[MMSegmentation](https://github.com/open-mmlab/mmsegmentation/tree/1.x) aka `mmseg` is an open source semantic segmentation toolbox based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
## Installation
### Install mmseg
Please follow the [installation guide](https://mmsegmentation.readthedocs.io/en/1.x/get_started.html) to install mmseg.
### Install mmdeploy
There are several methods to install mmdeploy, among which you can choose an appropriate one according to your target platform and device.
- Adding `$(pwd)/build/lib` to `PYTHONPATH` is for importing mmdeploy SDK python module - `mmdeploy_python`, which will be presented in chapter [SDK model inference](#sdk-model-inference).
- When [inference onnx model by ONNX Runtime](#backend-model-inference), it requests ONNX Runtime library be found. Thus, we add it to `LD_LIBRARY_PATH`.
**Method III:** Build from source
If neither **I** nor **II** meets your requirements, [building mmdeploy from source](../01-how-to-build/build_from_source.md) is the last option.
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmseg models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmseg) of all supported backends for mmsegmentation. The config filename pattern is:
Therefore, in the above example, you can also convert `unet` to other backend models by changing the deployment config file `segmentation_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmseg), e.g., converting to tensorrt-fp16 model by `segmentation_tensorrt-fp16_dynamic-512x1024-2048x2048.py`.
When converting mmseg models to tensorrt models, --device should be set to "cuda"
```
## Model specification
Before moving on to model inference chapter, let's know more about the converted model structure which is very important for model inference.
The converted model locates in the working directory like `mmdeploy_models/mmseg/ort` in the previous example. It includes:
```
mmdeploy_models/mmseg/ort
├── deploy.json
├── detail.json
├── end2end.onnx
└── pipeline.json
```
in which,
- **end2end.onnx**: backend model which can be inferred by ONNX Runtime
- \***.json**: the necessary information for mmdeploy SDK
The whole package **mmdeploy_models/mmseg/ort** is defined as **mmdeploy SDK model**, i.e., **mmdeploy SDK model** includes both backend model and inference meta information.
## Model inference
### Backend model inference
Take the previous converted `end2end.onnx` model as an example, you can use the following code to inference the model and visualize the results.
```python
from mmdeploy.apis.utils import build_task_processor
from mmdeploy.utils import get_input_shape, load_config
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
-<iid="static_shape">PSPNet, Fast-SCNN</i> only support static shape, because [nn.AdaptiveAvgPool2d](https://github.com/open-mmlab/mmsegmentation/blob/0c87f7a0c9099844eff8e90fa3db5b0d0ca02fee/mmseg/models/decode_heads/psp_head.py#L38) is not supported by most inference backends.
- For models that only supports static shape, you should use the deployment config file of static shape such as `configs/mmseg/segmentation_tensorrt_static-1024x2048.py`.
