Before installing the service module, you need to prepare the inference model and put it in the correct path. The default model path is:
Before installing the service module, you need to prepare the inference model and put it in the correct path. The default model path is:
```
```
Model structure file: ./inference/cls_infer.pdmodel
Model structure file: PaddleClas/inference/inference.pdmodel
Model parameters file: ./inference/cls_infer.pdiparams
Model parameters file: PaddleClas/inference/inference.pdiparams
```
```
**The model path can be found and modified in `params.py`.** More models provided by PaddleClas can be obtained from the [model library](../../docs/en/models/models_intro_en.md). You can also use models trained by yourself.
* The model file path can be viewed and modified in `PaddleClas/deploy/hubserving/clas/params.py`.
It should be noted that the prefix of model structure file and model parameters file must be `inference`.
* More models provided by PaddleClas can be obtained from the [model library](../../docs/en/models/models_intro_en.md). You can also use models trained by yourself.
### 3. Install Service Module
### 3. Install Service Module
* On Linux platform, the examples are as follows.
* On Linux platform, the examples are as follows.
```shell
```shell
hub install deploy/hubserving/clas/
cd PaddleClas/deploy
hub install hubserving/clas/
```
```
* On Windows platform, the examples are as follows.
* On Windows platform, the examples are as follows.
```shell
```shell
hub install deploy\hubserving\clas\
cd PaddleClas\deploy
hub install hubserving\clas\
```
```
### 4. Start service
### 4. Start service
...
@@ -103,32 +109,30 @@ Wherein, the format of `config.json` is as follows:
...
@@ -103,32 +109,30 @@ Wherein, the format of `config.json` is as follows:
For example, use GPU card No. 3 to start the 2-stage series service:
For example, use GPU card No. 3 to start the 2-stage series service:
-**image_path**: Test image path, can be a single image path or an image directory path
-**image_path**: Test image path, can be a single image path or an image directory path
-**top_k**: [**Optional**] Return the top `top_k` 's scores ,default by `1`.
-**batch_size**: [**Optional**] batch_size. Default by `1`.
-**batch_size**: [**Optional**] batch_size. Default by `1`.
-**resize_short**: [**Optional**] Resize the input image according to short size. Default by `256`.
-**resize**: [**Optional**] Resize the input image. Default by `224`.
-**normalize**: [**Optional**] Whether normalize the input image. Default by `True`.
**Notice**:
**Notice**:
If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `--resize_short=384`, `--resize=384`.
If you want to use `Transformer series models`, such as `DeiT_***_384`, `ViT_***_384`, etc., please pay attention to the input size of model, and need to set `--resize_short=384`, `--resize=384`.
└─ float: The time cost of predicting the picture, unit second
└─ float: The time cost of predicting the picture, unit second
```
```
**Note：** If you need to add, delete or modify the returned fields, you can modify the file `module.py` of the corresponding module. For the complete process, refer to the user-defined modification service module in the next section.
**Note：** If you need to add, delete or modify the returned fields, you can modify the corresponding module. For the details, refer to the user-defined modification service module in the next section.
## User defined service module modification
## User defined service module modification
If you need to modify the service logic, the following steps are generally required:
If you need to modify the service logic, the following steps are generally required:
...
@@ -151,20 +155,41 @@ If you need to modify the service logic, the following steps are generally requi
...
@@ -151,20 +155,41 @@ If you need to modify the service logic, the following steps are generally requi
```shell
```shell
hub serving stop --port/-p XXXX
hub serving stop --port/-p XXXX
```
```
2. Modify the code in the corresponding files, like `module.py` and `params.py`, according to the actual needs.
For example, if you need to replace the model used by the deployed service, you need to modify model path parameters `cfg.model_file` and `cfg.params_file` in `params.py`. Of course, other related parameters may need to be modified at the same time. Please modify and debug according to the actual situation.
After modifying and installing (`hub install deploy/hubserving/clas/`) and before deploying, you can use `python deploy/hubserving/clas/test.py` to test the installed service module.
2. Modify the code in the corresponding files, like `module.py` and `params.py`, according to the actual needs. You need re-install(hub install hubserving/clas/) and re-deploy after modifing `module.py`.
After modifying and installing and before deploying, you can use `python hubserving/clas/module.py` to test the installed service module.
For example, if you need to replace the model used by the deployed service, you need to modify model path parameters `cfg.model_file` and `cfg.params_file` in `params.py`. Of course, other related parameters may need to be modified at the same time. Please modify and debug according to the actual situation.
3. Uninstall old service module
3. Uninstall old service module
```shell
```shell
hub uninstall clas_system
hub uninstall clas_system
```
```
4. Install modified service module
4. Install modified service module
```shell
```shell
hub install deploy/hubserving/clas/
hub install hubserving/clas/
```
```
5. Restart service
5. Restart service
```shell
```shell
hub serving start -m clas_system
hub serving start -m clas_system
```
```
**Note**:
Common parameters can be modified in params.py:
* Directory of model files(include model structure file and model parameters file):
```python
"inference_model_dir":
```
* The number of Top-k results returned during post-processing:
```python
'topk':
```
* Mapping file corresponding to label and class ID during post-processing:
```python
'class_id_map_file':
```
In order to avoid unnecessary delay and be able to predict in batch, the preprocessing (include resize, crop and other) is completed in the client, so modify [test_hubserving.py](./test_hubserving.py#L35-L52) if necessary.
