为确保你提交的代码身份被 Gitee 正确识别,请执行以下命令完成配置

git config --global user.name userName git config --global user.email userEmail

初次使用 SSH 协议进行代码克隆、推送等操作时,需按下述提示完成 SSH 配置

1 生成 RSA 密钥

2 获取 RSA 公钥内容,并配置到 SSH公钥 中

在 Gitee 上使用 SVN,请访问 使用指南

使用 HTTPS 协议时,命令行会出现如下账号密码验证步骤。基于安全考虑,Gitee 建议 配置并使用私人令牌 替代登录密码进行克隆、推送等操作

Username for 'https://gitee.com': userName

Password for 'https://userName@gitee.com': # 私人令牌

新建文件 新建 Diagram 文件

docs

examples

images

segmentation_models

tests

.gitignore

.gitmodules

.travis.yml

CHANGELOG.md

LICENSE

MANIFEST.in

README.rst

__init__.py

requirements.txt

setup.py

Segmentation Models

Segmentation models is python library with Neural Networks for Keras and Table of Contents

• Quick start
• Simple training pipeline
• Examples
• Models and Backbones
• Installation
• Documentation
• Change log
• Citing
• License

Quick start

Library is build to work together with Keras and TensorFlow Keras frameworks

import segmentation_models as sm
# Segmentation Models: using `keras` framework.

By default it tries to import keras, if it is not installed, it will try to start with tensorflow.keras framework. There are several ways to choose framework:

• Provide environment variable SM_FRAMEWORK=keras / SM_FRAMEWORK=tf.keras before import segmentation_models
• Change framework sm.set_framework('keras') / sm.set_framework('tf.keras')

You can also specify what kind of image_data_format to use, segmentation-models works with both: channels_last and channels_first. This can be useful for further model conversion to Nvidia TensorRT format or optimizing model for cpu/gpu computations.

import keras
# or from tensorflow import keras

keras.backend.set_image_data_format('channels_last')
# or keras.backend.set_image_data_format('channels_first')

Created segmentation model is just an instance of Keras Model, which can be build as easy as:

model = sm.Unet()

Depending on the task, you can change the network architecture by choosing backbones with fewer or more parameters and use pretrainded weights to initialize it:

model = sm.Unet('resnet34', encoder_weights='imagenet')

Change number of output classes in the model (choose your case):

# binary segmentation (this parameters are default when you call Unet('resnet34')
model = sm.Unet('resnet34', classes=1, activation='sigmoid')

# multiclass segmentation with non overlapping class masks (your classes + background)
model = sm.Unet('resnet34', classes=3, activation='softmax')

# multiclass segmentation with independent overlapping/non-overlapping class masks
model = sm.Unet('resnet34', classes=3, activation='sigmoid')

Change input shape of the model:

# if you set input channels not equal to 3, you have to set encoder_weights=None
# how to handle such case with encoder_weights='imagenet' described in docs
model = Unet('resnet34', input_shape=(None, None, 6), encoder_weights=None)

Simple training pipeline

import segmentation_models as sm

BACKBONE = 'resnet34'
preprocess_input = sm.get_preprocessing(BACKBONE)

# load your data
x_train, y_train, x_val, y_val = load_data(...)

# preprocess input
x_train = preprocess_input(x_train)
x_val = preprocess_input(x_val)

# define model
model = sm.Unet(BACKBONE, encoder_weights='imagenet')
model.compile(
 'Adam',
 loss=sm.losses.bce_jaccard_loss,
 metrics=[sm.metrics.iou_score],
)

# fit model
# if you use data generator use model.fit_generator(...) instead of model.fit(...)
# more about `fit_generator` here: https://keras.io/models/sequential/#fit_generator
model.fit(
 x=x_train,
 y=y_train,
 batch_size=16,
 epochs=100,
 validation_data=(x_val, y_val),
)

Same manipulations can be done with Linknet, PSPNet and FPN. For more detailed information about models API and use cases Examples

Models training examples:

• [Jupyter Notebook] Binary segmentation (cars) on CamVid dataset here.

Models and Backbones

Models

• FPN
• PSPNet

Unet	Linknet
unet_image	linknet_image

PSPNet	FPN
psp_image	fpn_image

Backbones

Type	Names
VGG	'vgg16' 'vgg19'
ResNet	'resnet18' 'resnet34' 'resnet50' 'resnet101' 'resnet152'
SE-ResNet	'seresnet18' 'seresnet34' 'seresnet50' 'seresnet101' 'seresnet152'
ResNeXt	'resnext50' 'resnext101'
SE-ResNeXt	'seresnext50' 'seresnext101'
SENet154	'senet154'
DenseNet	'densenet121' 'densenet169' 'densenet201'
Inception	'inceptionv3' 'inceptionresnetv2'
MobileNet	'mobilenet' 'mobilenetv2'
EfficientNet	'efficientnetb0' 'efficientnetb1' 'efficientnetb2' 'efficientnetb3' 'efficientnetb4' 'efficientnetb5' efficientnetb6' efficientnetb7'

All backbones have weights trained on 2012 ILSVRC ImageNet dataset (encoder_weights='imagenet').

Installation

Requirements

1. python 3
2. keras >= 2.2.0 or tensorflow >= 1.13
3. keras-applications >= 1.0.7, <=1.0.8
4. image-classifiers == 1.0.*
5. efficientnet == 1.0.*

PyPI stable package

$ pip install -U segmentation-models

PyPI latest package

$ pip install -U --pre segmentation-models

Source latest version

$ pip install git+https://github.com/qubvel/segmentation_models

Documentation

Latest documentation is avaliable on Change Log

To see important changes between versions look at Citing

@misc{Yakubovskiy:2019,
 Author = {Pavel Yakubovskiy},
 Title = {Segmentation Models},
 Year = {2019},
 Publisher = {GitHub},
 Journal = {GitHub repository},
 Howpublished = {\url{https://github.com/qubvel/segmentation_models}}
}

License

Project is distributed under /githubGAN/segmentation_models/tree/master

README

MIT

0 Stars

1 Watching

0 Forks

不能加载更多了

尝试更多