https://github.com/shibing624/cvnet
have fun with image AI
https://github.com/shibing624/cvnet
ai face face-recognition imagefun
Last synced: about 2 months ago
JSON representation
have fun with image AI
- Host: GitHub
- URL: https://github.com/shibing624/cvnet
- Owner: shibing624
- License: apache-2.0
- Created: 2018-08-23T08:02:09.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2025-03-22T03:22:21.000Z (7 months ago)
- Last Synced: 2025-07-09T02:20:36.064Z (3 months ago)
- Topics: ai, face, face-recognition, imagefun
- Language: Jupyter Notebook
- Size: 15.7 MB
- Stars: 4
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# cvnet
Model for Computer Vision(CV) Neural Network.
## 图像分类
image classification
## 图像分割
- 语义分割
- 实例分割
- 全景分割
### 技术演化路径
1. 2010年前，传统分割：1）边缘检测；2）遗传算法
2. 2010-2015年，机器学习：1）随机森林；2）支持向量机
3. 2015年后，深度学习：1）经典分割算法：FCN, U-Net, SegNet, DeepLab; 2)实时分割算法：ENet, LinkNet, BiSeNet, DFANet, Light-Weight RefineNet; 3)RGB-D分割算法：RedNet, RDFNet
#### MEAL-V2
https://github.com/szq0214/MEAL-V2
介绍他们如何通过蒸馏（distillation）训练一个强大的小模型。所提出方法使用相同模型结构和输入图片大小的前提下，
在 ImageNet 上的性能远超之前 state-of-the-art 的 FixRes 2.5% 以上，甚至超过了魔改结构的 ResNeSt 的结果。
https://www.jiqizhixin.com/articles/2020-09-29-2
### Networks implemented
* [PSPNet](https://arxiv.org/abs/1612.01105) - With support for loading pretrained models w/o caffe dependency
* [ICNet](https://arxiv.org/pdf/1704.08545.pdf) - With optional batchnorm and pretrained models
* [FRRN](https://arxiv.org/abs/1611.08323) - Model A and B
* [FCN](https://arxiv.org/abs/1411.4038) - All 1 (FCN32s), 2 (FCN16s) and 3 (FCN8s) stream variants
* [U-Net](https://arxiv.org/abs/1505.04597) - With optional deconvolution and batchnorm
* [Link-Net](https://codeac29.github.io/projects/linknet/) - With multiple resnet backends
* [Segnet](https://arxiv.org/abs/1511.00561) - With Unpooling using Maxpool indices
#### Upcoming
* [E-Net](https://arxiv.org/abs/1606.02147)
* [RefineNet](https://arxiv.org/abs/1611.06612)
### DataLoaders implemented
* [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/)
* [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/segexamples/index.html)
* [ADE20K](http://groups.csail.mit.edu/vision/datasets/ADE20K/)
* [MIT Scene Parsing Benchmark](http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip)
* [Cityscapes](https://www.cityscapes-dataset.com/)
### Demo
1. demo site: https://www.remove.bg/upload
2. 演示效果：
demo1:
remove background:
demo2:
remove background:
# Reference
1. [ClassyVision](https://github.com/facebookresearch/ClassyVision)
2. [Deep-Learning-Project-Template](https://github.com/L1aoXingyu/Deep-Learning-Project-Template)
3. [pytorch-semseg](https://github.com/meetshah1995/pytorch-semseg)
4. [torchcv](https://github.com/donnyyou/torchcv)
5. [pytorch-cnn-finetune](https://github.com/creafz/pytorch-cnn-finetune)
6. [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)