https://github.com/hari31416/revision
This is a project where I'm trying to recreate some of the ground breaking papers in computor vision using Tensorflow and/or Pytorch.
https://github.com/hari31416/revision
computer-vision deep-learning personal-project python
Last synced: 2 months ago
JSON representation
This is a project where I'm trying to recreate some of the ground breaking papers in computor vision using Tensorflow and/or Pytorch.
- Host: GitHub
- URL: https://github.com/hari31416/revision
- Owner: Hari31416
- Created: 2023-02-26T09:00:42.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-04-07T12:54:37.000Z (over 3 years ago)
- Last Synced: 2025-06-03T20:55:10.342Z (about 1 year ago)
- Topics: computer-vision, deep-learning, personal-project, python
- Language: Jupyter Notebook
- Homepage:
- Size: 21.3 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# ReVision
This is a project where I'm trying to recreate all the ground breaking papers in computor vision using Tensorflow and Pytorch, and hence the name ReVision. The goal is to learn the concepts and the implementation details of the papers, and also to learn how to use Tensorflow and Pytorch. The papers and architectures which I'm planning to implement are listed below.
> Please have a look at the file `How_to_Use.md` for information on how to use this repository.
## Papers/Architectures
### LeNet
LeNet is a convolutional neural network which was proposed by Yann LeCun in 1998. It was the first convolutional neural network which was used to classify handwritten digits. The paper can be found [here](http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf).
- [ ] Doing
- [x] Done
### AlexNet
AlexNet is a convolutional neural network which was proposed by Alex Krizhevsky, Ilya Sutskever and Geoffrey Hinton in 2012. It was the first convolutional neural network which was used to classify images. The paper can be found [here](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf).
- [ ] Doing
- [x] Done
### VGG
VGG is a convolutional neural network which was proposed by Karen Simonyan and Andrew Zisserman in 2014. It achieved state-of-the-art results on the ImageNet classification challenge. The paper can be found [here](https://arxiv.org/pdf/1409.1556.pdf).
- [ ] Doing
- [x] Done
### ResNet
ResNet is a convolutional neural network which was proposed by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun in 2015. It introduced the concept of residual connections, which enabled the training of very deep neural networks. The paper can be found [here](https://arxiv.org/pdf/1512.03385.pdf).
- [ ] Doing
- [x] Done
### Inception
Inception (also known as GoogleNet) is a convolutional neural network which was proposed by Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich in 2014. It introduced the concept of inception modules, which allowed for more efficient and accurate feature extraction. The paper can be found [here](https://arxiv.org/pdf/1409.4842.pdf).
- [ ] Doing
- [x] Done
### MobileNet
MobileNet is a family of convolutional neural networks which was proposed by Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam in 2017. It was designed to be computationally efficient and suitable for mobile and embedded devices. The paper can be found [here](https://arxiv.org/pdf/1704.04861.pdf).
- [ ] Doing
- [x] Done
### EfficientNet
EfficientNet is a family of convolutional neural networks which was proposed by Mingxing Tan and Quoc V. Le in 2019. It achieved state-of-the-art results on the ImageNet classification, COCO object detection, and OpenImages image classification benchmarks while being highly parameter-efficient. The paper can be found [here](https://arxiv.org/pdf/1905.11946.pdf).
- [ ] Doing
- [x] Done
### DenseNet
DenseNet is a convolutional neural network which was proposed by Gao Huang, Zhuang Liu, Kilian Q. Weinberger, and Laurens van der Maaten in 2016. It introduced the concept of dense connections, which enabled feature reuse and improved parameter efficiency. The paper can be found [here](https://arxiv.org/pdf/1608.06993.pdf).
- [ ] Doing
- [x] Done
> Later, this list will be updated with more papers and architectures.
>
> For a full list of papers and architectures, check out the notion page [here](https://swamp-water-c4a.notion.site/10a70e2c390f4e119cb709b712d3b168?v=8224d1d9652e48fd83100ab516a228d3).