet-ins for ascend backend

  #2751 opened 2 months ago by tycallen
  0

• [Bug] 使用瑞芯微rk3588部署mmpose模型报错

  #2765 opened a month ago by vicnoah
  0

• rtmpose mmpose demo里的image_demo和inference_demo效果区别怎么这么大？

  #2764 opened a month ago by lsm140
  0

• [Bug] 尝试进行瑞芯微RK3588模型转换出错

  #2740 opened a month ago by vicnoah
  1

• issue deploying libra-retinanet to onnx due to BFP neck component

  #2763 opened a month ago by reiffd7
  0

• [Bug] mmpretrain预训练模型转ncnn int8的时候报错！

  #2762 opened a month ago by shenjun1994
  0

• [Bug] win11 No module named 'distutils'

  #2761 opened a month ago by a819411321
  0

• [Bug] Tried to run the example in the mmdeploy tutorial but failed

  #2756 opened a month ago by Ochre-amber
  3

• [Bug] Could not load the library of tensorrt plugins. & Serialization (Serialization assertion creator failed.Cannot deserialize plugin since corresponding IPluginCreator not found in Plugin Registry)

  #2747 opened 2 months ago by xiao-song2022
  2

• How to convert a Segmenter model?

  #2760 opened a month ago by crmauceri
  1

• YOLOX to Onnx failed RuntimeError: Only tuples, lists and Variables are supported as JIT inputs/outputs.

  #2759 opened a month ago by 99HU
  0

• Unable to install mmdeploy/tensorrt on H100 : Unsupported SM: 0x900 [Bug]

  #2757 opened a month ago by timsainb
  0

• Does MMDeploy support mmaction2 (skeleton: posec3d with slowonly_r50_8xb32-u48-240e_k400-keypoint)?

  #2754 opened a month ago by hoduy1411
  0

• [Bug] Issue with tools/deploy.py on centerpoint model

  #2726 opened 2 months ago by soellingeraj-code19
  1

• [Bug] run device is wrong

  #2752 opened 2 months ago by Winnie202
  0

• [Bug]

  #2750 opened 2 months ago by Gbbfine
  0

• [Bug] Failed to convert fcos-resnet50 to onnx

  #2736 opened 2 months ago by moonlightian
  1

• [Bug] Parameters Codebase config

  #2748 opened 2 months ago by Daanfb
  0

• How to load model in memory?(windows SDK with ncnn backend)

  #2744 opened 2 months ago by Cauli-hugh
  0

• [Docs] RTMO inference with TensorRT

  #2741 opened 2 months ago by Daanfb
  0

• [Bug] Wrong Onnx Execution Provider - Error when binding input: There's no data transfer registered for copying tensors from Device:[DeviceType:1 MemoryType:0 DeviceId:0] to Device:[DeviceType:0 MemoryType:0 DeviceId:0]

  #2742 opened 2 months ago by ehratjon
  1

• [Bug] wrong order of arguments in `scaled_dot_product_attention__default`

  #2746 opened 2 months ago by lilanxiao
  0

• [Bug] Cannot use MMDeploy with MMAction2

  #2743 opened 2 months ago by oschan77
  0

• [Bug]When I deploy segmentation, the result of SDK occurs discontinuous results. Sometimes the result is normal, but another time it's unnormal.

  #2739 opened 2 months ago by GSusan
  0

• [Feature] Torchscript Backend support for Pytorch 2.1.0+ versions

  #2738 opened 2 months ago by achbogga
  0

• RTMO model convert to onnx

  #2734 opened 2 months ago by anzisheng
  1

• [Bug] Detection TensorRT has zero output binding shape

  #2737 opened 2 months ago by vision-gtc
  0

• [Bug] RTMDet model to ONNXRuntime or Torchscript doesn't produce masks

  #2735 opened 2 months ago by soulslicer
  0

• Fatal error: mmdeploy:MMCVModulatedDeformConv2d(-1) is not a registered function/op

  #2733 opened 2 months ago by Homura852
  0

• [Bug] The C++ environment has been configured. When I use the exported onnx file, it shows that the model cannot be loaded during C++ inference.

  #2732 opened 2 months ago by JackIRose
  0

• [Bug] Detection is not possible depending on the aspect ratio of the defect.

  #2727 opened 2 months ago by skzlzl
  0

• [Feature] DSVT in mmdeploy

  #2729 opened 2 months ago by MarvinKlemp
  0

• [Docs] ONNX export Optimizer

  #2728 opened 2 months ago by YOODS-Xu
  0

• [Bug] [mmdeploy] [error] [module_adapter.h:31] unhandled exception: invalid argument (1)

  #2725 opened 2 months ago by DarshanVirdi
  0

• [Bug] Dynamic Axes Not supported with this tensorRT version

  #2724 opened 2 months ago by aaditya-srivathsan
  0

• [Bug] IndexError: list index out of range

  #2721 opened 2 months ago by aaditya-srivathsan
  0

• how to remove "mmdeploy" domain in model's input and keep the onnx model reasoning normal

  #2722 opened 2 months ago by nanhui69
  1