实现效果
mask RCNN 目标检测和识别
Deeplab V3 语义分割
提取检测目标
人物检测和提取
Mask RCNN
人物检测和显示
deeplab V3 人物和背景提取, 合成显示
代码整理好,再分享。
DeeplabV3
https://github.com/tensorflow/models/tree/master/research/deeplab
安装
替换deeplab 最新
######################
查看所有环境
conda info --envs
1
新建虚拟环境
conda create -n myenv python=3.6
1
删除虚拟环境
conda remove -n myenv --all
1
**虚拟环境
conda activate myenv
1
退出虚拟环境
conda deactivate myenv
创建环境
conda create -n TF_Deeplab --clone tensorflow-API
Pytest 安装
Numpy 更新1.15.1
运行model_test 测试
Quick test by running model_test.py:
# From tensorflow/models/research/
python deeplab/model_test.py
Quick running the whole code on the PASCAL VOC 2012 dataset:
# From tensorflow/models/research/deeplab
sh local_test.sh
DeepLab depends on the following libraries:
- Numpy
- Pillow 1.0
- tf Slim (which is included in the "tensorflow/models/research/" checkout)
- Jupyter notebook
- Matplotlib
- Tensorflow
We provide deeplab models pretrained several datasets, including (1) PASCAL VOC 2012, (2) Cityscapes, and (3) ADE20K for reproducing our results
Pretrained model
PASCAL2012
CITYSCAPES
ADE
Mobilenet
https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet
本站文章如无特殊说明,均为本站原创,如若转载,请注明出处:deeplab V3 Mask RCNN tensorflow实现 语义分割 人物背景分开 合成不同场景的图像 目标检测 - Python技术站