mmdeploy

mmdeploy copied to clipboard

Profiler

1

## Motivation profiler ## Modification Please briefly describe what modification is made in this PR.

irexyc

How/where to get started developing support for models.

7

I potentially need to convert other models (mmdet, instance segmentation, e.g., yolact, solo) than currently support by mmdeploy. Is there a more detailed [guide](https://mmdeploy.readthedocs.io/en/latest/tutorials/how_to_support_new_models.html) about how to do this/ how...

rickvanveen

Result divergence of deployed ConvNeXt model

3

I used the latest MMDeploy tool to convert ConvNeXt into tensorRT backend. It converted successfully. However, when I visualized the results, I found the output from tensorRT backend was totally...

haofanwang

Inconsistent behavior of the test script in mmdetection vs mmdeploy

4

Thanks for your bug report. We appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md)...

ernestlwt

faster rcnn model deployed to tensorrt with fp32 and the map drop a little

2

@grimoire Hi! I asked you about the faster rcnn model map drop after I deploy it to tensortt, you said because of the tensorrt version,https://github.com/open-mmlab/mmdeploy/issues/496#issuecomment-1134230895 I just update tensorrt version...

Ricardosuzaku

[Enhancement] make build script for windows platform

4

**Describe the feature** Write a script to build mmdeploy under windows platform. **Motivation** make windows build easier.

lvhan028

Dynamic num_dets does not take effect when onnx is converted to openvino.

5

When converting maskrcnn into an openvino model, it is found that even if the configuration file uses a dynamic config, the result given by openvino is still a fixed value...

hong-kailin

Quantized Model for Torchscript

3

Hello～ Do you have plan to support quantized models for torchscript?

xingyueye

Hi, Thank you for your work on the deploy of 3D detection model. I have test the `pointpillars` and `centerpoints` in `mmdeploy`. But I found that the inference latency is...

chenxyyy

Use the Python API interface and the TensorRT engine file to infer the image, the program terminates directly and the above prompt message Process finished with exit code -1073741819 (0xC0000005) appears

3

**from mmdeploy.apis.inference import inference_model from mmdeploy.apis.utils import build_task_processor from detect.utils_torchvision import inference from mmdeploy.utils.utils import get_root_logger logger = get_root_logger(log_level=logging.DEBUG) logging.root = logger deploy_cfg = 'C:/Users/12481/MMDeploy/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py' model_cfg = 'C:/Users/12481/mmdetection/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py' backend_files =...

1wang11lijian1