alisure-ml / Semantic-Segmentation-PSPNet Licence: other
PSPNet in tensorflow
Programming Languages python 139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Semantic-Segmentation-PSPNet semantic-segmentation-tensorflow Semantic segmentation task for ADE20k & cityscapse dataset, based on several models.
Stars : ✭ 84 (+342.11%)
Mutual labels: pspnet
PSPNet-Pytorch Implemetation of Pyramid Scene Parsing Network in Pytorch
Stars : ✭ 26 (+36.84%)
Mutual labels: pspnet
etos-deepcut Deep Extreme Cut http://www.vision.ee.ethz.ch/~cvlsegmentation/dextr . a tool to do automatically object segmentation from extreme points.
Stars : ✭ 24 (+26.32%)
Mutual labels: pspnet
image-segmentation Mask R-CNN, FPN, LinkNet, PSPNet and UNet with multiple backbone architectures support readily available
Stars : ✭ 62 (+226.32%)
Mutual labels: pspnet
Mmsegmentation OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Stars : ✭ 2,875 (+15031.58%)
Mutual labels: pspnet
Segmentation models Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Stars : ✭ 3,575 (+18715.79%)
Mutual labels: pspnet
TensorFlow-Advanced-Segmentation-Models A Python Library for High-Level Semantic Segmentation Models based on TensorFlow and Keras with pretrained backbones.
Stars : ✭ 64 (+236.84%)
Mutual labels: pspnet
Paper
Pyramid Scene Parsing Network.pdf
Run Image
下载模型Google Drive ,放入model
目录.
准备图片,运行RunnerOne.py
即可:
Runner(is_flip=False, num_classes=19, log_dir="./model", save_dir="./output").run("data/input/test.png")
Run Result
1. Data - ImageReader.py
ReaderTrainImageAndLabel
ReaderTestImage
2. Model - PSPNet.py
3. Tool - Tools.py
4. Runner - RunnerXXX.py
RunnerTrain.py
训练模型,输入是训练图片和标签的list,输出是训练好的模型
RunnerOne.py
RunnerAll.py
使用模型,输入是图片的list,输出是语义分割结果
Reference
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at
[email protected] .