diff --git a/README.md b/README.md index dadf080e2..66617fc2b 100644 --- a/README.md +++ b/README.md @@ -47,7 +47,7 @@ Please refer to [get_started.md](docs/get_started.md) for installation. ## Getting Started -Please read [get_started.md](docs/get_started.md) for the basic usage of MMDeploy. There are also tutorials for [how to convert a model](docs/tutorials/how_to_convert_model.md), [how to write a config](docs/tutorials/how_to_write_config.md), [how to support new models](docs/tutorials/how_to_support_new_models.md) and [how to test model](docs/tutorials/how_to_test_model.md). +Please read [how_to_convert_model.md](docs/tutorials/how_to_convert_model.md) for the basic usage of MMDeploy. There are also tutorials on [how to write config](docs/tutorials/how_to_write_config.md), [how to support new models](docs/tutorials/how_to_support_new_models.md) and [how to measure performance of models](docs/tutorials/how_to_measure_performance_of_models.md). Please refer to [FAQ](docs/faq.md) for frequently asked questions. diff --git a/README_zh-CN.md b/README_zh-CN.md index cc67ed69c..19121c6ec 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -47,7 +47,7 @@ MMDeploy 是一个开源深度学习模型部署工具箱,它是 [OpenMMLab](h 请阅读 [如何进行模型转换](docs/tutorials/how_to_convert_model.md) 来了解基本的 MMDeploy 使用。 -我们还提供了诸如 [如何编写配置文件](docs/tutorials/how_to_write_config.md), [如何添加新模型支持](docs/tutorials/how_to_support_new_models.md) 和 [如何测试模型效果](docs/tutorials/how_to_test_model.md) 等教程。 +我们还提供了诸如 [如何编写配置文件](docs/tutorials/how_to_write_config.md), [如何添加新模型支持](docs/tutorials/how_to_support_new_models.md) 和 [如何测试模型效果](docs/tutorials/how_to_measure_performance_of_models.md) 等教程。 如果遇到问题,请参考 [常见问题解答](docs/faq.md)。 diff --git a/docs/codebases/mmseg.md b/docs/codebases/mmseg.md index fa968fd05..d22d18eef 100644 --- a/docs/codebases/mmseg.md +++ b/docs/codebases/mmseg.md @@ -8,16 +8,18 @@ Please refer to [get_started.md](https://github.com/open-mmlab/mmsegmentation/bl ### List of MMSegmentation models supported by MMDeploy -| model | OnnxRuntime | TensorRT | NCNN | PPL | OpenVino | model config file(example) | -|:---------- | :---------: | :-----------: | :---:| :---: | :------: | :--------------------------------------------------------------------------------------- | -| FCN | Y | Y | Y | Y | ? | $PATH_TO_MMSEG/configs/fcn/fcn_r50-d8_512x1024_40k_cityscapes.py | -| PSPNet | Y | Y | N | Y | ? | $PATH_TO_MMSEG/configs/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes.py | -| DeepLabV3 | Y | Y | Y | Y | ? | $PATH_TO_MMSEG/configs/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes.py | -| DeepLabV3+ | Y | Y | Y | Y | ? | $PATH_TO_MMSEG/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py | +| 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[*](#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 -None +- 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](https://github.com/open-mmlab/mmsegmentation/blob/97f9670c5a4a2a3b4cfb411bcc26db16b23745f7/mmseg/models/decode_heads/psp_head.py#L38) in psp_head is not supported in most of backends dynamically. ### FAQs diff --git a/docs/index.rst b/docs/index.rst index 0b94d51f6..3aa4180d7 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -16,7 +16,7 @@ You can switch between Chinese and English documents in the lower-left corner of tutorials/how_to_convert_model.md tutorials/how_to_write_config.md tutorials/how_to_evaluate_a_model.md - tutorials/how_to_test_model.md + tutorials/how_to_measure_performance_of_models.md tutorials/how_to_support_new_models.md tutorials/how_to_add_test_units_for_backend_ops.md tutorials/how_to_test_rewritten_models.md diff --git a/docs/tutorials/how_to_test_model.md b/docs/tutorials/how_to_measure_performance_of_models.md similarity index 97% rename from docs/tutorials/how_to_test_model.md rename to docs/tutorials/how_to_measure_performance_of_models.md index 86da53a39..0addd7dd2 100644 --- a/docs/tutorials/how_to_test_model.md +++ b/docs/tutorials/how_to_measure_performance_of_models.md @@ -1,4 +1,4 @@ -## How to test model +# How to measure the performance of a model After we convert a PyTorch model to a backend model, we may need to test the speed of the model before using it. In MMDeploy, we provide a tool to test the speed of backend models in `tools/test.py`