Data

Tools

Indexes

Applications

Experiments

Open Source Science

computer-vision-in-action

A computer vision closed-loop learning platform where code can be run interactively online. 学习闭环《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（持续更新中 ...） 📘 在线电子书 https://charmve.github.io/computer-vision-in-action/ 👇项目主页

https://github.com/charmve/computer-vision-in-action

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.9%) to scientific vocabulary

Keywords

books charmve colab-notebook computer-vision computer-vision-algorithms deep-learning deep-learning-tutorial handbook in-action ipynb jupyter-notebook machine-learning neural-network notebook pytorch transformer tutorial
Last synced: 6 months ago · JSON representation

Repository

A computer vision closed-loop learning platform where code can be run interactively online. 学习闭环《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（持续更新中 ...） 📘 在线电子书 https://charmve.github.io/computer-vision-in-action/ 👇项目主页

Basic Info
Statistics
  • Stars: 2,767
  • Watchers: 34
  • Forks: 402
  • Open Issues: 60
  • Releases: 0
Topics
books charmve colab-notebook computer-vision computer-vision-algorithms deep-learning deep-learning-tutorial handbook in-action ipynb jupyter-notebook machine-learning neural-network notebook pytorch transformer tutorial
Created almost 5 years ago · Last pushed over 1 year ago
Metadata Files
Readme Changelog Contributing Funding License Code of conduct Citation

README.md

""

L0CV ``   HTML


  


Computer Vision in Action

[Charmve](https://github.com/Charmve)

CircleCI Documentation status Code License
Python version jupyter version PyTorch version
Binder Run on Colab Docker Gitpod Ready-to-Code Stars Forks

logo:L0CV


L0CV Website
>

> - https://charmve.github.io/computer-vision-in-action/ >

PDF

> - https://github.com/charmve/computer-vision-in-action/releases ( ...)
Scan QR L0CV QR
QQ WeChat Weibo Twitter Zhihu CSDN

Index

L0CV architecture

:label: sec_code 1 L0CV

:label: fig_book_org

book_org.png

  • AdaBoost

  • Transformer7PyTorch3D

  • notebook L0CV import L0CV

  • TransformerAttention chap_optimization

Index

Index


  • https://charmve.github.io/computer-vision-in-action/
()
-

[](/docs/book_preface.md)

 -

-

- 0 [](https://charmve.github.io/computer-vision-in-action/#/chapter0/chapter0) - 0.1 [](docs/0_/chapter0.1_.md) - 0.1.1 - 0.1.2 - 0.1.3 - 0.2 [](docs/0_/chapter0.2_.md) - 0.3 [](docs/0_/chapter0.3_.md) - 0.4 [](docs/0_/chapter0.4_.md) - - - - 3D - 0.5 [](docs/0_/chapter0.5_.md) - - - -

- 1 [](https://charmve.github.io/computer-vision-in-action/#/chapter2/chapter2) - 1.1 [](/1_/chapter1_Neural-Networks/chapter1.1_line-regression.md) - 1.1.1 - 1.1.2 - 1.1.3 - 1.2 [Softmax ](./docs/1_/chapter3_Image-Classification/chapter1.2_Softmax.md) - 1.2.1 softmax - 1.2.2 softmax - 1.2.3 softmax - 1.3 [](./docs/1_/chapter1_Neural-Networks/chapter1.3_MLP.md) - 1.3.1 - 1.3.2 - 1.3.3 - 1.4 [](./docs/1_/chapter1_Neural-Networks/chapter1.4_Back-Propagation.md) - 1.5 [](./docs/1_/chapter1_Neural-Networks/chapter1.5_neural-networks.md) - 1.5.1 [](./docs/1_/chapter1_Neural-Networks/chapter1.5.1_.md) - 1.5.2 [1-](https://cs231n.github.io/neural-networks-1/) - 1.5.3 [2-](https://cs231n.github.io/neural-networks-2/) - 1.5.4 [3-](https://cs231n.github.io/neural-networks-3/) - 1.5.5 [-](https://cs231n.github.io/neural-networks-case-study/) - 1.6 [ 1 - ](https://blog.csdn.net/Charmve/article/details/108531735) - - - 2 [](docs/1_/chapter2_CNN/chapter2_CNN.md) - 2.1 [](docs/1_/chapter2_CNN/chapter2_CNN.md#21-) - 2.1.1 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#211-) - 2.1.2 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#212-) - 2.2 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#22-) - 2.2.1 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#221-) - 2.2.2 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#222-) - 2.2.3 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#223-) - 2.2.4 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#224-) - 2.2.5 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#225-) - 2.3 [](/docs/1_/chapter2_CNN/chapter2_CNN.md#23-) - 2.4 [ 2 - ](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md) - 2.4.1 [](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#271-) - 2.4.2 [](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#272-) - 2.4.3 [](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#273-) - [1. ](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#1-) - [2. ](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#2-) - [3. ](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#3-) - [4. ](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#4-) - [5. ](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#5-) - [6. MaxPooling](docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#6-MaxPooling) - 2.4.4 [PaddlePaddle](/docs/1_/chapter2_CNN/chapter2_CNN-in-Action.md#274-PaddlePaddle) - [](docs/1_/chapter2_CNN/chapter2_CNN.md#) - [](/docs/1_/chapter2_CNN/chapter2_CNN.md#) - 3 [](./docs/1_/chapter3_Image-Classification/) - 3.1 [](https://cs231n.github.io/classification/) - 3.1.1 - 3.1.2 - 3.1.3 - 3.2 [k ](./docs/1_/chapter3_Image-Classification/chapter3.2_knn.md) - 3.2.1 k - 3.2.2 k - 3.2.3 KNN - 3.2.4 k Python - - - 3.3 [](./docs/1_/chapter3_Image-Classification/chapter3.3_.md) - 3.3.1 - 3.3.2 - 3.3.3 - 3.3.4 - 3.4 [ LR](./docs/1_/chapter3_Image-Classification/chapter3.4_Logistic-Regression.md) - 3.4.1 - 3.4.2 - 3.4.3 - 3.5 [ 3 - ](https://blog.csdn.net/charmve/category_9754344.html) - 3.6 [ 4 - CIFAR10](http://mp.weixin.qq.com/s?__biz=MzIxMjg1Njc3Mw%3D%3D&chksm=97bef597a0c97c813e185e1bbf987b93d496c6ead8371364fd175d9bac46e6dcf7059cf81cb2&idx=1&mid=2247487293&scene=21&sn=89684d1c107177983dc1b4dca8c20a5b#wechat_redirect) - [](./docs/1_/chapter3_Image-Classification/README.md#) - [](./docs/1_/chapter3_Image-Classification/README.md#) - 4 - [4.1 RNN](/docs/1_/chapter4_/chapter4.1_.md) - [4.2 ](/docs/1_/chapter4_/chapter4.1_.md) - [4.3 ](/docs/1_/chapter4_/chapter4.1_.md) - [4.4 LSTM](/docs/1_/chapter4_/chapter4.4_LSTM.md) - [4.5 GRU](/docs/1_/chapter4_/chapter4.5_.md) - - - - 5 [](/docs/1_/chapter5_/chapter5_.md) - 5.1 [](/docs/1_/chapter5_/chapter5_.md#51-) - 5.2 [(Graph Neural Network)](https://www.cnblogs.com/SivilTaram/p/graph_neural_network_1.html) - 5.2.1 [](/docs/1_/chapter5_/chapter5_.md#51-) - 5.2.2 [](/docs/2_/chapter8_/chapter8.1_.md#812-pytorch) - 5.2.3 [](/docs/2_/chapter8_/chapter8.1_.md#813-) - 5.2.4 []() - 5.2.5 [GNNRNN](/docs/2_/chapter8_/chapter8.2_BenchMark.md) - 5.2.6 [GNN]() - 5.3 [(Gated Graph Neural Network)]() - 5.3.1 - 5.3.2 1: - 5.3.3 2: - 5.3.4 GNNGGNN - 5.4 [(GCNN)](https://www.cnblogs.com/SivilTaram/p/graph_neural_network_2.html) - 5.4.1 - 5.4.2 (Framework) - 5.4.3 - 5.4.4 (Spatial Convolution) - 5.4.5 (Message Passing Neural Network) - 5.4.6 (Graph Sample and Aggregate) - 5.4.7 (PATCHY-SAN) - 5.4.8 (Spectral Convolution) - 5.5 [](https://www.cnblogs.com/SivilTaram/p/graph_neural_network_3.html) - 5.5.1 (ReadOut) - 5.5.2 (Statistics Category) - 5.5.3 (Learning Category) - 5.5.4 - 5.6 [](https://www.cnblogs.com/SivilTaram/p/graph_neural_network_3.html) - 5.6.1 [](https://arxiv.org/abs/1904.03751) - 5.6.2 [](https://openreview.net/forum?id=SJeXSo09FQ) - 5.6.3 [RGBD](https://www.cs.toronto.edu/~urtasun/publications/qi_etal_iccv17.pdf) - 5.6.4 [VQA](https://visualqa.org/) - 5.6.5 [ZSL](https://arxiv.org/pdf/1803.08035.pdf) - - - 5 [](/notebooks/) - 5.1 [](/notebooks/) - 5.2 [](/notebooks/) - 5.3 [](/notebooks/) - 5.4 [](/notebooks/) - 5.5 [](/notebooks/) - - - 6 [](/notebooks/chapter07_optimization/) - 6.1 [](/notebooks/chapter07_optimization/7.1_optimization-intro.ipynb) - 6.2 [](/notebooks/chapter07_optimization/7.2_gd-sgd.ipynb) - 6.3 [](/notebooks/chapter07_optimization/7.3_minibatch-sgd.ipynb) - 6.4 [](/notebooks/chapter07_optimization/7.4_momentum.ipynb) - 6.5 [AdaGrad](/notebooks/chapter07_optimization/7.5_adagrad.ipynb) - 6.6 [RMSProp](/notebooks/chapter07_optimization/7.6_rmsprop.ipynb) - 6.7 [AdaDelta](/notebooks/chapter07_optimization/7.7_adadelta.ipynb) - 6.8 [Adam](/notebooks/chapter07_optimization/7.8_adam.ipynb) - - -

- 6 [](https://charmve.github.io/computer-vision-in-action/#/chapter6/chapter6) - 6.1 [](docs/2_/chapter6_/chapter6.1_.md) - 6.2 [Pytorch ](docs/2_/chapter6_/chapter6.2_Pytorch-.md) - 6.2.1 [Tensors](docs/2_/chapter6_/chapter6.2_Pytorch-.md#621-tensors) - 6.2.2 [Operations](docs/2_/chapter6_/chapter6.2_Pytorch-.md#622-operations) - 6.2.3 [Numpy](docs/2_/chapter6_/chapter6.2_Pytorch-.md#623-numpy) - 6.2.4 [CUDA Tensors](docs/2_/chapter6_/chapter6.2_Pytorch-.md#624-cuda-tensors) - 6.3 [Python](./notebooks/chapter08_environment-setup-and-tool-use/02_Python.ipynb) - 6.4 [Numpy ](./notebooks/chapter08_environment-setup-and-tool-use/03_NumPy.ipynb) - 6.5 [Pandas ](./notebooks/chapter08_environment-setup-and-tool-use/04_Pandas.ipynb) - 6.6 [OpenCV ](./notebooks/chapter08_environment-setup-and-tool-use/OpenCV-ImageStitching.ipynb) - 6.7 [Jupyter Notebook ](./notebooks/chapter08_environment-setup-and-tool-use/01_Notebooks.ipynb) - 6.8 [](docs/2_/chapter6_/chapter6.8_.md) - 6.8.1 [PILPython](docs/2_/chapter6_/chapter6.8_.md#781-pil-python) - 6.8.2 [Matplotlib](docs/2_/chapter6_/chapter6.8_.md#782-matplotlib) - 6.8.3 [NumPy](docs/2_/chapter6_/chapter6.8_.md#783-numpy) - 6.8.4 [SciPy](docs/2_/chapter6_/chapter6.8_.md#784-scipy) - 6.8.5 [](docs/2_/chapter6_/chapter6.8_.md#785--) - 6.9 [ 5 - OpenCV](https://blog.csdn.net/Charmve/article/details/107897468) - - - 7 [PyTorch](https://github.com/Charmve/Semantic-Segmentation-PyTorch) - 7.1 [LeNet](docs/2_/chapter7_-PyTorch/7.1%20LeNet.md) - 7.2 [AlexNet](docs/2_/chapter7_-PyTorch/7.2%20AlexNet.md) - 7.3 [VGG](docs/2_/chapter7_-PyTorch/7.3%20VGG.md) - 7.4 [GoogLeNet](docs/2_/chapter7_-PyTorch/7.4%20GoogLeNet.md) - 7.5 [ResNet](docs/2_/chapter7_-PyTorch/chapter7.6_-ResNet.md) - 7.6 [U-Net](docs/2_/chapter7_-PyTorch/chapter7.7_-UNet.md) - 7.7 [DenseNet](docs/2_/chapter7_-PyTorch/chapter7.8_-DenseNet.md) - 7.8 [SegNet](docs/2_/chapter7_-PyTorch/chapter7.9_-SegNet.md) - 7.9 [Mask-RCNN](docs/2_/chapter7_-PyTorch/chapter7.9_-Mask-RCNN.md) - 7.10 [R-CNN](docs/2_/chapter7_-PyTorch/chapter7.10_-RCNN.md) - 7.11 [FCN](docs/2_/chapter7_-PyTorch/chapter7.11_-FCN.md) - 7.12 [YOLO: ](https://pjreddie.com/darknet/yolo/) - - - 8 [](docs/2_/chapter8_) - 8.1 [](/docs/2_/chapter8_/chapter8.1_.md) - 8.1.1 [](/docs/2_/chapter8_/chapter8.1_.md#811-) - 8.1.1.1 [ImageNet](https://image-net.org/) - 8.1.1.2 [MNIST](http://yann.lecun.com/exdb/mnist/) - 8.1.1.3 [COCO](https://cocodataset.org/) - 8.1.1.4 [CIFAR-10](http://www.cs.toronto.edu/~kriz/cifar.html) - 8.1.2 [Pytorch](/docs/2_/chapter8_/chapter8.1_.md#812-pytorch) - 8.1.3 [](/docs/2_/chapter8_/chapter8.1_.md#813-) - [](/docs/2_/chapter8_/chapter8.1_.md#) - 8.2 [](/docs/2_/chapter8_/chapter8.2_BenchMark.md) - 8.3 [](/chapter8.3_.md) - 8.4 [ 6 - KaggleCIFAR-10](docs/2_/chapter7_-PyTorch/7.12%20KaggleCIFAR-10.md) - 8.5 [ 7 - KaggleImageNet Dogs](docs/2_/chapter7_-PyTorch/7.13%20KaggleImageNet%20Dogs.md) - - - 9 [](https://charmve.github.io/computer-vision-in-action/#/chapter9/chapter9) - 9.1 - 9.1.1 [ PyTorch ](https://github.com/Charmve/Semantic-Segmentation-PyTorch) - 9.1.2 [ 8 - PolarNet]() - 9.2 - 9.2.1 - 9.2.2 [ 9 - PyTorchYOLO5]() - 9.3 [](/docs/2_/chapter9_/9.3%20.md) - 9.3.1 [](/docs/2_/chapter9_/9.3%20.md#931-) - 9.3.2 [ 10 - ](/docs/2_/chapter9_/9.3%20.md#932--8-) - 9.3.3 [](https://blog.csdn.net/Charmve/article/details/108915225), [PointRend](https://blog.csdn.net/Charmve/article/details/108892076), [PolarMask](https://github.com/xieenze/PolarMask) - - - 10 [](https://charmve.github.io/computer-vision-in-action/#/chapter10/chapter10) - 10.1 [](https://blog.csdn.net/Charmve/article/details/108531735) - 10.2 [](https://github.com/Charmve/Scene-Text-Detection) - 10.3 [](https://github.com/Charmve/Awesome-Lane-Detection) - 10.3.1 [](https://github.com/Charmve/Awesome-Lane-Detection) - 10.3.2 [ 11 - ](https://blog.csdn.net/Charmve/article/details/116678477) - 10.4 [](https://github.com/Charmve/Mirror-Glass-Detection) - 10.5 [ Matting](/docs/2_/chapter10_/charpter10_5-.md) - 10.6 [](/docs/2_/chapter10_/charpter10_6-.md) - 10.7 [3D ](/docs/2_/chapter10_/charpter10_7-3D.md) - - -

- 11 [](/docs/3_/chapter11-/) - 11.1 - 11.2 - 11.3 - 11.4 [Embeddings](https://nbviewer.jupyter.org/format/slides/github/Charmve/computer-vision-in-action/blob/main/notebooks/chapter13_Understanding-and-Visualizing/Embeddings.ipynb) - 11.5 - 11.6 [DeepDream ](/docs/3_/chapter12-/chapter12.3.3_neural-style.md) - 11.7 [ 12: PyTorch TensorBoard](/docs/3_/chapter11-/chapter11-.md) - 11.4.1 [ TensorBoard](/docs/3_/chapter11-/chapter11-.md#1141--tensorboard) - 11.4.2 [ TensorBoard](/docs/3_/chapter11-/chapter11-.md#1142--tensorboard) - 11.4.3 [ TensorBoard ](/docs/3_/chapter11-/chapter11-.md#1143--tensorboard-) - 11.4.4 [ TensorBoard "Projector"](/docs/3_/chapter11-/chapter11-.md#1144--tensorboard--projector) - 11.4.5 [ TensorBoard ](/docs/3_/chapter11-/chapter11-.md#1145--tensorboard-) - 11.4.6 [ TensorBoard ](/docs/3_/chapter11-/chapter11-.md#1146--tensorboard-) - 11.4.7 [](/docs/3_/chapter11-/chapter11-.md#) - - - 12 [](https://charmve.github.io/computer-vision-in-action/#/chapter6/chapter6) - 12.1 Pixel RNN/CNN - 12.2 [ Auto-encoder](/docs/3_/chapter12-/chapter12_2-Auto-encoder.md) - 12.3 [ GAN](/docs/3_/chapter12-/chapter12.3_GAN.md) - 12.3.1 [](/docs/3_/chapter12-/chapter12.3_GAN.md#1231-) - 12.3.2 [GAN](/docs/3_/chapter12-/chapter12.3_GAN.md#1232-gan) - 12.3.3 [GAN](/docs/3_/chapter12-/chapter12.3_GAN.md#1233-gan) - 12.3.3.1 [GAN](/docs/3_/chapter12-/chapter12.3_GAN.md#12331-gan) - 12.3.3.2 [GAN](/docs/3_/chapter12-/chapter12.3_GAN.md#12332-gan) - [](/docs/3_/chapter12-/chapter12.3_GAN.md#) - [](/docs/3_/chapter12-/chapter12.3_GAN.md#) - [](/docs/3_/chapter12-/chapter12.3_GAN.md#) - 12.3.4 [](/docs/3_/chapter12-/chapter12.3_GAN.md#1234) - 12.3.5 StyleGAN - [StyleGAN](https://github.com/Charmve/VOGUE-Try-On) - [StyleGAN 2.0](https://blog.csdn.net/Charmve/article/details/115315353) - 12.3.6 [11 - ](/docs/3_/chapter12-/chapter12.3.3_neural-style.md) - [](/docs/3_/chapter12-/chapter12.3_GAN.md#) - [](/docs/3_/chapter12-/chapter12.3_GAN.md#) - 12.4 [ Variational Auto-encoder, VAE](docs/3_/chapter12-/chapter12_4-VAE.md) - 12.4.1 [](docs/3_/chapter12-/chapter12_4-VAE.md#1241-) - 12.4.2 [](docs/3_/chapter12-/chapter12_4-VAE.md#1242-) - 12.4.2.1 [](docs/3_/chapter12-/chapter12_4-VAE.md#1-) - 12.4.2.2 [](docs/3_/chapter12-/chapter12_4-VAE.md#2-) - 12.4.2.3 [](docs/3_/chapter12-/chapter12_4-VAE.md#3-) - 12.4.3 [VAE v.s. AE ](docs/3_/chapter12-/chapter12_4-VAE.md#1243-vae-vs-ae-) - 12.4.4 [](docs/3_/chapter12-/chapter12_4-VAE.md#1244-) - 12.4.5 [](docs/3_/chapter12-/chapter12_4-VAE.md#1245-) - 12.4.6 [ 13 - ](https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life) - - [](docs/3_/chapter12-/chapter12_4-VAE.md#) - - 13 [](/docs/3_/chapter13-/chapter13-.md) - 13.1 [-](/docs/3_/chapter13-/chapter13-.md#141--) - 13.2 [](/docs/3_/chapter13-/chapter13-.md#142-) - 13.2.1 [](/docs/3_/chapter13-/chapter13-.md#1421-) - 13.2.2 [](/docs/3_/chapter13-/chapter13-.md#1422-) - 13.2.3 [](/docs/3_/chapter13-/chapter13-.md#1423-) - 13.3 [](/docs/3_/chapter13-/chapter13-.md#143-) - 13.3.1 [Policy-based DRL](/docs/3_/chapter13-/chapter13-.md#1431-policy-based-drl) - 13.3.2 [Value-based DRL](/docs/3_/chapter13-/chapter13-.md#1432-value-based-drl) - 13.3.3 [Model-based DRL](/docs/3_/chapter13-/chapter13-.md#1433-model-based-drl) - 13.4 [](#144-) - [](/docs/3_/chapter13-/chapter13-.md#) - [](/docs/3_/chapter13-/chapter13-.md#) - 14 [](/docs/3_/chapter14-/chapter14-.md) - 14.1 [](/docs/3_/chapter14-/chapter14-.md#141-) - 14.2 [](/docs/3_/chapter14-/chapter14-.md#142-) - 14.3 [](/docs/3_/chapter14-/chapter14-.md#143-) - 14.4 [](/docs/3_/chapter14-/chapter14-.md#144-) - 14.5 [ METRICS](/docs/3_/chapter14-/chapter14-.md#145--metrics) - 14.6 [](/docs/3_/chapter14-/chapter14-.md#146-) - [](/docs/3_/chapter14-/chapter14-.md#) - [](/docs/3_/chapter14-/chapter14-.md#) - 15 [](./docs/3_/chapter15_) - 15.1 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#151-) - 15.1.1 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#1511-) - 15.1.2 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#1512-) - 15.1.3 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#1513-) - 15.2 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#152-) - 15.3 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#153-) - 15.4 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#154-) - 15.5 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#155-) - 15.7 [ 14 - ](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md) - 15.7.1 [](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#1571-) - 15.7.2 [: ](https://github.com/Charmve/computer-vision-in-action/tree/main/docs/3_/chapter15_/chapter15_.md#1572--) - [](#) - [](#) - 16 [ Attention is All You Need](./notebooks/chapter16_Attention/1_Attention.ipynb) - 16.1 - 16.2 Attention with RNNs - 16.3 [Self-attention ](https://mp.weixin.qq.com/s/nUd7YtCci1_AwQ4nOwK9bA) - 16.4 soft-attention - 16.4.1 - 16.4.2 - 16.4.3 Positional encoding - 16.4.4 - 16.4.5 Masked attention - 16.4.6 Multi-head attention - 16.5 hard attention - 16.6 [Attention - ](/docs/3_/chapter16-%20Attention%20is%20All%20You%20Need/chapter16_Attention-is-All-You-Need.md) - - - 17 [ Transformer](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md) - 17.1 [](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#%E4%B8%80%E6%80%9D%E6%83%B3%E5%92%8C%E6%A1%86%E5%9B%BE) - 17.2 [](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#) - [17.2.1 Encoder](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#2-1-Encoder) - [17.2.2 Decoder](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#2-2-Decoder) - [17.2.3 Self-Attention](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#2-3-Self-Attention) - [17.2.4 Multi-Headed Attention](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#2-4-Multi-Headed-Attention) - [17.2.5 Positional Encoding](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#2-5-Positional-Encoding) - 17.3 [](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#-) - 17.3.1 [NLP](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#3-1-NLP) - 17.3.2 [CV](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#3-2-CV) - 17.3.2.1 [DETR](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#3-2-1-DETR) - 17.3.2.2 [ViT](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#3-2-2-ViT) - 17.3.2.3 [SETR](https://github.com/Charmve/computer-vision-in-action/blob/main/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#3-2-3-SETR) - 17.3.2.4 [Deformable-DETR](https://github.com/Charmve/computer-vision-in-action/blob/main/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#3-2-4-Deformable-DETR) - 17.4 [](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#-) - 17.5 [](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#-) - [ 15 - TransformerVisTR (CVPR2021)](https://blog.csdn.net/Charmve/article/details/115339803) - - [](/docs/3_%E8%BF%9B%E9%98%B6%E7%AF%87/chapter17-%E8%B7%A8%E7%95%8C%E6%A8%A1%E5%9E%8B%20Transformer/chapter17_Transformer.md#-) - 18 [](https://mp.weixin.qq.com/s/e3c_-rs2rncmWhbm-cU5rA) - 18.1 - 18.2 KD - 18.2.1 Logits(Response)-based Knowledge - 18.2.2 Feature-based Knowledge - 18.2.3 Relation-based Knowledge - 18.3 NLP-BERT - 18.4 - [ 16 - CVPR](https://mp.weixin.qq.com/s/RTkBQJ7Uj86Wxt7HmwWKzA) - - [](#) - 19 [Normalization ](https://blog.csdn.net/Charmve/article/details/107650487) - 19.1 Mini-Batch SGD - 19.2 Normalization - 19.3 Batch Normalization - 19.3.1 BN - 19.3.2 CNNBN - 19.3.3 Batch Norm - 19.4 Layer NormalizationInstance NormalizationGroup Normalization - 19.4.1 Layer Normalization - 19.4.2 Instance Normalization - 19.4.3 Group Normalization - 19.4.4 - 19.5 NormalizationRe-Scaling - 19.6 Batch Normalization - - [](#) - 20 [](https://mp.weixin.qq.com/s/e3c_-rs2rncmWhbm-cU5rA) - 20.1 - 20.2 - 20.2.1 1990~2014 - - 20.2.2 1989~2014 - - 20.2.3 2016 - - 20.2.4 - 20.2.5 2014- - 20.3 - 20.3.1 Op-Level - 20.3.2 Layer0-level - 20.3.3 - CPUGPUNPU - ASIC FPGA - PIMNDP - 20.4 - 20.4.1 TensorRT Nvidia) - 20.4.2 TVM (Tensor Virtual Machine) - 20.4.3 Tensor Comprehension (Facebook) - 20.4.4 Distiller (Intel) - - [](#-) -

- A - B [](https://mp.weixin.qq.com/s?__biz=MzIxMjg1Njc3Mw==&mid=2247484495&idx=1&sn=0bbb2094d93169baf20eedb284bc668f) - C [](https://blog.csdn.net/Charmve/article/details/106089198) - D [](https://blog.csdn.net/Charmve/article/details/107650479) -

[](/docs/book_postscript.md)

 -

[](#-1)
- ...
[](#-)

Index

docs/ 1 code/ 2 Colab notebooks/ 3

  • L0CV/ - L0CV
  • code/ -
  • datasets/ -
    • images/ -
  • docs/ -
    • 0_/ -
    • 1_/ -
    • 2_/ -
    • 3_/ - CV
    • / -
    • img/ -
  • models/ -
  • notebooks/ - Colab notebook Binder
    • chapter01_neural-networks/ - 1 - Jupyter Notebook
    • chapter02_CNN/ - 2 - Jupyter Notebook
    • chapter03_Image-Classification - 3 - Jupyter Notebook
    • chapter04_recurrent-neural-networks/ - 4 - Jupyter Notebook
    • chapter05_graph-neural-network/ - 5 - Jupyter Notebook
    • chapter07_optimization/ - 6 - Jupyter Notebook
    • chapter08_environment-setup-and-tool-use/ - 7 - Jupyter Notebook
    • chapter09_convolutional-neural-networks/ - 8 - PyTorch Jupyter Notebook
    • chapter12_practice-projects - 12 - Jupyter Notebook
    • chapter13_Understanding-and-Visualizing/ - 13 - Jupyter Notebook
    • chapter14_GAN/ - 14 - Jupyter Notebook
    • chapter15_Transfer-Learning/ - 15 - Jupyter Notebook
    • Go for it!
    • chapter16_Attention/ - 16 - Jupyter Notebook
    • chapter17_Transformers/ - 17 - Transformers Jupyter Notebook
    • ...
    • imgs/ - Jupyter Notebook
    • docker/ -
    • res/ - ui PDF
    • README.md -

Index

L0CV DemoDay

L0CV-Universe

L0CV

V1.2 *


| | | Binder | Google Colab | | :-- | :---| :---:| :---: | | 1 - | 1 - | | | | 2 - | 2 - | | | | 3 - | 3 - | | | | 4 - CIFAR10 | 3 - | | | | 5 - OpenCV | 6 - | Binder | | | 6 - KaggleCIFAR-10 | 8 - | Binder | | | 7 - KaggleImageNet Dogs | 8 - | Binder | | | 8 - PolarNet | 9 - || | | 9 - PyTorchYOLO5 | 9 - || | | 10 - | 9 - || | | 11 - | 10 - | | | | 12 - PyTorch TensorBoard | 13 - | | | | 13 - | 14 | Binder | | | 14 - | 14 - | Binder | | | 15 - | 14 - | Binder | | | 16 - SlowFast + Multi-Moments in Time | 16 - | Binder | | | 17 - | 17 - | Binder | | | 18 - TransformerVisTR (CVPR2021) | 19 - Transformer | | | | 19 - CVPR| 20 - | | | | ... | ... | ... |


Index

### Jupyter Notebook ( ) #### 1. - ``` pip3 install -r requirements.txt ``` - Jupyter ``` python3 -m pip install --upgrade pip python3 -m pip install jupyter ``` - jupyter Mac / LinuxWindows ```shell cd notebooks jupyter notesbook ``` #### 2. - Google Colab Copy to Drive [Copy to Drive] - Binder ``mybinder``

Run on Colab
2 12.3.3

Copy to Drive
3 12.3.3 Colab Copy to Drive [Copy to Drive]

### ``/code`` #### 1. + L0CV - ```shell sudo apt-get update pip3 install -r requirements.txt ``` - L0CV ```shell python3 setup.py ``` - ```shell cd code python3 L0CV_test.py ``` #### 2. ```python3 import L0CV ```
[](#-)

Jupyter

Run
locally

Google
Colab

+ +

Index

  • host

    : host Apple Mac Win10 Windows

  • GitHubMarkdownLATEXChromeMathJax Plugin for GithubdocsdocsifyGitHub Pages

    clonecode

  • *Jupyter Notebook GitHub * nbviewer Binder

Index

AI Made With ML       360

Index

Index

LICENSE

Code License

  • L0CV Apache 2.0 L0CV /code/notebook

    • ****
    • ****Apache 2.0

  • L0CV 4.0

    • ****
    • ****
    • **** 4.0

Index

  • GitHub Discuss Q&A

  • Stack Overflow Segment Fault L0CV

  • Segment Fault tag #L0CV

  • L0CV (Yida_Zhang2L0CV-/-)

Index

Support this project

Donating to help me continue working on this project. I'm appreciate all you in backer list. BuymeaCoffee

Buy Me A Coffee

CONTRIBUTION

Help us make these docs great!

All VC-action docs are open source. See something that's wrong or unclear? Submit a pull request.

Make a contribution

Or, learn how to contribute.

Index

Citation

Use this bibtex to cite this repository: @misc{computer-vision-in-action, title={Computer Vision in Action}, author={Charmve}, year={2021.06}, publisher={Github}, journal={GitHub repository}, howpublished={\url{https://github.com/Charmve/computer-vision-in-action}}, }

Index

Stargazers Over Time

Awesome! Charmve/computer-vision-in-action was created 2 months ago and now has 1546 stars.

Stargazers over time


Go for it!

Feel free to ask any questions, open a PR if you feel something can be done differently!

Star this repository

Created by Charmve & maiwei.ai Community | Deployed on GitHub Page

Owner

  • Name: Wei ZHANG
  • Login: Charmve
  • Kind: user
  • Location: Suzhou, Beijing, Shanghai, Hongkong
  • Company: 公众号: 迈微AI研习社

Founder of @MaiweiAI Lab, @UFund-Me and @DeepVTuber. My research interests lie at AI Infra, Machine Learning and Computer Vision.

GitHub Events

Total
  • Watch event: 234
  • Issue comment event: 5
  • Fork event: 27
Last Year
  • Watch event: 234
  • Issue comment event: 5
  • Fork event: 27

Committers

Last synced: 8 months ago

All Time
  • Total Commits: 575
  • Total Committers: 4
  • Avg Commits per committer: 143.75
  • Development Distribution Score (DDS): 0.103
Past Year
  • Commits: 1
  • Committers: 1
  • Avg Commits per committer: 1.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Wei ZHANG y****1@g****m 516
Charmve z****3@3****n 57
张益达 z****a@z****l 1
xetdata[bot] 1****] 1
Committer Domains (Top 20 + Academic)
360.cn: 1

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 75
  • Total pull requests: 1
  • Average time to close issues: 4 days
  • Average time to close pull requests: N/A
  • Total issue authors: 11
  • Total pull request authors: 1
  • Average comments per issue: 0.64
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • Charmve (65)
  • wyyaa123 (1)
  • YJHnu (1)
  • jinzhedu (1)
  • yuan243212790 (1)
  • fyzm (1)
  • Zhong-master (1)
  • DoveJing (1)
  • ezio1320 (1)
  • jackiehym (1)
  • XiaYuanxiang (1)
Pull Request Authors
  • TrellixVulnTeam (1)
Top Labels
Issue Labels
Gitalk (63) chapter0.1_概述 (3) 📑/README (3) 👐 open-question (3) chapter0.3_发展历史回顾 (2) 📑 /book_preface (2) book_preface (2) 📁 documentation (2) chapter0.2_基本概念辨析 (2) 📘 book (2) 🏇wontfix (2) README (2) 🐞 bug (2) 📑 /0_绪论/README (2) chapter0.4_典型的计算机视觉任务 (1) chapter3.2_knn (1) REFERENCE (1) chapter2_CNN-in-Action (1) chapter13-深度增强学习 (1) chapter8.1_著名数据集 (1) 7.1 卷积神经网络（LeNet） (1) chapter1.4_Back-Propagation (1) chapter2_CNN (1) chapter14-视频理解 (1) 📑 /1_理论篇/chapter2_CNN/README (1) 📚 书籍推荐 (1) 👽 interesting things (1) 🐍Python (1) chapter0.1_%E6%A6%82%E8%BF%B0 (1) home (1)
Pull Request Labels

Dependencies

.github/workflows/codeql-analysis.yml actions
  • actions/checkout v2 composite
  • github/codeql-action/analyze v1 composite
  • github/codeql-action/autobuild v1 composite
  • github/codeql-action/init v1 composite