apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-27 10:30:34 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[Doc] Fixed quantize.md (#795)

Browse Source 
* add onnx_ort_runtime demo

* rm in requirements

* support batch eval

* fixed MattingResults bug

* move assignment for DetectionResult

* integrated x2paddle

* add model convert readme

* update readme

* re-lint

* add processor api

* Add MattingResult Free

* change valid_cpu_backends order

* add ppocr benchmark

* mv bs from 64 to 32

* fixed quantize.md

* fixed quantize bugs

Co-authored-by: Jason <jiangjiajun@baidu.com>
This commit is contained in:
WJJ1995
2022-12-05 16:38:48 +08:00
committed by GitHub
parent 65f270df29
commit c6d943b7f0
7 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/vision/detection/yolov5/quantize/README.md
View File

@@ -10,7 +10,7 @@ FastDeploy 提供了一键模型自动化压缩工具, 能够简单地通过输
用户也可以直接下载下表中的量化模型进行部署.(点击模型名字即可下载)
Benchmark表格说明:
- Rtuntime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
- Runtime时延为模型在各种Runtime上的推理时延,包含CPU->GPU数据拷贝,GPU推理,GPU->CPU数据拷贝时间. 不包含模型各自的前后处理时间.
- 端到端时延为模型在实际推理场景中的时延, 包含模型的前后处理.
- 所测时延均为推理1000次后求得的平均值, 单位是毫秒.
- INT8 + FP16 为在推理INT8量化模型的同时, 给Runtime 开启FP16推理选项
@@ -29,7 +29,7 @@ Benchmark表格说明:
| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle Inference| CPU | 213.73 | 130.19 | None | None | 1.64 |37.6 | 35.2 | 量化蒸馏训练 |
#### 端到端 Benchmark
| 模型 |推理后端 |部署硬件 | FP32 Runtime时延 | INT8 Runtime时延 | INT8 + FP16 Runtime时延 | INT8+FP16+PM Runtime时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
| 模型 |推理后端 |部署硬件 | FP32 End2End时延 | INT8 End2End时延 | INT8 + FP16 End2End时延 | INT8+FP16+PM End2End时延 | 最大加速比 | FP32 mAP | INT8 mAP | 量化方式 |
| ------------------- | -----------------|-----------| -------- |-------- |-------- | --------- |-------- |----- |----- |----- |
| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | TensorRT | GPU | 24.61 | 21.20 | 20.78 | 20.94 | 1.18 | 37.6 | 36.7 | 量化蒸馏训练 |
| [YOLOv5s](https://bj.bcebos.com/paddlehub/fastdeploy/yolov5s_quant.tar) | Paddle-TensorRT | GPU | 23.53 | None | 21.98 | 19.84 | 1.28 | 37.6 | 36.8 | 量化蒸馏训练 |