mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 08:37:06 +08:00
[Quantization] Change the usage of FastDeploy auto compression tool. (#576)
* Add PaddleOCR Support * Add PaddleOCR Support * Add PaddleOCRv3 Support * Add PaddleOCRv3 Support * Update README.md * Update README.md * Update README.md * Update README.md * Add PaddleOCRv3 Support * Add PaddleOCRv3 Supports * Add PaddleOCRv3 Suport * Fix Rec diff * Remove useless functions * Remove useless comments * Add PaddleOCRv2 Support * Add PaddleOCRv3 & PaddleOCRv2 Support * remove useless parameters * Add utils of sorting det boxes * Fix code naming convention * Fix code naming convention * Fix code naming convention * Fix bug in the Classify process * Imporve OCR Readme * Fix diff in Cls model * Update Model Download Link in Readme * Fix diff in PPOCRv2 * Improve OCR readme * Imporve OCR readme * Improve OCR readme * Improve OCR readme * Imporve OCR readme * Improve OCR readme * Fix conflict * Add readme for OCRResult * Improve OCR readme * Add OCRResult readme * Improve OCR readme * Improve OCR readme * Add Model Quantization Demo * Fix Model Quantization Readme * Fix Model Quantization Readme * Add the function to do PTQ quantization * Improve quant tools readme * Improve quant tool readme * Improve quant tool readme * Add PaddleInference-GPU for OCR Rec model * Add QAT method to fastdeploy-quantization tool * Remove examples/slim for now * Move configs folder * Add Quantization Support for Classification Model * Imporve ways of importing preprocess * Upload YOLO Benchmark on readme * Upload YOLO Benchmark on readme * Upload YOLO Benchmark on readme * Improve Quantization configs and readme * Add support for multi-inputs model * Add backends and params file for YOLOv7 * Add quantized model deployment support for YOLO series * Fix YOLOv5 quantize readme * Fix YOLO quantize readme * Fix YOLO quantize readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Improve quantize YOLO readme * Fix bug, change Fronted to ModelFormat * Change Fronted to ModelFormat * Add examples to deploy quantized paddleclas models * Fix readme * Add quantize Readme * Add quantize Readme * Add quantize Readme * Modify readme of quantization tools * Modify readme of quantization tools * Improve quantization tools readme * Improve quantization readme * Improve PaddleClas quantized model deployment readme * Add PPYOLOE-l quantized deployment examples * Improve quantization tools readme * Improve Quantize Readme * Fix conflicts * Fix conflicts * improve readme * Improve quantization tools and readme * Improve quantization tools and readme * Add quantized deployment examples for PaddleSeg model * Fix cpp readme * Fix memory leak of reader_wrapper function * Fix model file name in PaddleClas quantization examples * Update Runtime and E2E benchmark * Update Runtime and E2E benchmark * Rename quantization tools to auto compression tools * Remove PPYOLOE data when deployed on MKLDNN * Fix readme * Support PPYOLOE with OR without NMS and update readme * Update Readme * Update configs and readme * Update configs and readme * Add Paddle-TensorRT backend in quantized model deploy examples * Support PPYOLOE+ series * Add reused_input_tensors for PPYOLOE * Improve fastdeploy tools usage * improve fastdeploy tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * remove modify * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool * Improve fastdeploy auto compression tool
This commit is contained in:
yunyaoXYY
@@ -3,3 +3,4 @@ requests
|
||||
tqdm
|
||||
numpy
|
||||
opencv-python
|
||||
fd-auto-compress>=0.0.0
|
||||
|
||||
35
tools/README.md
Normal file
35
tools/README.md
Normal file
@@ -0,0 +1,35 @@
|
||||
# FastDeploy 工具包
|
||||
FastDeploy提供了一系列高效易用的工具优化部署体验, 提升推理性能.
|
||||
例如, FastDeploy基于PaddleSlim的Auto Compression Toolkit(ACT), 给用户提供了一键模型自动化压缩的工具, 用户可以轻松地通过一行命令对模型进行自动化压缩, 并在FastDeploy上部署压缩后的模型, 提升推理速度. 本文档将以FastDeploy一键模型自动化压缩工具为例, 介绍如何安装此工具, 并提供相应的使用文档.
|
||||
|
||||
## FastDeploy一键模型自动化压缩工具
|
||||
|
||||
### 环境准备
|
||||
1.用户参考PaddlePaddle官网, 安装develop版本
|
||||
```
|
||||
https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/develop/install/pip/linux-pip.html
|
||||
```
|
||||
|
||||
2.安装PaddleSlim develop版本
|
||||
```bash
|
||||
git clone https://github.com/PaddlePaddle/PaddleSlim.git & cd PaddleSlim
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
3.安装fd-auto-compress一键模型自动化压缩工具
|
||||
```bash
|
||||
# 通过pip安装fd-auto-compress.
|
||||
# FastDeploy的python包已包含此工具, 不需重复安装.
|
||||
pip install fd-auto-compress
|
||||
|
||||
# 在当前目录执行以下命令
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
### 一键模型自动化压缩工具的使用
|
||||
按照以上步骤成功安装后,即可使用FastDeploy一键模型自动化压缩工具, 示例如下.
|
||||
|
||||
```bash
|
||||
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
|
||||
```
|
||||
详细使用文档请参考[FastDeploy一键模型自动化压缩工具](./auto_compression/README.md)
|
||||
35
tools/README_EN.md
Normal file
35
tools/README_EN.md
Normal file
@@ -0,0 +1,35 @@
|
||||
# FastDeploy Toolkit
|
||||
FastDeploy provides a series of efficient and easy-to-use tools to optimize the deployment experience and improve inference performance.
|
||||
For example, based on PaddleSlim's Auto Compression Toolkit (ACT), FastDeploy provides users with a one-click model automation compression tool that allows users to easily compress the model with a single command. This document will take FastDeploy's one-click model automation compression tool as an example, introduce how to install the tool, and provide the corresponding documentation for usage.
|
||||
|
||||
|
||||
## FastDeploy One-Click Model Auto Compression Tool
|
||||
|
||||
### Environmental Preparation
|
||||
1.Install PaddlePaddle develop version
|
||||
```
|
||||
https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/develop/install/pip/linux-pip.html
|
||||
```
|
||||
|
||||
2.Install PaddleSlim dev version
|
||||
```bash
|
||||
git clone https://github.com/PaddlePaddle/PaddleSlim.git & cd PaddleSlim
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
3.Install fd-auto-compress package
|
||||
```bash
|
||||
# Installing fd-auto-compress via pip
|
||||
# This tool is included in the python installer of FastDeploy, so you don't need to install it again.
|
||||
pip install fd-auto-compress
|
||||
|
||||
# Execute in the current directory
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
### The Usage of One-Click Model Auto Compression Tool
|
||||
After the above steps are successfully installed, you can use FastDeploy one-click model automation compression tool, as shown in the following example.
|
||||
```bash
|
||||
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
|
||||
```
|
||||
For detailed documentation, please refer to [FastDeploy One-Click Model Auto Compression Tool](./auto_compression/README.md)
|
||||
@@ -18,8 +18,11 @@ python setup.py install
|
||||
```
|
||||
|
||||
### fastdeploy-auto-compression 一键模型自动化压缩工具安装方式
|
||||
用户在当前目录下，运行如下命令:
|
||||
```
|
||||
# 通过pip安装fd-auto-compress包
|
||||
pip install fd-auto-compress
|
||||
|
||||
# 并在上一层目录(非本级目录)执行如下命令
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
@@ -43,12 +46,11 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_val_320.tar.gz
|
||||
tar -xvf COCO_val_320.tar.gz
|
||||
```
|
||||
|
||||
##### 2.使用fastdeploy_auto_compress命令，执行一键模型自动化压缩:
|
||||
##### 2.使用fastdeploy --auto_compress命令，执行一键模型自动化压缩:
|
||||
以下命令是对yolov5s模型进行量化, 用户若想量化其他模型, 替换config_path为configs文件夹下的其他模型配置文件即可.
|
||||
```shell
|
||||
fastdeploy_auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
|
||||
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
|
||||
```
|
||||
【说明】离线量化（训练后量化）：post-training quantization，缩写是PTQ
|
||||
|
||||
##### 3.参数说明
|
||||
|
||||
@@ -78,12 +80,12 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_train_320.tar
|
||||
tar -xvf COCO_train_320.tar
|
||||
```
|
||||
|
||||
##### 2.使用fastdeploy_auto_compress命令，执行一键模型自动化压缩:
|
||||
##### 2.使用fastdeploy --auto_compress命令，执行一键模型自动化压缩:
|
||||
以下命令是对yolov5s模型进行量化, 用户若想量化其他模型, 替换config_path为configs文件夹下的其他模型配置文件即可.
|
||||
```shell
|
||||
# 执行命令默认为单卡训练，训练前请指定单卡GPU, 否则在训练过程中可能会卡住.
|
||||
export CUDA_VISIBLE_DEVICES=0
|
||||
fastdeploy_auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/'
|
||||
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/'
|
||||
```
|
||||
|
||||
##### 3.参数说明
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
# FastDeploy One-Click Model Auto Compression
|
||||
|
||||
|
||||
|
||||
FastDeploy, based on PaddleSlim's Auto Compression Toolkit(ACT), provides developers with a one-click model auto compression tool that supports post-training quantization and knowledge distillation training.
|
||||
We take the Yolov5 series as an example to demonstrate how to install and execute FastDeploy's one-click model auto compression.
|
||||
|
||||
@@ -24,9 +22,13 @@ python setup.py install
|
||||
|
||||
### Install Fastdeploy Auto Compression Toolkit
|
||||
|
||||
Run the following command in the current directory
|
||||
Run the following command to install
|
||||
|
||||
```
|
||||
# Install fd-auto-compress package using pip
|
||||
pip install fd-auto-compress
|
||||
|
||||
# Execute the following command in the previous directory (not in the current directory)
|
||||
python setup.py install
|
||||
```
|
||||
|
||||
@@ -52,12 +54,12 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_val_320.tar.gz
|
||||
tar -xvf COCO_val_320.tar.gz
|
||||
```
|
||||
|
||||
##### 2. Run fastdeploy_auto_compress command to compress the model
|
||||
##### 2. Run fastdeploy --auto_compress command to compress the model
|
||||
|
||||
The following command is to quantize the yolov5s model, if developers want to quantize other models, replace the config_path with other model configuration files in the configs folder.
|
||||
|
||||
```shell
|
||||
fastdeploy_quant --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
|
||||
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
|
||||
```
|
||||
|
||||
[notice] PTQ is short for post-training quantization
|
||||
@@ -89,14 +91,14 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_val_320.tar.gz
|
||||
tar -xvf COCO_val_320.tar.gz
|
||||
```
|
||||
|
||||
##### 2.Use fastdeploy_auto_compress command to compress models
|
||||
##### 2.Use fastdeploy --auto_compress command to compress models
|
||||
|
||||
The following command is to quantize the yolov5s model, if developers want to quantize other models, replace the config_path with other model configuration files in the configs folder.
|
||||
|
||||
```shell
|
||||
# Please specify the single card GPU before training, otherwise it may get stuck during the training process.
|
||||
export CUDA_VISIBLE_DEVICES=0
|
||||
fastdeploy_quant --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/'
|
||||
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/'
|
||||
```
|
||||
|
||||
##### 3.Parameters
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
import fd_auto_compress
|
||||
|
||||
@@ -82,13 +82,11 @@ def reader_wrapper(reader, input_list):
|
||||
return gen
|
||||
|
||||
|
||||
def main():
|
||||
def auto_compress(FLAGS):
|
||||
|
||||
#FLAGS needs parse
|
||||
time_s = time.time()
|
||||
|
||||
paddle.enable_static()
|
||||
parser = argsparser()
|
||||
FLAGS = parser.parse_args()
|
||||
|
||||
assert FLAGS.devices in ['cpu', 'gpu', 'xpu', 'npu']
|
||||
paddle.set_device(FLAGS.devices)
|
||||
@@ -189,7 +187,3 @@ def main():
|
||||
|
||||
time_total = time.time() - time_s
|
||||
print("Finish Compression, total time used is : ", time_total, "seconds.")
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
||||
@@ -1,26 +1,25 @@
|
||||
import setuptools
|
||||
import fd_auto_compress
|
||||
|
||||
long_description = "fastdeploy-auto-compression is a toolkit for model auto compression of FastDeploy.\n\n"
|
||||
long_description += "Usage: fastdeploy_auto_compress --config_path=./yolov7_tiny_qat_dis.yaml --method='QAT' --save_dir='../v7_qat_outmodel/' \n"
|
||||
long_description = "fd_auto_compress is a toolkit for model auto compression of FastDeploy.\n\n"
|
||||
long_description += "Usage: fastdeploy --auto_compress --config_path=./yolov7_tiny_qat_dis.yaml --method='QAT' --save_dir='../v7_qat_outmodel/' \n"
|
||||
|
||||
with open("requirements.txt") as fin:
|
||||
REQUIRED_PACKAGES = fin.read()
|
||||
|
||||
setuptools.setup(
|
||||
name="fastdeploy-auto-compression", # name of package
|
||||
name="fd_auto_compress", # name of package
|
||||
description="A toolkit for model auto compression of FastDeploy.",
|
||||
long_description=long_description,
|
||||
long_description_content_type="text/plain",
|
||||
packages=setuptools.find_packages(),
|
||||
author='fastdeploy',
|
||||
author_email='fastdeploy@baidu.com',
|
||||
url='https://github.com/PaddlePaddle/FastDeploy.git',
|
||||
install_requires=REQUIRED_PACKAGES,
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: Apache Software License",
|
||||
"Operating System :: OS Independent",
|
||||
],
|
||||
license='Apache 2.0',
|
||||
entry_points={
|
||||
'console_scripts':
|
||||
['fastdeploy_auto_compress=fd_auto_compress.fd_auto_compress:main', ]
|
||||
})
|
||||
license='Apache 2.0', )
|
||||
|
||||
0
tools/common_tools/__init__.py
Normal file
0
tools/common_tools/__init__.py
Normal file
51
tools/common_tools/common_tools.py
Normal file
51
tools/common_tools/common_tools.py
Normal file
@@ -0,0 +1,51 @@
|
||||
import argparse
|
||||
|
||||
|
||||
def argsparser():
|
||||
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
## argumentments for auto compression
|
||||
parser.add_argument('--auto_compress', default=False, action='store_true')
|
||||
parser.add_argument(
|
||||
'--config_path',
|
||||
type=str,
|
||||
default=None,
|
||||
help="path of compression strategy config.",
|
||||
required=True)
|
||||
parser.add_argument(
|
||||
'--method',
|
||||
type=str,
|
||||
default=None,
|
||||
help="choose PTQ or QAT as quantization method",
|
||||
required=True)
|
||||
parser.add_argument(
|
||||
'--save_dir',
|
||||
type=str,
|
||||
default='./output',
|
||||
help="directory to save compressed model.")
|
||||
parser.add_argument(
|
||||
'--devices',
|
||||
type=str,
|
||||
default='gpu',
|
||||
help="which device used to compress.")
|
||||
|
||||
## arguments for other tools
|
||||
return parser
|
||||
|
||||
|
||||
def main():
|
||||
|
||||
args = argsparser().parse_args()
|
||||
if args.auto_compress == True:
|
||||
try:
|
||||
from fd_auto_compress.fd_auto_compress import auto_compress
|
||||
print("Welcome to use FastDeploy Auto Compression Toolkit!")
|
||||
auto_compress(args)
|
||||
except ImportError:
|
||||
print(
|
||||
"Can not start auto compresssion successfully! Please check if you have installed it!"
|
||||
)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
20
tools/setup.py
Normal file
20
tools/setup.py
Normal file
@@ -0,0 +1,20 @@
|
||||
import setuptools
|
||||
|
||||
long_description = "fastdeploy-tools is a toolkit for FastDeploy, including auto compression .etc.\n\n"
|
||||
long_description += "Usage of auto compression: fastdeploy --auto_compress --config_path=./yolov7_tiny_qat_dis.yaml --method='QAT' --save_dir='./v7_qat_outmodel/' \n"
|
||||
|
||||
setuptools.setup(
|
||||
name="fastdeploy-tools", # name of package
|
||||
description="A toolkit for FastDeploy.",
|
||||
long_description=long_description,
|
||||
long_description_content_type="text/plain",
|
||||
packages=setuptools.find_packages(),
|
||||
classifiers=[
|
||||
"Programming Language :: Python :: 3",
|
||||
"License :: OSI Approved :: Apache Software License",
|
||||
"Operating System :: OS Independent",
|
||||
],
|
||||
license='Apache 2.0',
|
||||
entry_points={
|
||||
'console_scripts': ['fastdeploy = common_tools.common_tools:main', ]
|
||||
})
|
||||
Reference in New Issue
Block a user