mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 16:48:03 +08:00
Add Examples to deploy quantized models (#342)
* 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
This commit is contained in:
yunyaoXYY
28
examples/vision/detection/yolov7/quantize/python/README.md
Normal file
28
examples/vision/detection/yolov7/quantize/python/README.md
Normal file
@@ -0,0 +1,28 @@
|
||||
# YOLOv7量化模型 Python部署示例
|
||||
本目录下提供的`infer.py`,可以帮助用户快速完成YOLOv7量化模型在CPU/GPU上的部署推理加速.
|
||||
|
||||
## 部署准备
|
||||
### FastDeploy环境准备
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../../docs/environment.md)
|
||||
- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](../../../../../../docs/quick_start)
|
||||
|
||||
### 量化模型准备
|
||||
- 1. 用户可以直接使用由FastDeploy提供的量化模型进行部署.
|
||||
- 2. 用户可以使用FastDeploy提供的[一键模型量化工具](../../../../../../tools/quantization/),自行进行模型量化, 并使用产出的量化模型进行部署.
|
||||
|
||||
## 以量化后的YOLOv7模型为例, 进行部署
|
||||
```bash
|
||||
#下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd examples/vision/detection/yolov7/quantize/python
|
||||
|
||||
#下载FastDeloy提供的yolov7量化模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7_quant.tar
|
||||
tar -xvf yolov7_quant.tar
|
||||
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000014439.jpg
|
||||
|
||||
# 在CPU上使用Paddle-Inference推理量化模型
|
||||
python infer.py --model yolov7_quant --image 000000014439.jpg --device cpu --backend paddle
|
||||
# 在GPU上使用TensorRT推理量化模型
|
||||
python infer.py --model yolov7_quant --image 000000014439.jpg --device gpu --backend trt
|
||||
```
|
||||
81
examples/vision/detection/yolov7/quantize/python/infer.py
Normal file
81
examples/vision/detection/yolov7/quantize/python/infer.py
Normal file
@@ -0,0 +1,81 @@
|
||||
import fastdeploy as fd
|
||||
import cv2
|
||||
import os
|
||||
from fastdeploy import ModelFormat
|
||||
|
||||
|
||||
def parse_arguments():
|
||||
import argparse
|
||||
import ast
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"--model", required=True, help="Path of yolov7 onnx model.")
|
||||
parser.add_argument(
|
||||
"--image", required=True, help="Path of test image file.")
|
||||
parser.add_argument(
|
||||
"--device",
|
||||
type=str,
|
||||
default='cpu',
|
||||
help="Type of inference device, support 'cpu' or 'gpu'.")
|
||||
parser.add_argument(
|
||||
"--backend",
|
||||
type=str,
|
||||
default="default",
|
||||
help="Type of inference backend, support ort/trt/paddle/openvino, default 'openvino' for cpu, 'tensorrt' for gpu"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--device_id",
|
||||
type=int,
|
||||
default=0,
|
||||
help="Define which GPU card used to run model.")
|
||||
parser.add_argument(
|
||||
"--cpu_thread_num",
|
||||
type=int,
|
||||
default=9,
|
||||
help="Number of threads while inference on CPU.")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def build_option(args):
|
||||
option = fd.RuntimeOption()
|
||||
if args.device.lower() == "gpu":
|
||||
option.use_gpu(0)
|
||||
|
||||
option.set_cpu_thread_num(args.cpu_thread_num)
|
||||
|
||||
if args.backend.lower() == "trt":
|
||||
assert args.device.lower(
|
||||
) == "gpu", "TensorRT backend require inference on device GPU."
|
||||
option.use_trt_backend()
|
||||
elif args.backend.lower() == "ort":
|
||||
option.use_ort_backend()
|
||||
elif args.backend.lower() == "paddle":
|
||||
option.use_paddle_backend()
|
||||
elif args.backend.lower() == "openvino":
|
||||
assert args.device.lower(
|
||||
) == "cpu", "OpenVINO backend require inference on device CPU."
|
||||
option.use_openvino_backend()
|
||||
return option
|
||||
|
||||
|
||||
args = parse_arguments()
|
||||
|
||||
model_file = os.path.join(args.model, "model.pdmodel")
|
||||
params_file = os.path.join(args.model, "model.pdiparams")
|
||||
# 配置runtime，加载模型
|
||||
runtime_option = build_option(args)
|
||||
model = fd.vision.detection.YOLOv7(
|
||||
model_file,
|
||||
params_file,
|
||||
runtime_option=runtime_option,
|
||||
model_format=ModelFormat.PADDLE)
|
||||
|
||||
# 预测图片检测结果
|
||||
im = cv2.imread(args.image)
|
||||
result = model.predict(im.copy())
|
||||
print(result)
|
||||
|
||||
# 预测结果可视化
|
||||
vis_im = fd.vision.vis_detection(im, result)
|
||||
cv2.imwrite("visualized_result.jpg", vis_im)
|
||||
print("Visualized result save in ./visualized_result.jpg")
|
||||
Reference in New Issue
Block a user