Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into develop

README.md

@@ -17,6 +17,7 @@ PaddleX是基于飞桨技术生态的全流程深度学习模型开发工具。
 - [10分钟快速上手PaddleX模型训练](docs/quick_start.md)
 - [PaddleX使用教程](docs/tutorials)
 - [PaddleX模型库](docs/model_zoo.md)
+- [导出模型部署](docs/deploy.md)
 
 
 ## 反馈

docs/tutorials/train/instance_segmentation.md

@@ -113,4 +113,4 @@ predict_result = model.predict('./garbage_ins_det/JPEGImages/000114.bmp')
 ```python
 pdx.det.visualize('./garbage_ins_det/JPEGImages/000114.bmp', predict_result, threshold=0.7, save_dir='./output/mask_rcnn_r50_fpn')
 ```
-![](../images/visualized_maskrcnn.bmp)
+![](../../images/visualized_maskrcnn.bmp)

docs/tutorials/train/segmentation.md

 # 训练语义分割模型
 
 ---
-更多语义分割模型在Cityscapes数据集上的训练代码可参考[代码tutorials/train/segmentation/unet.py](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/segmentation/unet.py)、[代码tutorials/train/segmentation/deeplabv3p.py](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/segmentation/deeplabv3p.py)。
+更多语义分割模型在视盘数据集上的训练代码可参考[代码tutorials/train/segmentation/deeplabv3p.py](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/segmentation/deeplabv3p.py)。
 
 **1.下载并解压训练所需的数据集**
 
@@ -114,4 +114,4 @@ import paddlex as pdx
 pdx.seg.visualize(image_name, predict_result, weight=0.4)
 ```
 
-![](../images/visualized_deeplab.jpg)
+![](../../images/visualized_deeplab.jpg)