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.
Tensorflow implementation of "Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network"
| Date | Stars |
|---|---|
| 2026-07-24 | 326 |
| 2026-07-25 | 326 |
| 2026-07-28 | 326 |
| 2026-07-30 | 326 |
| 2026-07-31 | 326 |
| 2026-08-06 | 326 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network ## What's New July 11, 2020 * We reimplemented assemble-resnet with tensorflow 2.1. If you want to see the code with better readability, refer to [this branch](https://github.com/clovaai/assembled-cnn/tree/tf2.1). [paper v2](https://arxiv.org/abs/2001.06268) | [pretrained model](https://drive.google.com/drive/folders/1o8vj8_ZOPByjRKZzRPZMbuoKyxIwd_IZ?usp=sharing) Official Tensorflow implementation > [Jungkyu Lee](mailto:[email protected]), [Taeryun Won](mailto:[email protected]), [Tae Kwan Lee](mailto:[email protected]), > [Hyemin Lee](mailto:[email protected]), [Geonmo Gu](mailto:[email protected]), [Kiho Hong](mailto:[email protected])<br/> > @NAVER/LINE Vision **Abstract** > Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g., ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3% to 82.78%, mCE from 76.0% to 48.9% and mFR from 57.7% to 32.3% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019 <p align="center"> <img src="./figures/summary_architecture.png" align="center" width="1000" title="summary_architecture"> </p> ## Main Results ### Summary of key results <p align="center"> <img src="./figures/summary_table.png" align="center" width="500" title="summary_table" > </p> ### Ablation Study <p align="center"> <img src="./figures/ablation_study_imagenet.png" align="center" width="1000" title="summary_table"> </p> <p align="center"> <img src="./figures/ablation_study_mobilenet.png" align="center" width="1000" title="summary_table"> </p> ### Transfer learning <p align="center"> <img src="./figures/FGVC.png" align="center" width="700" title="FGVC"> </p> ## Honor * Based on our repository, we achieved 1st place in [iFood Competition Fine-Grained Visual Recognition at CVPR 2019](https://www.kaggle.com/c/ifood-2019-fgvc6/leaderboard). ## Related links Thankfully some people have written testimonial and posts related to our paper. * [Jeremy Howard's testimonial tweet](https://twitter.com/jeremyphoward/status/1219695492927328256) * [Stan Kriventsov's summary post](https://dl.reviews/2020/01/26/compounding-resnet-improvements/) * [akira's summary post](https://medium.com/analytics-vidhya/assemble-resnet-that-is-5-times-faster-with-the-same-accuracy-as-efficientnet-b6-autoaugment-c752f1835c38) * [norman3(one of authurs)'s korean version paper](https://norman3.github.io/papers/docs/assembled_cnn) ## Tutorial: Fine-Tuning on Oxford-flower102 As first try, you can fine-tune your flower classifier in colab. [](https://colab.research.google.com/drive/11GJf-frlk_mj30h_cZoRJZ5W6j2lO9HM) ## Getting Started * This work was tested with Tensorflow 1.14.0, CUDA 10.0, python 3.6. ### Requirements ```bash pip install Pillow sklearn requests Wand tqdm ``` ### Data preparation We assume you already have the following data: * ImageNet2012 raw images and tfrecord. For this data, please ref
Excerpt of 9,147 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8035f5e5854f5b5e, topic:computer-vision, topic:image-classification, readme:image classification
matched fp:8035f5e5854f5b5e, topic:deep-learning, topic:tensorflow