Semyon Bevzyuk bb9b0a98de
[Enhancement]: Added static config and CI tests for OpenVINO. (#218)
* Add openvino_static.

* Add openvino-dev.

* Fix skipping ORT tests in test_mmocr_models.

* Updated docs.

* Fix print.

* Fix

* Fix

* Fix other backends

* Fix is_available

* fix ncnn

* Add constrict for get rewrite output

* add not

* Fix

* fix

* Fix

* Fix

* Improve tests

* Remove rebundant `cuda`

* Prevent None object and rename variable

* Fix multi-line string

* rename get_backend_checker

* Add Troubleshooting to doc.

* Fix postprocessing_masks with empty masks.

* Fix tests

* lint

* Update docs.

Co-authored-by: SingleZombie <singlezombie@163.com>
2021-12-01 14:03:48 +08:00

1.9 KiB

MMSegmentation Support

MMSegmentation is an open source object segmentation toolbox based on PyTorch. It is a part of the OpenMMLab project.

MMSegmentation installation tutorial

Please refer to get_started.md for installation.

List of MMSegmentation models supported by MMDeploy

model OnnxRuntime TensorRT NCNN PPL OpenVino model config file(example)
FCN Y Y Y Y ? ${MMSEG_DIR}/configs/fcn/fcn_r50-d8_512x1024_40k_cityscapes.py
PSPNet* Y Y N Y ? ${MMSEG_DIR}/configs/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes.py
DeepLabV3 Y Y Y Y ? ${MMSEG_DIR}/configs/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes.py
DeepLabV3+ Y Y Y Y ? ${MMSEG_DIR}/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py

Reminder

  • Only whole inference mode is supported for all mmseg models.

  • PSPNet only supports static shape, better to use the deployment config file of static shape such as configs/mmseg/segmentation_tensorrt_static-512x1024.py. Because nn.AdaptiveAvgPool2d in psp_head is not supported in most of backends dynamically.

FAQs

None