Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Revisions and implementations of modern Convolutional Neural Networks architectures in TensorFlow and Keras
| Date | Stars |
|---|---|
| 2026-07-24 | 358 |
| 2026-07-25 | 358 |
| 2026-07-28 | 358 |
| 2026-07-30 | 358 |
| 2026-07-31 | 358 |
| 2026-08-06 | 358 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Modern Convolutional Neural Network Architectures <p style='text-align: justify;'> <a href="https://nbviewer.jupyter.org/github/Nyandwi/ModernConvNets"><img src="https://raw.githubusercontent.com/jupyter/design/master/logos/Badges/nbviewer_badge.svg" alt="Render nbviewer" /> </a> <a href="https://colab.research.google.com/github/Nyandwi/ModernConvNets" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> </p> >***Revision of the designs and implementation of Modern Convolutional Neural Network architectures*** ---------  ## Introduction to Convolutional Neural Networks Convolutional Neural Networks (ConvNets or CNNs) are a class of neural networks algorithms that are mostly used in visual recognition tasks such as [image classification](https://twitter.com/Jeande_d/status/1462040682437120001), object detection, and image segmentation. The use of ConvNets in visual recognition is inarguably one of the [biggest inventions of decade 2010s in deep learning community](https://twitter.com/Jeande_d/status/1501188511281549321?s=20&t=dCZzcKKoXgvVL_8ebVDclg). A standard ConvNet architecture is typically made of 3 main layers that are convolution, max-pooling, and fully connected layers. Convolution layers are the main component of ConvNets. They are used for extracting features in images using filters. Pooling layers are used for downsampling the activation or feature maps produced by convolutional layers. Downsampling can also be achieved by using strides(greater than 1) in a normal convolution layer, but max-pooling layers don't have any learnable parameters and they introduce translational invariance which improves model generalization on the cost of [spatial inductive bias](https://samiraabnar.github.io/articles/2020-05/indist). Fully connected layers are used for classification purpose(matching learned features with their respective labels). In classification settings, the last fully connected layer is typically activated with `softmax` activation function! Example of ConvNets architectures that follow the above structure are [AlexNet](convnets/01-alexnet.ipynb) and [VGG](convnets/02-vgg.ipynb). Most modern ConvNet architectures go beyond plain stack of convolution, max-pooling and fully connected layers. For example, architectures like [ResNet](convnets/04-resnet.ipynb) and other alike networks involve residual connections. As you go through the materials in this repository, you will learn more about those architectures and how they are implemented. For more about ConvNets, check [resources section](#further-learning)! ## ConvNet Architectures * AlexNet - Deep Convolutional Neural Networks: [implementation](convnets/01-alexnet.ipynb), [paper](https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf) * VGG - Very Deep Convolutional Networks for Large Scale Image Recognition: [implementation](convnets/02-vgg.ipynb), [paper](https://arxiv.org/pdf/1409.1556.pdf) * GoogLeNet(Inceptionv1) - Going Deeper with Convolutions: [implementation](convnets/03-googlenet.ipynb), [paper](https://arxiv.org/abs/1409.4842) * ResNet - Deep Residual Learning for Image Recognition: [implementation](convnets/04-resnet.ipynb), [annotated paper](annotated_papers/resnet.pdf) [paper](https://arxiv.org/abs/1512.03385) * ResNeXt - Aggregated Residual Transformations for Deep Neural Networks: [implementation](convnets/06-resnext.ipynb), [annotated paper](annotated_papers/resnext.pdf), [paper](https://arxiv.org/abs/1611.05431v2) * Xception - Deep Learning with Depthwise Separable Convolutions: [implementation](convnets/07-xception.ipynb), [annotated paper](annotated_papers/xception.pdf), [paper](https://arxiv.org/abs/1610.02357) * DenseNet - Densely Connected Convolutional Neural Networks: [implementation](convnets/05-densenet.ipynb), [annotated paper](annotated_papers/densenet.pdf), [paper](https://arxiv.org/abs/160
Excerpt of 10,900 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7868865a291ec817, topic:computer-vision, topic:image-classification, readme:object detection