Skip to content

P
PaddleDetection

s920243400 / PaddleDetection
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleDetection

通知 2
Star 0
Fork 0
P
PaddleDetection
未验证 提交 8055e86e 编写于 作者: K Kaipeng Deng 提交者： GitHub
浏览文件
操作

split weights and PaddleLite model in configs/mobile/README (#935) 

* split weights and PaddleLite model in configs/mobile/README
上级 e77baea4
显示空白变更内容
内联 并排
Showing with 18 addition and 26 deletion
configs/mobile/README.md
浏览文件 @ 8055e86e
...@@ -7,23 +7,19 @@ ...@@ -7,23 +7,19 @@
PaddleDetection目前提供一系列针对移动应用进行优化的模型，主要支持以下结构: PaddleDetection目前提供一系列针对移动应用进行优化的模型，主要支持以下结构:
| 骨干网络 | 结构 | 输入大小 | 图片/gpu <sup>1</sup> | 学习率策略 | Box AP | 下载 <sup>2</sup> | | 骨干网络 | 结构 | 输入大小 | 图片/gpu <sup>1</sup> | 学习率策略 | Box AP | 下载 | PaddleLite模型下载 |
|--------------------------|---------------------------|-------|------------------------|---------------|--------|-----------------------| | :----------------------- | :------------------------ | :---: | :--------------------: | :------------ | :----: | :--- | :----------------- |
| MobileNetV3 Small | SSDLite | 320 | 64 | 400K (cosine) | 16.6 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v3_small.tar.gz) | | MobileNetV3 Small | SSDLite | 320 | 64 | 400K (cosine) | 16.6 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small.tar) | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/ssdlite_mobilenet_v3_small.tar) |
| MobileNetV3 Large | SSDLite | 320 | 64 | 400K (cosine) | 22.8 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v3_large.tar.gz) | | MobileNetV3 Large | SSDLite | 320 | 64 | 400K (cosine) | 22.8 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large.tar) | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/ssdlite_mobilenet_v3_large.tar) |
| MobileNetV3 Large w/ FPN | Cascade RCNN | 320 | 2 | 500k (cosine) | 25.0 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_mobilenetv3_fpn_320.tar.gz) | | MobileNetV3 Large w/ FPN | Cascade RCNN | 320 | 2 | 500k (cosine) | 25.0 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/cascade_rcnn_mobilenetv3_fpn_320.tar) | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/cascade_rcnn_mobilenetv3_fpn_320.tar) |
| MobileNetV3 Large w/ FPN | Cascade RCNN | 640 | 2 | 500k (cosine) | 30.2 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_mobilenetv3_fpn_640.tar.gz) | | MobileNetV3 Large w/ FPN | Cascade RCNN | 640 | 2 | 500k (cosine) | 30.2 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/cascade_rcnn_mobilenetv3_fpn_640.tar) | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/cascade_rcnn_mobilenetv3_fpn_640.tar) |
| MobileNetV3 Large | YOLOv3 | 320 | 8 | 500K | 27.1 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.tar.gz) | | MobileNetV3 Large | YOLOv3 | 320 | 8 | 500K | 27.1 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/yolov3_mobilenet_v3.tar) |
| MobileNetV3 Large | YOLOv3 Prune <sup>3</sup> | 320 | 8 | - | 24.6 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3_prune86_FPGM_320.tar.gz) | | MobileNetV3 Large | YOLOv3 Prune <sup>2</sup> | 320 | 8 | - | 24.6 | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/yolov3_mobilenet_v3_prune75875_FPGM_distillby_r34.pdparams) | [链接](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/yolov3_mobilenet_v3_prune86_FPGM_320.tar) |
**注意**: **注意**:
- <a name="gpu">[1]</a> 模型统一使用8卡训练. - <a name="gpu">[1]</a> 模型统一使用8卡训练.
- <a name="tarball">[2]</a> 压缩包包括下列文件 - <a name="prune">[2]</a> 参考下面关于YOLO剪裁的说明
- 模型权重文件 (`.pdparams` or `.tar`)
- inference model 文件 (`__model__` and `__params__`)
- Paddle-Lite 模型文件 (`.nb`)
- <a name="prune">[3]</a> 参考下面关于YOLO剪裁的说明
## 评测结果 ## 评测结果
......
configs/mobile/README_en.md
浏览文件 @ 8055e86e
...@@ -7,23 +7,19 @@ English | [简体中文](README.md) ...@@ -7,23 +7,19 @@ English | [简体中文](README.md)
This directory contains models optimized for mobile applications, at present the following models included: This directory contains models optimized for mobile applications, at present the following models included:
| Backbone | Architecture | Input | Image/gpu <sup>1</sup> | Lr schd | Box AP | Download <sup>2</sup> | | Backbone | Architecture | Input | Image/gpu <sup>1</sup> | Lr schd | Box AP | Download | PaddleLite Model Download |
|--------------------------|---------------------------|-------|------------------------|---------------|--------|-----------------------| | :----------------------- | :------------------------ | :---: | :--------------------: | :------------ | :----: | :------- | :------------------------ |
| MobileNetV3 Small | SSDLite | 320 | 64 | 400K (cosine) | 16.6 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v3_small.tar.gz) | | MobileNetV3 Small | SSDLite | 320 | 64 | 400K (cosine) | 16.6 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_small.tar) | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/ssdlite_mobilenet_v3_small.tar) |
| MobileNetV3 Large | SSDLite | 320 | 64 | 400K (cosine) | 22.8 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/ssdlite_mobilenet_v3_large.tar.gz) | | MobileNetV3 Large | SSDLite | 320 | 64 | 400K (cosine) | 22.8 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/ssdlite_mobilenet_v3_large.tar) | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/ssdlite_mobilenet_v3_large.tar) |
| MobileNetV3 Large w/ FPN | Cascade RCNN | 320 | 2 | 500k (cosine) | 25.0 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_mobilenetv3_fpn_320.tar.gz) | | MobileNetV3 Large w/ FPN | Cascade RCNN | 320 | 2 | 500k (cosine) | 25.0 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/cascade_rcnn_mobilenetv3_fpn_320.tar) | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/cascade_rcnn_mobilenetv3_fpn_320.tar) |
| MobileNetV3 Large w/ FPN | Cascade RCNN | 640 | 2 | 500k (cosine) | 30.2 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/cascade_rcnn_mobilenetv3_fpn_640.tar.gz) | | MobileNetV3 Large w/ FPN | Cascade RCNN | 640 | 2 | 500k (cosine) | 30.2 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/cascade_rcnn_mobilenetv3_fpn_640.tar) | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/cascade_rcnn_mobilenetv3_fpn_640.tar) |
| MobileNetV3 Large | YOLOv3 | 320 | 8 | 500K | 27.1 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.tar.gz) | | MobileNetV3 Large | YOLOv3 | 320 | 8 | 500K | 27.1 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3.pdparams) | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/yolov3_mobilenet_v3.tar) |
| MobileNetV3 Large | YOLOv3 Prune <sup>3</sup> | 320 | 8 | - | 24.6 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v3_prune86_FPGM_320.tar.gz) | | MobileNetV3 Large | YOLOv3 Prune <sup>2</sup> | 320 | 8 | - | 24.6 | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/yolov3_mobilenet_v3_prune75875_FPGM_distillby_r34.pdparams) | [Link](https://paddlemodels.bj.bcebos.com/object_detection/mobile_models/lite/yolov3_mobilenet_v3_prune86_FPGM_320.tar) |
**Notes**: **Notes**:
- <a name="gpu">[1]</a> All models are trained on 8 GPUs. - <a name="gpu">[1]</a> All models are trained on 8 GPUs.
- <a name="tarball">[2]</a> Each tarball contains the following files - <a name="prune">[2]</a> See the note section on how YOLO head is pruned
- model weight file (`.pdparams` or `.tar`)
- inference model files (`__model__` and `__params__`)
- Paddle-Lite model file (`.nb`)
- <a name="prune">[3]</a> See the note section on how YOLO head is pruned
## Benchmarks Results ## Benchmarks Results
......
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