Add links to tutorials of paddledetection. (PaddlePaddle#155)

slf12 · Feb 25, 2020 · df30145 · df30145
1 parent ea88326
commit df30145
Show file tree

Hide file tree

Showing 7 changed files with 87 additions and 1 deletion.
diff --git a/docs/zh_cn/tutorials/index.rst b/docs/zh_cn/tutorials/index.rst
@@ -7,4 +7,9 @@
 
    image_classification_sensitivity_analysis_tutorial.md
    darts_nas_turorial.md
-
+   paddledetection_slim_distillation_tutorial.md
+   paddledetection_slim_nas_tutorial.md
+   paddledetection_slim_pruing_tutorial.md
+   paddledetection_slim_prune_dist_tutorial.md
+   paddledetection_slim_quantization_tutorial.md
+   paddledetection_slim_sensitivy_tutorial.md
diff --git a/docs/zh_cn/tutorials/paddledetection_slim_distillation_tutorial.md b/docs/zh_cn/tutorials/paddledetection_slim_distillation_tutorial.md
@@ -0,0 +1,32 @@
+# 目标检测模型蒸馏教程
+
+教程内容请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/distillation/README.md
+
+
+## 示例结果
+
+### MobileNetV1-YOLO-V3-VOC
+
+| FLOPS |输入尺寸|每张GPU图片个数|推理时间（fps）|Box AP|下载|
+|:-:|:-:|:-:|:-:|:-:|:-:|
+|baseline|608     |16|104.291|76.2|[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar)|
+|蒸馏后|608 |16|106.914|79.0|[下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_voc_distilled.tar)|
+|baseline|416 |16|-|76.7|[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar)|
+|蒸馏后|416 |16|-|78.2|[下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_voc_distilled.tar)|
+|baseline|320 |16|-|75.3|[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar)|
+|蒸馏后|320 |16|-|75.5|[下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_voc_distilled.tar)|
+
+> 蒸馏后的结果用ResNet34-YOLO-V3做teacher，4GPU总batch_size64训练90000 iter得到
+
+### MobileNetV1-YOLO-V3-COCO
+
+| FLOPS |输入尺寸|每张GPU图片个数|推理时间（fps）|Box AP|下载|
+|:-:|:-:|:-:|:-:|:-:|:-:|
+|baseline|608     |16|78.302|29.3|[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar)|
+|蒸馏后|608 |16|78.523|31.4|[下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar)|
+|baseline|416 |16|-|29.3|[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar)|
+|蒸馏后|416 |16|-|30.0|[下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar)|
+|baseline|320 |16|-|27.0|[下载链接](https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1_voc.tar)|
+|蒸馏后|320 |16|-|27.1|[下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_distilled.tar)|
+
+> 蒸馏后的结果用ResNet34-YOLO-V3做teacher，4GPU总batch_size64训练600000 iter得到
diff --git a/docs/zh_cn/tutorials/paddledetection_slim_nas_tutorial.md b/docs/zh_cn/tutorials/paddledetection_slim_nas_tutorial.md
@@ -0,0 +1,8 @@
+# 人脸检测模型小模型结构搜索教程
+
+教程内容请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/nas/README.md
+
+## 概述
+
+我们选取人脸检测的BlazeFace模型作为神经网络搜索示例，该示例使用PaddleSlim 辅助完成神经网络搜索实验。
+基于PaddleSlim进行搜索实验过程中，搜索限制条件可以选择是浮点运算数(FLOPs)限制还是硬件延时(latency)限制，硬件延时限制需要提供延时表。本示例提供一份基于blazeface搜索空间的硬件延时表，名称是latency_855.txt(基于PaddleLite在骁龙855上测试的延时)，可以直接用该表进行blazeface的硬件延时搜索实验。
diff --git a/docs/zh_cn/tutorials/paddledetection_slim_pruing_tutorial.md b/docs/zh_cn/tutorials/paddledetection_slim_pruing_tutorial.md
@@ -0,0 +1,3 @@
+# 目标检测模型卷积通道剪裁教程
+
+请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/prune/README.md
diff --git a/docs/zh_cn/tutorials/paddledetection_slim_prune_dist_tutorial.md b/docs/zh_cn/tutorials/paddledetection_slim_prune_dist_tutorial.md
@@ -0,0 +1,7 @@
+# 目标检测模型蒸馏剪裁教程
+
+教程内容请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/extensions/distill_pruned_model/README.md
+
+## 概述
+
+该文档介绍如何使用PaddleSlim的蒸馏接口和卷积通道剪裁接口对检测库中的模型进行卷积层的通道剪裁并使用较高精度模型对其蒸馏。
diff --git a/docs/zh_cn/tutorials/paddledetection_slim_quantization_tutorial.md b/docs/zh_cn/tutorials/paddledetection_slim_quantization_tutorial.md
@@ -0,0 +1,28 @@
+# 目标检测模型定点量化教程
+
+教程内容请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/quantization/README.md
+
+
+## 示例结果
+
+### 训练策略
+
+- 量化策略`post`为使用离线量化得到的模型，`aware`为在线量化训练得到的模型。
+
+### YOLOv3 on COCO
+
+| 骨架网络         | 预训练权重 | 量化策略 | 输入尺寸 | Box AP  |                           下载                          |
+| :----------------| :--------: | :------: | :------: |:------: | :-----------------------------------------------------: |
+| MobileNetV1      |  ImageNet  |   post   |   608    |  27.9   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) |
+| MobileNetV1      |  ImageNet  |   post   |   416    |  28.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) |
+| MobileNetV1      |  ImageNet  |   post   |   320    |  26.0   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_post.tar) |
+| MobileNetV1      |  ImageNet  |  aware   |   608    |  28.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_aware.tar) |
+| MobileNetV1      |  ImageNet  |  aware   |   416    |  28.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_aware.tar) |
+| MobileNetV1      |  ImageNet  |  aware   |   320    |  25.8   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_mobilenetv1_coco_quant_aware.tar) |
+| ResNet34         |  ImageNet  |   post   |   608    |  35.7   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_post.tar) |
+| ResNet34         |  ImageNet  |  aware   |   608    |  35.2   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) |
+| ResNet34         |  ImageNet  |  aware   |   416    |  33.3   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) |
+| ResNet34         |  ImageNet  |  aware   |   320    |  30.3   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r34_coco_quant_aware.tar) |
+| R50vd-dcn        | object365  |  aware   |   608    |  40.6   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r50vd_dcn_obj365_pretrained_coco_quant_aware.tar) |
+| R50vd-dcn        | object365  |  aware   |   416    |  37.5   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r50vd_dcn_obj365_pretrained_coco_quant_aware.tar) |
+| R50vd-dcn        | object365  |  aware   |   320    |  34.1   | [下载链接](https://paddlemodels.bj.bcebos.com/PaddleSlim/yolov3_r50vd_dcn_obj365_pretrained_coco_quant_aware.tar) |
diff --git a/docs/zh_cn/tutorials/paddledetection_slim_sensitivy_tutorial.md b/docs/zh_cn/tutorials/paddledetection_slim_sensitivy_tutorial.md
@@ -0,0 +1,3 @@
+# 目标检测模型敏感度分析教程
+
+教程内容请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/sensitive/README.md
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		# 目标检测模型卷积通道剪裁教程

		请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/prune/README.md
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		# 目标检测模型敏感度分析教程

		教程内容请参考：https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.2/slim/sensitive/README.md