Image Semantic Segmentation之DeepLab两个坑

1、实验平台：ubuntu 16.04 + TensorFlow 1.12.0 + cuda 9.0 + python 3.6

第一个坑：tensorflow和cuda版本要对应。

2、下载：git clone https://github.com/tensorflow/models.git，切换到models/research/下。

3、测试：选择PASCAL VOC 2012数据集 https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/pascal.md

1)加载路径：

# From tensorflow/models/research/
export PYTHONPATH=$PYTHONPATH:tensorflow/models/research/:tensorflow/models/research/slim

第二个坑：python默认带__init__.py文件的文件夹可以识别为包，但这里不生效，只能每次手动加载路径。

2）快速测试：

# From tensorflow/models/research/
python deeplab/model_test.py

3）该数据集有一个sh脚本可以合并运行：

# From tensorflow/models/research/deeplab
sh local_test.sh

实验结果查看：https://github.com/tensorflow/models/blob/master/research/deeplab/deeplab_demo.ipynb

下步实验Cityscapes Datasets数据集。https://github.com/mcordts/cityscapesScripts

Image Semantic Segmentation之DeepLab两个坑相关推荐

FCN的学习及理解（Fully Convolutional Networks for Semantic Segmentation）
大多数人接触"语义"都是在和文字相关的领域,或语音识别,期望机器能够识别你发出去的消息或简短的语音,然后给予你适当的反馈和回复.嗯,看到这里你应该已经猜到了,图像领域也是存在&qu ...
语义分割--Global Deconvolutional Networks for Semantic Segmentation
语义分割 Global Deconvolutional Networks for Semantic Segmentation BMVC 2016 https://github.com/DrSleep/ ...
论文精读及分析：Fully Convolutional Networks for Semantic Segmentation
本文主要内容为论文<Fully Convolutional Networks for Semantic Segmentation> 的阅读笔记,在原始论文的基础上加入了自己的一些理解, ...
Semantic Segmentation: A thorough Review
语义分割可以划分到目标检测领域,不同的是,一般意义上目标检测只需要输出被检测物体的bounding box,而语义分割则需要输出一个mask,所以要求更高了. 从技术上说,语义分割归根结底就是对con ...
【论文翻译】SETR:Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformer
SETR 摘要介绍相关工作语义分割 Transformer 模型设计 FCN-based semantic segmentation Segmentation transformers (SET ...
【RedNet2018】RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation RedNet: 用于室内RGB-D语义分 ...
Semi-supervised semantic segmentation needs strong, varied perturbations
论文阅读: Semi-supervised semantic segmentation needs strong, varied perturbations 作者声明版权声明:本文为博主原创文章,遵 ...
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation (CVPR2019) 1.摘要目前 ...
DFAnet：Deep Feature Aggregation for Real-time Semantic Segmentation自己翻译的
DFAnet:Deep Feature Aggregation for Real-time Semantic Segmentation 原始论文Li H, Xiong P, Fan H, et al. ...

Image Semantic Segmentation之DeepLab两个坑

Image Semantic Segmentation之DeepLab两个坑相关推荐

最新文章

热门文章