mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 16:48:03 +08:00
Add PaddleSeg doc and infer.cc demo (#114)
* Update README.md * Update README.md * Update README.md * Create README.md * Update README.md * Update README.md * Update README.md * Update README.md * Add evaluation calculate time and fix some bugs * Update classification __init__ * Move to ppseg * Add segmentation doc * Add PaddleClas infer.py * Update PaddleClas infer.py * Delete .infer.py.swp * Add PaddleClas infer.cc * Update README.md * Update README.md * Update README.md * Update infer.py * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Add PaddleSeg doc and infer.cc demo * Update README.md * Update README.md * Update README.md Co-authored-by: Jason <jiangjiajun@baidu.com>
This commit is contained in:
huangjianhui
@@ -1,46 +1,43 @@
|
||||
# PaddleClas模型 Python部署示例
|
||||
# PaddleSeg Python部署示例
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/quick_start/requirements.md)
|
||||
- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../docs/quick_start/install.md)
|
||||
|
||||
本目录下提供`infer.py`快速完成ResNet50_vd在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
|
||||
本目录下提供`infer.py`快速完成Unet在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
|
||||
|
||||
```
|
||||
# 下载ResNet50_vd模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/ResNet50_vd_infer.tgz
|
||||
tar -xvf ResNet50_vd_infer.tgz
|
||||
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
|
||||
|
||||
|
||||
#下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd examples/vision/classification/paddleclas/python
|
||||
cd FastDeploy/examples/vision/segmentation/paddleseg/python
|
||||
|
||||
# 下载Unet模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_without_argmax_infer.tgz
|
||||
tar -xvf Unet_cityscapes_without_argmax_infer.tgz
|
||||
wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
|
||||
|
||||
|
||||
# CPU推理
|
||||
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device cpu
|
||||
python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device cpu
|
||||
# GPU推理
|
||||
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device gpu
|
||||
python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu
|
||||
# GPU上使用TensorRT推理 （注意：TensorRT推理第一次运行，有序列化模型的操作，有一定耗时，需要耐心等待）
|
||||
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True
|
||||
python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu --use_trt True
|
||||
```
|
||||
|
||||
运行完成后返回结果如下所示
|
||||
```
|
||||
ClassifyResult(
|
||||
label_ids: 153,
|
||||
scores: 0.686229,
|
||||
)
|
||||
```
|
||||
运行完成可视化结果如下图所示
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/184588768-45ee673b-ef1f-40f4-9fbd-6b1a9ce17c59.png", width=512px, height=256px />
|
||||
</div>
|
||||
|
||||
## PaddleClasModel Python接口
|
||||
## PaddleSegModel Python接口
|
||||
|
||||
```
|
||||
fd.vision.classification.PaddleClasModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
|
||||
fd.vision.segmentation.PaddleSegModel(model_file, params_file, config_file, runtime_option=None, model_format=Frontend.PADDLE)
|
||||
```
|
||||
|
||||
PaddleClas模型加载和初始化，其中model_file, params_file为训练模型导出的Paddle inference文件，具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleClas/blob/release/2.4/docs/zh_CN/inference_deployment/export_model.md#2-%E5%88%86%E7%B1%BB%E6%A8%A1%E5%9E%8B%E5%AF%BC%E5%87%BA)
|
||||
PaddleSeg模型加载和初始化，其中model_file, params_file以及config_file为训练模型导出的Paddle inference文件，具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleSeg/blob/release/2.6/docs/model_export_cn.md)
|
||||
|
||||
**参数**
|
||||
|
||||
@@ -53,7 +50,7 @@ PaddleClas模型加载和初始化，其中model_file, params_file为训练模
|
||||
### predict函数
|
||||
|
||||
> ```
|
||||
> PaddleClasModel.predict(input_image, topk=1)
|
||||
> PaddleSegModel.predict(input_image)
|
||||
> ```
|
||||
>
|
||||
> 模型预测结口，输入图像直接输出检测结果。
|
||||
@@ -61,15 +58,22 @@ PaddleClas模型加载和初始化，其中model_file, params_file为训练模
|
||||
> **参数**
|
||||
>
|
||||
> > * **input_image**(np.ndarray): 输入数据，注意需为HWC，BGR格式
|
||||
> > * **topk**(int):返回预测概率最高的topk个分类结果
|
||||
|
||||
> **返回**
|
||||
>
|
||||
> > 返回`fastdeploy.vision.ClassifyResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> > 返回`fastdeploy.vision.SegmentationResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
|
||||
### 类成员属性
|
||||
#### 预处理参数
|
||||
用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
|
||||
|
||||
> > * **is_vertical_screen**(bool): PP-HumanSeg系列模型通过设置此参数为`true`表明输入图片是竖屏，即height大于width的图片
|
||||
|
||||
#### 后处理参数
|
||||
> > * **with_softmax**(bool): 当模型导出时，并未指定`with_softmax`参数，可通过此设置此参数为`true`，将预测的输出分割标签（label_map）对应的概率结果(score_map)做softmax归一化处理
|
||||
|
||||
## 其它文档
|
||||
|
||||
- [PaddleClas 模型介绍](..)
|
||||
- [PaddleClas C++部署](../cpp)
|
||||
- [PaddleSeg 模型介绍](..)
|
||||
- [PaddleSeg C++部署](../cpp)
|
||||
- [模型预测结果说明](../../../../../docs/api/vision_results/)
|
||||
|
||||
@@ -8,11 +8,9 @@ def parse_arguments():
|
||||
import ast
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"--model", required=True, help="Path of PaddleClas model.")
|
||||
"--model", required=True, help="Path of PaddleSeg model.")
|
||||
parser.add_argument(
|
||||
"--image", type=str, required=True, help="Path of test image file.")
|
||||
parser.add_argument(
|
||||
"--topk", type=int, default=1, help="Return topk results.")
|
||||
parser.add_argument(
|
||||
"--device",
|
||||
type=str,
|
||||
@@ -43,14 +41,17 @@ args = parse_arguments()
|
||||
|
||||
# 配置runtime，加载模型
|
||||
runtime_option = build_option(args)
|
||||
model_file = os.path.join(args.model, "inference.pdmodel")
|
||||
params_file = os.path.join(args.model, "inference.pdiparams")
|
||||
config_file = os.path.join(args.model, "inference_cls.yaml")
|
||||
#model = fd.vision.classification.PaddleClasModel(model_file, params_file, config_file, runtime_option=runtime_option)
|
||||
model = fd.vision.classification.ResNet50vd(
|
||||
model_file = os.path.join(args.model, "model.pdmodel")
|
||||
params_file = os.path.join(args.model, "model.pdiparams")
|
||||
config_file = os.path.join(args.model, "deploy.yaml")
|
||||
model = fd.vision.segmentation.PaddleSegModel(
|
||||
model_file, params_file, config_file, runtime_option=runtime_option)
|
||||
|
||||
# 预测图片分类结果
|
||||
im = cv2.imread(args.image)
|
||||
result = model.predict(im, args.topk)
|
||||
result = model.predict(im)
|
||||
print(result)
|
||||
|
||||
# 可视化结果
|
||||
vis_im = fd.vision.visualize.vis_segmentation(im, result)
|
||||
cv2.imwrite("vis_img.png", vis_im)
|
||||
|
||||
Reference in New Issue
Block a user