apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Quantization] Improve the usage of fastdeploy tools (#722)

Browse Source 
Improve the usage of fastdeploy tools
This commit is contained in:
yunyaoXYY
2022-11-28 16:55:32 +08:00
committed by GitHub
parent 9ae5c24607
commit ae3487560d
10 changed files with 24 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
python/requirements.txt
View File

@@ -3,5 +3,5 @@ requests
tqdm tqdm
numpy numpy
opencv-python opencv-python
fastdeploy-tools fastdeploy-tools==0.0.1
pyyaml pyyaml

6
tools/README.md
View File

@@ -26,14 +26,14 @@ python setup.py install
```bash ```bash
# 通过pip安装fastdeploy-tools. 此工具包目前支持模型一键自动化压缩和模型转换的功能. # 通过pip安装fastdeploy-tools. 此工具包目前支持模型一键自动化压缩和模型转换的功能.
# FastDeploy的python包已包含此工具, 不需重复安装. # FastDeploy的python包已包含此工具, 不需重复安装.
pip install fastdeploy-tools==0.0.0 pip install fastdeploy-tools==0.0.1
``` ```
### 一键模型自动化压缩工具的使用 ### 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. 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 ```bash
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/' fastdeploy 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](./common_tools/auto_compression/README.md) 详细使用文档请参考[FastDeploy一键模型自动化压缩工具](./common_tools/auto_compression/README.md)
@@ -69,7 +69,7 @@ python setup.py install
按照以上步骤成功安装后,即可使用 FastDeploy 一键转换工具, 示例如下: 按照以上步骤成功安装后,即可使用 FastDeploy 一键转换工具, 示例如下:
```bash ```bash
fastdeploy --convert --framework onnx --model yolov5s.onnx --save_dir pd_model fastdeploy convert --framework onnx --model yolov5s.onnx --save_dir pd_model
``` ```
更多详细内容可参考[X2Paddle](https://github.com/PaddlePaddle/X2Paddle) 更多详细内容可参考[X2Paddle](https://github.com/PaddlePaddle/X2Paddle)

6
tools/README_EN.md
View File

@@ -26,14 +26,14 @@ python setup.py install
```bash ```bash
# Installing fastdeploy-tools via pip # Installing fastdeploy-tools via pip
# This tool is included in the python installer of FastDeploy, so you don't need to install it again. # This tool is included in the python installer of FastDeploy, so you don't need to install it again.
pip install fastdeploy-tools==0.0.0 pip install fastdeploy-tools==0.0.1
``` ```
### The Usage of One-Click Model Auto Compression Tool ### 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. After the above steps are successfully installed, you can use FastDeploy one-click model automation compression tool, as shown in the following example.
```bash ```bash
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/' fastdeploy 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](./common_tools/auto_compression/README_EN.md) For detailed documentation, please refer to [FastDeploy One-Click Model Auto Compression Tool](./common_tools/auto_compression/README_EN.md)
@@ -69,7 +69,7 @@ python setup.py install
After successful installation according to the above steps, you can use the FastDeploy one-click conversion tool. The example is as follows: After successful installation according to the above steps, you can use the FastDeploy one-click conversion tool. The example is as follows:
```bash ```bash
fastdeploy --convert --framework onnx --model yolov5s.onnx --save_dir pd_model fastdeploy convert --framework onnx --model yolov5s.onnx --save_dir pd_model
``` ```
For more details, please refer to[X2Paddle](https://github.com/PaddlePaddle/X2Paddle) For more details, please refer to[X2Paddle](https://github.com/PaddlePaddle/X2Paddle)

8
tools/common_tools/auto_compression/README.md
View File

@@ -40,10 +40,10 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_val_320.tar.gz
tar -xvf 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 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. 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 ```shell
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/' fastdeploy compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
``` ```
##### 3.参数说明 ##### 3.参数说明
@@ -74,12 +74,12 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_train_320.tar
tar -xvf 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 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. 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 ```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. # 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 export CUDA_VISIBLE_DEVICES=0
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/' fastdeploy compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/'
``` ```
##### 3.参数说明 ##### 3.参数说明

8
tools/common_tools/auto_compression/README_EN.md
View File

@@ -46,12 +46,12 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_val_320.tar.gz
tar -xvf 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 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. 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 ```shell
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/' fastdeploy compress --config_path=./configs/detection/yolov5s_quant.yaml --method='PTQ' --save_dir='./yolov5s_ptq_model/'
``` ```
[notice] PTQ is short for post-training quantization [notice] PTQ is short for post-training quantization
@@ -83,14 +83,14 @@ wget https://bj.bcebos.com/paddlehub/fastdeploy/COCO_val_320.tar.gz
tar -xvf COCO_val_320.tar.gz tar -xvf COCO_val_320.tar.gz
``` ```
##### 2.Use fastdeploy --auto_compress command to compress models ##### 2.Use fastdeploy 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. 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 ```shell
# Please specify the single card GPU before training, otherwise it may get stuck during the training process. # Please specify the single card GPU before training, otherwise it may get stuck during the training process.
export CUDA_VISIBLE_DEVICES=0 export CUDA_VISIBLE_DEVICES=0
fastdeploy --auto_compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/' fastdeploy compress --config_path=./configs/detection/yolov5s_quant.yaml --method='QAT' --save_dir='./yolov5s_qat_model/'
``` ```
##### 3.Parameters ##### 3.Parameters

0
tools/common_tools/auto_compression/__init__.py Normal file
View File

1
tools/common_tools/auto_compression/fd_auto_compress/__init__.py
View File

@@ -1 +0,0 @@
import fd_auto_compress

2
tools/common_tools/auto_compression/fd_auto_compress/fd_auto_compress.py
View File

@@ -22,7 +22,7 @@ import paddle
from paddleslim.common import load_config, load_onnx_model from paddleslim.common import load_config, load_onnx_model
from paddleslim.auto_compression import AutoCompression from paddleslim.auto_compression import AutoCompression
from paddleslim.quant import quant_post_static from paddleslim.quant import quant_post_static
from fd_auto_compress.dataset import * from .dataset import *
def argsparser(): def argsparser():

18
tools/common_tools/common_tools.py
View File

@@ -4,8 +4,8 @@ import ast
def argsparser(): def argsparser():
parser = argparse.ArgumentParser(description=__doc__) parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('tools', choices=['compress', 'convert'])
## argumentments for auto compression ## argumentments for auto compression
parser.add_argument('--auto_compress', default=False, action='store_true')
parser.add_argument( parser.add_argument(
'--config_path', '--config_path',
type=str, type=str,
@@ -27,7 +27,6 @@ def argsparser():
default='gpu', default='gpu',
help="which device used to compress.") help="which device used to compress.")
## arguments for other x2paddle ## arguments for other x2paddle
parser.add_argument('--convert', default=False, action='store_true')
parser.add_argument( parser.add_argument(
'--framework', '--framework',
type=str, type=str,
@@ -76,16 +75,11 @@ def argsparser():
def main(): def main():
args = argsparser().parse_args() args = argsparser().parse_args()
if args.auto_compress == True: if args.tools == "compress":
try: from .auto_compression.fd_auto_compress.fd_auto_compress import auto_compress
from .auto_compression.fd_auto_compress.fd_auto_compress import auto_compress print("Welcome to use FastDeploy Auto Compression Toolkit!")
print("Welcome to use FastDeploy Auto Compression Toolkit!") auto_compress(args)
auto_compress(args) if args.tools == "convert":
except ImportError:
print(
"Can not start auto compresssion successfully! Please check if you have installed it!"
)
if args.convert == True:
try: try:
import platform import platform
import logging import logging

3
tools/setup.py
View File

@@ -1,10 +1,11 @@
import setuptools import setuptools
long_description = "fastdeploy-tools is a toolkit for FastDeploy, including auto compression .etc.\n\n" 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" long_description += "Usage of auto compression: fastdeploy compress --config_path=./yolov7_tiny_qat_dis.yaml --method='QAT' --save_dir='./v7_qat_outmodel/' \n"
setuptools.setup( setuptools.setup(
name="fastdeploy-tools", # name of package name="fastdeploy-tools", # name of package
version="0.0.1", #version of package
description="A toolkit for FastDeploy.", description="A toolkit for FastDeploy.",
long_description=long_description, long_description=long_description,
long_description_content_type="text/plain", long_description_content_type="text/plain",