Skip to content

M
models

PaddlePaddle / models
大约 1 年 前同步成功

通知 222
Star 6828
Fork 2962
M
models
未验证 提交 6835becc 编写于 作者: T totorolin 提交者： GitHub
浏览文件
操作

Add fastdeploy.md (#5664) 

* Add files via upload

* Delete fastdeploy_cn.md

* Delete fastdeploy_en.md

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload

* Add files via upload
上级 0defbf34
显示空白变更内容
内联 并排
Showing with 1116 addition and 0 deletion
modelcenter/ERNIE-3.0/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
# 下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/text/ernie-3.0/python
# 下载AFQMC数据集的微调后的ERNIE 3.0模型
wget https://bj.bcebos.com/fastdeploy/models/ernie-3.0/ernie-3.0-medium-zh-afqmc.tgz
tar xvfz ernie-3.0-medium-zh-afqmc.tgz
# CPU 推理
python seq_cls_infer.py --device cpu --model_dir ernie-3.0-medium-zh-afqmc
# GPU 推理
python seq_cls_infer.py --device gpu --model_dir ernie-3.0-medium-zh-afqmc
```
运行完成后返回的结果如下：
```bash
[INFO] fastdeploy/runtime.cc(469)::Init Runtime initialized with Backend::ORT in Device::CPU.
Batch id:0, example id:0, sentence1:花呗收款额度限制, sentence2:收钱码，对花呗支付的金额有限制吗, label:1, similarity:0.5819
Batch id:1, example id:0, sentence1:花呗支持高铁票支付吗, sentence2:为什么友付宝不支持花呗付款, label:0, similarity:0.9979
```
### 参数说明
`seq_cls_infer.py` 除了以上示例的命令行参数，还支持更多命令行参数的设置。以下为各命令行参数的说明。
| 参数 |参数说明 |
|----------|--------------|
|--model_dir | 指定部署模型的目录， |
|--batch_size |最大可测的 batch size，默认为 1|
|--max_length |最大序列长度，默认为 128|
|--device | 运行的设备，可选范围: ['cpu', 'gpu']，默认为'cpu' |
|--backend | 支持的推理后端，可选范围: ['onnx_runtime', 'paddle', 'openvino', 'tensorrt', 'paddle_tensorrt']，默认为'onnx_runtime' |
|--use_fp16 | 是否使用FP16模式进行推理。使用tensorrt和paddle_tensorrt后端时可开启，默认为False |
|--use_fast| 是否使用FastTokenizer加速分词阶段。默认为True|
\ No newline at end of file
modelcenter/ERNIE-3.0/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/text/ernie-3.0/python
# download the fine-tuned ERNIE 3.0 model trained from the AFQMC dataset
wget https://bj.bcebos.com/fastdeploy/models/ernie-3.0/ernie-3.0-medium-zh-afqmc.tgz
tar xvfz ernie-3.0-medium-zh-afqmc.tgz
# CPU deployment
python seq_cls_infer.py --device cpu --model_dir ernie-3.0-medium-zh-afqmc
# GPU deployment
python seq_cls_infer.py --device gpu --model_dir ernie-3.0-medium-zh-afqmc
```
The results returned after the operation is completed are as follows:
```bash
[INFO] fastdeploy/runtime.cc(469)::Init Runtime initialized with Backend::ORT in Device::CPU.
Batch id:0, example id:0, sentence1:花呗收款额度限制, sentence2:收钱码，对花呗支付的金额有限制吗, label:1, similarity:0.5819
Batch id:1, example id:0, sentence1:花呗支持高铁票支付吗, sentence2:为什么友付宝不支持花呗付款, label:0, similarity:0.9979
```
### Parameter Description
`seq_cls_infer.py` In addition to the command line parameters in the above example, more command line parameters are also supported. The following is a description of each command line parameter.
| Parameter |Parameter Description |
|----------|--------------|
|--model_dir | Specify the directory where the model is deployed， |
|--batch_size |Maximum measurable batch size，default 1|
|--max_length |Maximum sequence length，default 128|
|--device | equipment running，Optional range: ['cpu', 'gpu']，default'cpu' |
|--backend | Supported Inference Backends，Optional range: ['onnx_runtime', 'paddle', 'openvino', 'tensorrt', 'paddle_tensorrt']，default 'onnx_runtime' |
|--use_fp16 | Whether to use FP16 mode for inference。Use tensorrt and paddle_tensorrt can be turned on when backend，default False |
|--use_fast| Whether to use FastTokenizer to speed up the word segmentation stage。default True|
\ No newline at end of file
modelcenter/PP-HGNet/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
# 下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python
# 下载HGNet模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PPHGNet_tiny_ssld_infer.tgz
tar xvfz PPHGNet_tiny_ssld_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
# CPU推理
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU推理
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
# 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 PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
# IPU推理（注意：IPU推理首次运行会有序列化模型的操作，有一定耗时，需要耐心等待）
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
运行完成后返回的结果如下：
```bash
==============================PPHGNet_tiny_ssld==============================
cpu_label: 153, cpu_score: 0.536040
ipu_label: 153, ipu_score: 0.536039
==============================PPHGNet_tiny_ssld==============================
```
\ No newline at end of file
modelcenter/PP-HGNet/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python
# download HGNet model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/PPHGNet_tiny_ssld_infer.tgz
tar xvfz PPHGNet_tiny_ssld_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
# CPU deployment
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU deployment
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
#TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
#IPU inference (note: the first run of IPU inference will have serialized model operations, which will take a certain amount of time, so you need to wait patiently)
python infer.py --model PPHGNet_tiny_ssld_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
```
The results returned after the operation is completed are as follows：
```bash
==============================PPHGNet_tiny_ssld==============================
cpu_label: 153, cpu_score: 0.536040
ipu_label: 153, ipu_score: 0.536039
==============================PPHGNet_tiny_ssld==============================
```
\ No newline at end of file
modelcenter/PP-HumanSegV2/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
# 下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/segmentation/paddleseg/python
# 下载HumanSegV2模型文件和测试图片
wget https://bj.bcebos.com/paddle2onnx/libs/PP_HumanSegV2_Lite_192x192_infer.tgz
tar -xvf PP_HumanSegV2_Lite_192x192_infer.tgz
wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
# CPU推理
python infer.py --model PP_HumanSegV2_Lite_192x192_infer --image cityscapes_demo.png --device cpu
# GPU推理
python infer.py --model PP_HumanSegV2_Lite_192x192_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 PP_HumanSegV2_Lite_192x192_infer --image cityscapes_demo.png --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-HumanSegV2/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/segmentation/paddleseg/python
# download HumanSegV2 model and test image
wget https://bj.bcebos.com/paddle2onnx/libs/PP_HumanSegV2_Lite_192x192_infer.tgz
tar -xvf PP_HumanSegV2_Lite_192x192_infer.tgz
wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
# CPU deployment
python infer.py --model PP_HumanSegV2_Lite_192x192_infer --image cityscapes_demo.png --device cpu
# GPU deployment
python infer.py --model PP_HumanSegV2_Lite_192x192_infer --image cityscapes_demo.png --device gpu
#TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --model PP_HumanSegV2_Lite_192x192_infer --image cityscapes_demo.png --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-LCNet/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python
# 下载LCNet模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PPLCNet_x1_0_infer.tgz
tar -xvf PPLCNet_x1_0_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
# CPU推理
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU推理
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
# 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 PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
# IPU推理（注意：IPU推理首次运行会有序列化模型的操作，有一定耗时，需要耐心等待）
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
```
运行完成后返回的结果如下：
```bash
==============================PPLCNet_x1_0==============================
cpu_label: 153, cpu_score: 0.612086
ipu_label: 153, ipu_score: 0.612087
==============================PPLCNet_x1_0==============================
```
\ No newline at end of file
modelcenter/PP-LCNet/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python
# download LCNet model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/PPLCNet_x1_0_infer.tgz
tar -xvf PPLCNet_x1_0_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
# CPU deployment
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU deployment
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
#TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
#IPU inference (note: the first run of IPU inference will have serialized model operations, which will take a certain amount of time, so you need to wait patiently)
python infer.py --model PPLCNet_x1_0_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
```
The results returned after the operation is completed are as follows：
```bash
==============================PPLCNet_x1_0==============================
cpu_label: 153, cpu_score: 0.612086
ipu_label: 153, ipu_score: 0.612087
==============================PPLCNet_x1_0==============================
```
\ No newline at end of file
modelcenter/PP-LCNetV2/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python
# 下载LCNetv2模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PPLCNetV2_base_infer.tgz
tar -xvf PPLCNetV2_base_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
# CPU推理
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU推理
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
# 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 PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
# IPU推理（注意：IPU推理首次运行会有序列化模型的操作，有一定耗时，需要耐心等待）
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
```
运行完成后返回的结果如下：
```bash
==============================PPLCNetV2_base==============================
cpu_label: 332, cpu_score: 0.278354
ipu_label: 332, ipu_score: 0.278357
==============================PPLCNetV2_base==============================
```
\ No newline at end of file
modelcenter/PP-LCNetV2/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/classification/paddleclas/python
# download LCNetv2 model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/PPLCNetV2_base_infer.tgz
tar -xvf PPLCNetV2_base_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
# CPU deployment
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU deployment
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
#TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
#IPU inference (note: the first run of IPU inference will have serialized model operations, which will take a certain amount of time, so you need to wait patiently)
python infer.py --model PPLCNetV2_base_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
```
The results returned after the operation is completed are as follows：
```bash
==============================PPLCNetV2_base==============================
cpu_label: 332, cpu_score: 0.278354
ipu_label: 332, ipu_score: 0.278357
==============================PPLCNetV2_base==============================
```
\ No newline at end of file
modelcenter/PP-MSVSR/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/sr/ppmsvsr/python
# 下载VSR模型文件和测试视频
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-MSVSR_reds_x4.tar
tar -xvf PP-MSVSR_reds_x4.tar
wget https://bj.bcebos.com/paddlehub/fastdeploy/vsr_src.mp4
# CPU推理
python infer.py --model PP-MSVSR_reds_x4 --video person.mp4 --frame_num 2 --device cpu
# GPU推理
python infer.py --model PP-MSVSR_reds_x4 --video person.mp4 --frame_num 2 --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 PP-MSVSR_reds_x4 --video person.mp4 --frame_num 2 --device gpu --use_trt True
```
运行完成可视化结果如下图所示:
<div align="center">
<img src="https://user-images.githubusercontent.com/44053467/200456062-426b047a-3571-4463-94cf-c8d02ca25d16.png" width = "50%" >
</div>
\ No newline at end of file
modelcenter/PP-MSVSR/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/sr/ppmsvsr/python
# download VSR model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-MSVSR_reds_x4.tar
tar -xvf PP-MSVSR_reds_x4.tar
wget https://bj.bcebos.com/paddlehub/fastdeploy/vsr_src.mp4
# CPU deployment
python infer.py --model PP-MSVSR_reds_x4 --video person.mp4 --frame_num 2 --device cpu
# GPU deployment
python infer.py --model PP-MSVSR_reds_x4 --video person.mp4 --frame_num 2 --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --model PP-MSVSR_reds_x4 --video person.mp4 --frame_num 2 --device gpu --use_trt True
```
The results of the completed visualisation are shown below:
<div align="center">
<img src="https://user-images.githubusercontent.com/44053467/200456062-426b047a-3571-4463-94cf-c8d02ca25d16.png" width = "50%" >
</div>
\ No newline at end of file
modelcenter/PP-Matting/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/matting/ppmatting/python
# 下载PP-Matting模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz
tar -xvf PP-Matting-512.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
# CPU推理
python infer.py --model PP-Matting-512 --image matting_input.jpg --bg matting_bgr.jpg --device cpu
# GPU推理
python infer.py --model PP-Matting-512 --image matting_input.jpg --bg matting_bgr.jpg --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 PP-Matting-512 --image matting_input.jpg --bg matting_bgr.jpg --device gpu --use_trt True
```
运行完成可视化结果如下图所示
<div width="840">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852040-759da522-fca4-4786-9205-88c622cd4a39.jpg">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852587-48895efc-d24a-43c9-aeec-d7b0362ab2b9.jpg">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852116-cf91445b-3a67-45d9-a675-c69fe77c383a.jpg">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852554-6960659f-4fd7-4506-b33b-54e1a9dd89bf.jpg">
</div>
\ No newline at end of file
modelcenter/PP-Matting/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/matting/ppmatting/python
# download PP-Matting model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP-Matting-512.tgz
tar -xvf PP-Matting-512.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_input.jpg
wget https://bj.bcebos.com/paddlehub/fastdeploy/matting_bgr.jpg
# CPU deployment
python infer.py --model PP-Matting-512 --image matting_input.jpg --bg matting_bgr.jpg --device cpu
# GPU deployment
python infer.py --model PP-Matting-512 --image matting_input.jpg --bg matting_bgr.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --model PP-Matting-512 --image matting_input.jpg --bg matting_bgr.jpg --device gpu --use_trt True
```
The results of the completed visualisation are shown below:
<div width="840">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852040-759da522-fca4-4786-9205-88c622cd4a39.jpg">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852587-48895efc-d24a-43c9-aeec-d7b0362ab2b9.jpg">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852116-cf91445b-3a67-45d9-a675-c69fe77c383a.jpg">
<img width="200" height="200" float="left" src="https://user-images.githubusercontent.com/67993288/186852554-6960659f-4fd7-4506-b33b-54e1a9dd89bf.jpg">
</div>
\ No newline at end of file
modelcenter/PP-OCRv2/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
# 下载模型,图片和字典文件
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
tar -xvf ch_PP-OCRv2_det_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
wgethttps://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
tar -xvf ch_PP-OCRv2_rec_infer.tar
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/ocr/PP-OCRv2/python/
# CPU推理
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
# GPU推理
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
# GPU上使用TensorRT推理
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
```
运行完成可视化结果如下图所示
<img width="640" src="https://user-images.githubusercontent.com/109218879/185826024-f7593a0c-1bd2-4a60-b76c-15588484fa08.jpg">
\ No newline at end of file
modelcenter/PP-OCRv2/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download model, image and dictionary files
wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar
tar -xvf ch_PP-OCRv2_det_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
wgethttps://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar
tar -xvf ch_PP-OCRv2_rec_infer.tar
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/ocr/PP-OCRv2/python/
# CPU deployment
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
# GPU deployment
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --det_model ch_PP-OCRv2_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv2_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
```
The results of the completed visualisation are shown below
<img width="640" src="https://user-images.githubusercontent.com/109218879/185826024-f7593a0c-1bd2-4a60-b76c-15588484fa08.jpg">
\ No newline at end of file
modelcenter/PP-OCRv3/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
# 下载模型,图片和字典文件
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
tar xvf ch_PP-OCRv3_det_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
tar xvf ch_PP-OCRv3_rec_infer.tar
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/ocr/PP-OCRv3/python/
# CPU推理
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
# GPU推理
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
# GPU上使用TensorRT推理
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
```
运行完成可视化结果如下图所示
<img width="640" src="https://user-images.githubusercontent.com/109218879/185826024-f7593a0c-1bd2-4a60-b76c-15588484fa08.jpg">
\ No newline at end of file
modelcenter/PP-OCRv3/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download model, image and dictionary files
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar
tar xvf ch_PP-OCRv3_det_infer.tar
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar
tar -xvf ch_ppocr_mobile_v2.0_cls_infer.tar
wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar
tar xvf ch_PP-OCRv3_rec_infer.tar
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/doc/imgs/12.jpg
wget https://gitee.com/paddlepaddle/PaddleOCR/raw/release/2.6/ppocr/utils/ppocr_keys_v1.txt
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd examples/vison/ocr/PP-OCRv3/python/
# CPU deployment
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device cpu
# GPU deployment
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer.py --det_model ch_PP-OCRv3_det_infer --cls_model ch_ppocr_mobile_v2.0_cls_infer --rec_model ch_PP-OCRv3_rec_infer --rec_label_file ppocr_keys_v1.txt --image 12.jpg --device gpu --backend trt
```
The results of the completed visualisation are shown below
<img width="640" src="https://user-images.githubusercontent.com/109218879/185826024-f7593a0c-1bd2-4a60-b76c-15588484fa08.jpg">
\ No newline at end of file
modelcenter/PP-PicoDet/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
#下载PPYOLOE模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/picodet_l_320_coco_lcnet.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf picodet_l_320_coco_lcnet.tgz
# CPU推理
python infer_picodet.py --model_dir picodet_l_320_coco_lcnet --image 000000014439.jpg --device cpu
# GPU推理
python infer_picodet.py --model_dir picodet_l_320_coco_lcnet --image 000000014439.jpg --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_picodet.py --model_dir picodet_l_320_coco_lcnet --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-PicoDet/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
# download PicoDet model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/picodet_l_320_coco_lcnet.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf picodet_l_320_coco_lcnet.tgz
# CPU deployment
python infer_picodet.py --model_dir picodet_l_320_coco_lcnet --image 000000014439.jpg --device cpu
# GPU deployment
python infer_picodet.py --model_dir picodet_l_320_coco_lcnet --image 000000014439.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer_picodet.py --model_dir picodet_l_320_coco_lcnet --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-TinyPose/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/keypointdetection/tiny_pose/python
# 下载PP-TinyPose模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
tar -xvf PP_TinyPose_256x192_infer.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
# CPU推理
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device cpu
# GPU推理
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --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 pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu --use_trt True
```
运行完成可视化结果如下图所示:
<div align="center">
<img src="https://user-images.githubusercontent.com/16222477/196386764-dd51ad56-c410-4c54-9580-643f282f5a83.jpeg", width=359px, height=423px />
</div>
\ No newline at end of file
modelcenter/PP-TinyPose/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/keypointdetection/tiny_pose/python
# download TinyPose model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
tar -xvf PP_TinyPose_256x192_infer.tgz
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
# CPU deployment
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device cpu
# GPU deployment
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu --use_trt True
```
The results of the completed visualisation are shown below:
<div align="center">
<img src="https://user-images.githubusercontent.com/16222477/196386764-dd51ad56-c410-4c54-9580-643f282f5a83.jpeg", width=359px, height=423px />
</div>
\ No newline at end of file
modelcenter/PP-YOLO/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
#下载YOLO模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyolo_r50vd_dcn_1x_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyolo_r50vd_dcn_1x_coco.tgz
# CPU推理
python infer_ppyolo.py --model_dir ppyolo_r50vd_dcn_1x_coco --image 000000014439.jpg --device cpu
# GPU推理
python infer_ppyolo.py --model_dir ppyolo_r50vd_dcn_1x_coco --image 000000014439.jpg --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_ppyolo.py --model_dir ppyolo_r50vd_dcn_1x_coco --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-YOLO/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
# download YOLO model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyolo_r50vd_dcn_1x_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyolo_r50vd_dcn_1x_coco.tgz
# CPU deployment
python infer_ppyolo.py --model_dir ppyolo_r50vd_dcn_1x_coco --image 000000014439.jpg --device cpu
# GPU deployment
python infer_ppyolo.py --model_dir ppyolo_r50vd_dcn_1x_coco --image 000000014439.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer_ppyolo.py --model_dir ppyolo_r50vd_dcn_1x_coco --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-YOLOE+/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
#下载YOLOE+模型文件和测试图片
wget https://bj.bcebos.com/fastdeploy/models/ppyoloe_plus_crn_m_80e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyoloe_plus_crn_m_80e_coco.tgz
# CPU推理
python infer_ppyoloe.py --model_dir ppyoloe_plus_crn_m_80e_coco --image 000000014439.jpg --device cpu
# GPU推理
python infer_ppyoloe.py --model_dir ppyoloe_plus_crn_m_80e_coco --image 000000014439.jpg --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_ppyoloe.py --model_dir ppyoloe_plus_crn_m_80e_coco --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-YOLOE+/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
# download PPYOLOE model and test image
wget https://bj.bcebos.com/fastdeploy/models/ppyoloe_plus_crn_m_80e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyoloe_plus_crn_m_80e_coco.tgz
# CPU deployment
python infer_ppyoloe.py --model_dir ppyoloe_plus_crn_m_80e_coco --image 000000014439.jpg --device cpu
# GPU deployment
python infer_ppyoloe.py --model_dir ppyoloe_plus_crn_m_80e_coco --image 000000014439.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer_ppyoloe.py --model_dir ppyoloe_plus_crn_m_80e_coco --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-YOLOE/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
#下载PPYOLOE模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyoloe_crn_l_300e_coco.tgz
# CPU推理
python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device cpu
# GPU推理
python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --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_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device gpu --use_trt True
```
运行完成可视化结果如下图所示
<div align="center">
<img src="https://user-images.githubusercontent.com/19339784/184326520-7075e907-10ed-4fad-93f8-52d0e35d4964.jpg", width=480px, height=320px />
</div>
\ No newline at end of file
modelcenter/PP-YOLOE/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
# download PPYOLOE model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyoloe_crn_l_300e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyoloe_crn_l_300e_coco.tgz
# CPU deployment
python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device cpu
# GPU deployment
python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer_ppyoloe.py --model_dir ppyoloe_crn_l_300e_coco --image 000000014439.jpg --device gpu --use_trt True
```
The results of the completed visualisation are shown below:
<div align="center">
<img src="https://user-images.githubusercontent.com/19339784/184326520-7075e907-10ed-4fad-93f8-52d0e35d4964.jpg", width=480px, height=320px />
</div>
\ No newline at end of file
modelcenter/PP-YOLOv2/fastdeploy_cn.md 0 → 100644
浏览文件 @ 6835becc
## 0. 全场景高性能AI推理部署工具 FastDeploy
FastDeploy 是一款**全场景、易用灵活、极致高效**的AI推理部署工具。提供开箱即用的**云边端**部署体验, 支持超过 150+ Text, Vision, Speech和跨模态模型，实现了AI模型**端到端的优化加速**。目前支持的硬件包括 **X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU**等10类云边端的硬件，通过一行代码切换不同推理后端和硬件。
使用 FastDeploy 3步即可搞定AI模型部署：（1）安装FastDeploy预编译包（2）调用FastDeploy的API实现部署代码 （3）推理部署。
**注** : 本文档下载 FastDeploy 示例来完成高性能部署体验；仅展示X86 CPU、NVIDIA GPU的推理，且默认已经准备好GPU环境（如 CUDA >= 11.2等），如需要部署其他硬件或者完整了解 FastDeploy 部署能力，请参考 [FastDeploy的GitHub仓库](https://github.com/PaddlePaddle/FastDeploy)
## 1. 安装FastDeploy预编译包
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. 运行部署示例
```
#下载部署示例代码
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
#下载YOLOv2模型文件和测试图片
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyolov2_r101vd_dcn_365e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyolov2_r101vd_dcn_365e_coco.tgz
# CPU推理
python infer_ppyolo.py --model_dir ppyolov2_r101vd_dcn_365e_coco --image 000000014439.jpg --device cpu
# GPU推理
python infer_ppyolo.py --model_dir ppyolov2_r101vd_dcn_365e_coco --image 000000014439.jpg --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_ppyolo.py --model_dir ppyolov2_r101vd_dcn_365e_coco --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
modelcenter/PP-YOLOv2/fastdeploy_en.md 0 → 100644
浏览文件 @ 6835becc
## 0. FastDeploy
FastDeploy is an Easy-to-use and High Performance AI model deployment toolkit for Cloud, Mobile and Edge with out-of-the-box and unified experience, end-to-end optimization for over 150+ Text, Vision, Speech and Cross-modal AI models. FastDeploy Supports AI model deployment on
**X86 CPU、NVIDIA GPU、ARM CPU、XPU、NPU、IPU** etc. You can switch different inference backends and hardware with a single line of code.
Deploying AI model in 3 steps with FastDeploy: (1)Install FastDeploy SDK; (2)Use FastDeploy's API to implement the deployment code; (3) Deploy.
**Notes** : This document downloads FastDeploy examples to complete the high performance deployment experience; only X86 CPUs, NVIDIA GPUs are shown for reasoning and GPU environments are ready by default (e.g. CUDA >= 11.2, etc.), if you need to deploy AI model on other hardware or learn about FastDeploy's full capabilities, please refer to [FastDeploy GitHub](https://github.com/PaddlePaddle/FastDeploy).
## 1. Install FastDeploy SDK
```
pip install fastdeploy-gpu-python==0.0.0 -f https://www.paddlepaddle.org.cn/whl/fastdeploy_nightly_build.html
```
## 2. Run Deployment Example
```
# download deployment example
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/detection/paddledetection/python/
# download YOLOv2 model and test image
wget https://bj.bcebos.com/paddlehub/fastdeploy/ppyolov2_r101vd_dcn_365e_coco.tgz
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
tar xvf ppyolov2_r101vd_dcn_365e_coco.tgz
# CPU deployment
python infer_ppyolo.py --model_dir ppyolov2_r101vd_dcn_365e_coco --image 000000014439.jpg --device cpu
# GPU deployment
python infer_ppyolo.py --model_dir ppyolov2_r101vd_dcn_365e_coco --image 000000014439.jpg --device gpu
# TensorRT inference on GPU (note: if you run TensorRT inference the first time, there is a serialization of the model, which is time-consuming and requires patience)
python infer_ppyolo.py --model_dir ppyolov2_r101vd_dcn_365e_coco --image 000000014439.jpg --device gpu --use_trt True
```
\ No newline at end of file
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或